WO2023068148A1 - Prediction/estimation system, learning device, and prediction/estimation device - Google Patents

Prediction/estimation system, learning device, and prediction/estimation device Download PDF

Info

Publication number
WO2023068148A1
WO2023068148A1 PCT/JP2022/038127 JP2022038127W WO2023068148A1 WO 2023068148 A1 WO2023068148 A1 WO 2023068148A1 JP 2022038127 W JP2022038127 W JP 2022038127W WO 2023068148 A1 WO2023068148 A1 WO 2023068148A1
Authority
WO
WIPO (PCT)
Prior art keywords
prediction
estimation
variable
data
latent
Prior art date
Application number
PCT/JP2022/038127
Other languages
French (fr)
Japanese (ja)
Inventor
賢一 堀内
修平 桑田
Original Assignee
株式会社アマダ
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 株式会社アマダ filed Critical 株式会社アマダ
Publication of WO2023068148A1 publication Critical patent/WO2023068148A1/en

Links

Images

Classifications

    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B23—MACHINE TOOLS; METAL-WORKING NOT OTHERWISE PROVIDED FOR
    • B23K—SOLDERING OR UNSOLDERING; WELDING; CLADDING OR PLATING BY SOLDERING OR WELDING; CUTTING BY APPLYING HEAT LOCALLY, e.g. FLAME CUTTING; WORKING BY LASER BEAM
    • B23K26/00—Working by laser beam, e.g. welding, cutting or boring
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N33/00—Investigating or analysing materials by specific methods not covered by groups G01N1/00 - G01N31/00
    • G01N33/38—Concrete; Lime; Mortar; Gypsum; Bricks; Ceramics; Glass
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N20/00—Machine learning

Definitions

  • the present invention relates to a prediction/estimation system, a learning device, and a prediction/estimation device.
  • auxiliary variables that are available at the time of prediction/estimation and are other than the objective variable may also be used as variables that have a causal relationship that results when the explanatory variable is the cause. be.
  • the following methods are known for learning such prediction/estimation models.
  • the values of chemical substances in multiple experimental samples are used as teacher data for objective variables, and the near-infrared spectral data converted from the collected spectra of multiple experimental samples, which are teacher data for explanatory variables, are used as part of the data.
  • a random selection is made into the calibration set and partly into the validation set.
  • the calibration set and the validation set are subjected to principal component analysis to obtain a spectral feature space, and in this spectral feature space, the samples in which the calibration set and the validation set are most similar are selected as the calibration subset by the Mahalanobis distance method. Collect as a Syndrome Set.
  • auxiliary variables are correlated with the explanatory variables, so the accuracy of prediction and estimation tends to deteriorate.
  • Such a tendency is widely known as multicollinearity, especially in multiple regression analysis.
  • One aspect of the present invention is a prediction/estimation system, a learning device, and a prediction/estimation device capable of improving the accuracy of prediction/estimation.
  • a prediction/estimation system includes teacher data of an objective variable, teacher data of an explanatory variable acting on the objective variable, and variables other than the objective variable that are correlated with the explanatory variable, a learning device for inputting teacher data of an auxiliary variable observed when the explanatory variable is given, and creating a prediction/estimation model of the objective variable; and the explanation for predicting/estimating the objective variable.
  • a first latent variable calculation unit, training data of the objective variable, training data of the explanatory variable, and training data of the latent variable calculated by the first latent variable calculation unit are input, and the objective variable and a prediction/estimation model learning unit that creates a prediction/estimation model of at least the auxiliary variable, based on the latent variable calculation information, from the prediction/estimation data of the auxiliary variable.
  • a second latent variable calculation unit that calculates prediction/estimation data; and from the prediction/estimation data of the latent variables calculated by the second latent variable calculation unit and the prediction/estimation data of the explanatory variables, the a prediction/estimation unit that calculates a prediction/estimation value of the objective variable based on the prediction/estimation model.
  • the teacher data of the objective variable, the teacher data of the explanatory variables, and the teacher data of the auxiliary variables are input, and at least the teacher data of the auxiliary variables are used to predict the potential variables.
  • Teacher data is calculated, and latent variable calculation information and a prediction/estimation model of objective variables are created. For this reason, by using teacher data of latent variables in which the correlation between explanatory variables and teacher data or between each other is reduced more than that of auxiliary variables, more teacher data can be used, and between teacher data By eliminating correlation, it becomes possible to create a more accurate prediction/estimation model.
  • the data for prediction/estimation of the latent variable is calculated based on the latent variable calculation information, and the calculated data for prediction/estimation of the latent variable and the explanatory variable are combined.
  • the prediction/estimation value of the objective variable is calculated based on the prediction/estimation model. For this reason, more data for prediction/estimation can be used by using prediction/estimation data for latent variables whose correlation between explanatory variables and data for prediction/estimation is reduced more than for auxiliary variables. and the elimination of the correlation between the prediction/estimation data, it becomes possible to obtain a more highly accurate prediction/estimation value of the objective variable.
  • FIG. 1 is an explanatory diagram showing the basic configuration of the prediction/estimation system according to the first embodiment of the present invention.
  • FIG. 2 is an explanatory diagram showing a basic hardware configuration of a learning device and/or a prediction/estimation device of the prediction/estimation system.
  • FIG. 3 is an explanatory diagram showing the basic configuration of the prediction/estimation system according to the second embodiment of the present invention.
  • FIG. 4 is an explanatory diagram showing the basic configuration of the prediction/estimation system according to the third embodiment of the present invention.
  • FIG. 5 is an explanatory diagram showing the basic configuration of the prediction/estimation system according to the fourth embodiment of the present invention.
  • FIG. 1 is an explanatory diagram showing the basic configuration of the prediction/estimation system according to the first embodiment of the present invention.
  • FIG. 2 is an explanatory diagram showing a basic hardware configuration of a learning device and/or a prediction/estimation device of the prediction/estimation system.
  • FIG. 3 is an
  • FIG. 6 is an explanatory diagram showing the basic configuration of the prediction/estimation system according to the fifth embodiment of the present invention.
  • FIG. 7 is an explanatory diagram showing the basic configuration of a welding strength estimation system for laser welding to which a prediction/estimation system according to a sixth embodiment of the present invention is applied.
  • FIG. 8 is an explanatory diagram showing the basic configuration of a learning device of a nondestructive measurement system to which the prediction/estimation system according to the seventh embodiment of the present invention is applied.
  • FIG. 9 is an explanatory diagram showing the basic configuration of a nondestructive testing device of the nondestructive measurement system.
  • FIG. 10 is an explanatory diagram showing the basic configuration of a quality judgment/prediction system for cutting quality of a laser cutting apparatus to which the prediction/estimation system according to the eighth embodiment of the present invention is applied.
  • FIG. 11 is a graph showing the relationship between welding temperature and elapsed time for explaining auxiliary variables in an example in which the prediction/estimation system according to the fourth embodiment shown in FIG. 5 is applied to actual laser welding.
  • FIG. 12 is a graph showing the relationship between estimated values and measured values and the frequency distribution of errors of estimated values with respect to estimated values in Comparative Example and Example.
  • FIG. 1 is an explanatory diagram showing the basic configuration of the prediction/estimation system according to the first embodiment of the present invention.
  • FIG. 2 is an explanatory diagram showing a basic hardware configuration of a learning device and/or a prediction/estimation device of the prediction/estimation system.
  • the prediction/estimation system 100 is a system for obtaining prediction/estimation values 8 of various types of objective variables.
  • the prediction/estimation system 100 includes teacher data 1 of the objective variable, teacher data 2 of the explanatory variable acting on the objective variable, and variables other than the objective variable that are correlated with the explanatory variable, and when the explanatory variable is given and training data 3 of the auxiliary variables observed in the learning device 10 to create a prediction/estimation model 7 of the target variable by, for example, machine learning.
  • the prediction/estimation system 100 includes explanatory variable prediction/estimation data 4 for predicting/estimating the objective variable, and auxiliary variable prediction/estimating data 5 for predicting/estimating the objective variable.
  • a prediction/estimation device 20 is provided for inputting and calculating a prediction/estimation value 8 of an objective variable based on the prediction/estimation model 7 created by the learning device 10 .
  • the learning device 10 generates, from at least the auxiliary variable teacher data 3, latent variable teacher data (reduced correlation) that has a smaller correlation (reduced correlation) with the explanatory variable teacher data 2 than the auxiliary variable teacher data 3 ( (not shown)) and outputs latent variable calculation information 6. Further, the learning device 10 inputs the teacher data 1 of the objective variable, the teacher data 2 of the explanatory variable, and the teacher data of the latent variable calculated by the first latent variable calculator 11, and performs machine learning, for example. and includes a prediction/estimation model learning unit 12 that creates a prediction/estimation model 7 of the objective variable.
  • the prediction/estimation device 20 extracts at least the auxiliary variable prediction/estimation data 5 from the explanatory variable prediction/estimation data 4 rather than the auxiliary variable prediction/estimation data 5 based on the latent variable calculation information 6. It includes a second latent variable calculation unit 21 that calculates prediction/estimation data (not shown) of latent variables with small inter- or inter-correlation (reduced correlation). Further, the prediction/estimation device 20 uses the prediction/estimation data of the latent variables calculated by the second latent variable calculation unit 21 and the prediction/estimation data 4 of the explanatory variables based on the prediction/estimation model 7. , a prediction/estimation unit 22 for calculating the prediction/estimation value 8 of the objective variable.
  • the prediction/estimation system 100 is a system capable of obtaining prediction/estimation values of various types of objective variables as described above.
  • the objective variable is, for example, the welding strength F (N/mm 2 ).
  • explanatory variables include welding conditions (laser output value, laser irradiation time, etc.).
  • auxiliary variables correlated with the explanatory variables include, for example, physical quantities observed during or after welding (welding temperature, sound, light, color, etc.). Note that the objective variable, explanatory variable, and auxiliary variable used in the prediction/estimation system 100 are not limited to these examples.
  • the latent variable teacher data and the latent variable prediction/estimation data calculated by the first latent variable calculation unit 11 of the learning device 10 and the second latent variable calculation unit 21 of the prediction/estimation device 20 are respectively used as auxiliary variables
  • An auxiliary variable, or an auxiliary variable and an explanatory variable are, for example, dimensionality-reduced or dimensionality-compressed so as to reduce the correlation between or between the explanatory variables than the explanatory variables.
  • the latent variable is a variable that characterizes the objective variable in the same way as the explanatory variable, and is a variable that is not directly observed but is estimated from the observed variable (auxiliary variable).
  • a latent variable means a variable that characterizes the observed variable and is dimensionality-reduced or dimensionality-compressed from at least the auxiliary variable.
  • the explanatory variables, objective variables, latent variables, and latent variable calculation information 6 used in the prediction/estimation system 100 can each consist of one or more variables or parameters.
  • "prediction/estimation of the objective variable” is used to mean “prediction of the objective variable” or “estimation of the objective variable”.
  • Prediction of objective variable means to assume an objective variable that is expected to be realized in the future (future).
  • Estimating the objective variable means estimating an objective variable that is currently realized but not directly observable.
  • “Correlation” is not limited to a linear relationship between multiple variables, but regardless of whether it is linear or non-linear, a relationship between multiple variables in which a change in one variable causes a change in the other variables. means.
  • the first latent variable calculation unit 11 of the learning device 10 calculates at least the auxiliary variable out of the data including the objective variable teacher data 1, the explanatory variable teacher data 2, and the auxiliary variable teacher data 3 input to the learning device 10.
  • the teacher data of the latent variables are calculated from the data including the teacher data 3 .
  • the first latent variable calculator 11 calculates latent variable training data using, for example, a predetermined algorithm.
  • Algorithms include, for example, regression analysis (RA), principal component analysis (PCA), singular value decomposition (SVD), linear discriminant analysis (LDA), independent component analysis (Independent Component Analysis: ICA), and at least one of Gaussian Process Latent Variable Model (GPLVM). Note that the algorithms are not limited to these.
  • the latent variable calculation information 6 means various kinds of information that is determined when calculating latent variable teacher data in the first latent variable calculation unit 11 and used when calculating additional latent variables.
  • the latent variable calculation information 6 includes various parameters, various formulas and/or algorithms, for example.
  • the prediction/estimation model learning unit 12 of the learning device 10 receives the objective variable teacher data 1 and the explanatory variable teacher data 2 input to the learning device 10, and the latent variable teacher data calculated by the first latent variable calculator 11. By inputting data, the target variable prediction/estimation model 7 is created by, for example, machine learning. Learning methods include, but are not limited to, algorithms such as regression, classification, clustering, discrimination, interpolation, feature quantity extraction, and time series modeling.
  • the prediction/estimation model 7 learned by the prediction/estimation model learning unit 12 includes various parameters, various formulas and/or algorithms for prediction/estimation that characterize the learning model. Then, the learning device 10 outputs at least the latent variable calculation information 6 and the prediction/estimation model 7 to the prediction/estimation device 20 .
  • the second latent variable calculation unit 21 of the prediction/estimation device 20 calculates prediction/estimation data for latent variables based on the latent variable calculation information 6 from at least the prediction/estimation data 5 for the auxiliary variables. Therefore, when the latent variable calculation information 6 includes an algorithm, the second latent variable calculation unit 21 uses the same algorithm as the one used to calculate latent variable teacher data in the first latent variable calculation unit 11 of the learning device 10. Calculate data for predicting and estimating latent variables using algorithms. In this way, prediction/estimation using the same prediction/estimation model 7 becomes possible by calculating latent variables using the same algorithm as that used in learning during prediction/estimation.
  • the prediction/estimation unit 22 of the prediction/estimation device 20 uses the prediction/estimation data 4 of the explanatory variables input to the prediction/estimation device 20, the prediction/estimation model 7, and the second latent variable calculation unit 21. Based on the latent variable prediction/estimation data, the target variable prediction/estimation value 8 is calculated and output.
  • the latent variable calculation information 6 passed from the learning device 10 side to the prediction/estimation device 20 side can be selected by the learning device 10 or the prediction/estimation device 20 to be suitable for calculating latent variables.
  • the latent variable parameters may be principal component vectors and eigenvalues. It is also possible to select latent variable parameters excluding principal component vectors whose rates are higher than a predetermined value. As a result, it is possible to use the latent variables that have a smaller correlation with or between the explanatory variables than the auxiliary variables, together with the explanatory variables, for the teacher data and prediction/estimation data. aggravation can be avoided.
  • Objective variable teacher data 1, explanatory variable teacher data 2, auxiliary variable teacher data 3, explanatory variable prediction/estimation data 4, and auxiliary variable prediction/estimation data 5 in the prediction/estimation system 100 can be stored, for example, in a stationary or portable storage device or storage medium (not shown). Further, each data can be transmitted and received via an information communication medium such as the Internet, and may be raw data acquired by a measuring device such as a sensor (not shown). Further, the latent variable calculation information 6 and the prediction/estimation model 7 may be input/output between the learning device 10 and the prediction/estimation device 20 via the above storage medium or information communication medium.
  • the learning device 10 and/or the prediction/estimation device 20 of the prediction/estimation system 100 has a basic hardware configuration such as a CPU 201, a RAM 202, a ROM 203, and a HDD (hard disk drive) 204. , an SSD (Solid State Drive) 205 and a memory card 206 .
  • the learning device 10 and/or the prediction/estimation device 20 also includes an input I/F (interface) 207, an output I/F (interface) 208, and a communication I/F (interface) 209, for example.
  • Each component 201 to 209 is interconnected by a bus 200, respectively.
  • the CPU 201 controls the learning device 10 and/or the prediction/estimation device 20 by executing various programs stored in the RAM 202, ROM 203, HDD 204, SSD 205, and the like.
  • the CPU 201 implements the functions of the first latent variable calculation unit 11 and the prediction/estimation model learning unit 12 by executing a learning program in the learning device 10 .
  • the CPU 201 implements the functions of the second latent variable calculation unit 21 and the prediction/estimation unit 22 by executing the prediction/determination program in the prediction/estimation device 20 .
  • the CPUs 201 of the learning device 10 and the prediction/estimation device 20 can be configured to control the entire prediction/estimation system 100 by cooperating.
  • the RAM 202 can be used as a work area for arithmetic processing of the CPU 201.
  • the ROM 203 stores at least the various programs described above in a readable manner.
  • the HDD 204 and SSD 205 store the various data described above in a readable and writable manner.
  • the memory card 206 stores these various data in a readable and writable manner, and constitutes a removable storage medium for each device 10 , 20 .
  • the HDD 204, SSD 205, and memory card 206 implement the functions of the storage device or storage medium described above.
  • a sensor 212 is connected to the input I/F 207 to acquire detection information.
  • the sensor 212 includes various sensors such as a temperature sensor, an optical sensor, an acoustic sensor, and an image sensor.
  • the input I/F 207 is connected to the touch panel 211 functioning as an operation unit or an input unit of the learning device 10 and/or the prediction/estimation device 20, and receives information accompanying an operation input from the user of the prediction/estimation system 100. .
  • Various input devices such as a keyboard and a mouse (including a trackball mouse) (not shown) can also be connected to the input I/F 207 .
  • the touch panel 211 may be provided on the display 210 .
  • the learning device 10 and/or the prediction/estimation device 20 can be indirectly or directly connected to a server device and external devices connected to a network such as the Internet (not shown) via the communication I/F 209 .
  • the first latent variable calculation unit 11 of the learning device 10 calculates latent variable teacher data from data including at least the auxiliary variable teacher data 3, and the latent variable teacher data is calculated.
  • a prediction/estimation model learning unit 12 learns and creates a prediction/estimation model 7 using data including data.
  • the latent variable calculation information 6 determined by the calculation of the teacher data of the latent variables in the learning device 10 is provided to the prediction/estimation device 20 .
  • the second latent variable calculation unit 21 of the prediction/estimation device 20 to which the latent variable calculation information 6 is provided uses the same algorithm as that used by the first latent variable calculation unit 11 to calculate at least auxiliary variables for prediction/estimation.
  • Data for prediction/estimation of latent variables are calculated from data including data 5 . Then, using the data including the latent variable prediction/estimation data, the prediction/estimation unit 22 calculates the prediction/estimation value 8 of the objective variable.
  • the accuracy of prediction/estimation can be improved by converting an auxiliary variable into a latent variable.
  • FIG. 3 is an explanatory diagram showing the basic configuration of the prediction/estimation system according to the second embodiment of the present invention.
  • the same reference numerals are given to the same constituent elements as those of the first embodiment and its modification, so redundant description will be omitted below.
  • the first latent variable calculation unit 11 of the learning device 10 receives teacher data 2 of explanatory variables and teacher data 3 of auxiliary variables. , latent variable teacher data (not shown) is calculated, and latent variable calculation information 6 is output. Further, the second latent variable calculation unit 21 of the prediction/estimation device 20 inputs the prediction/estimation data 4 of the explanatory variables and the prediction/estimation data 5 of the auxiliary variables, and calculates the latent variables based on the latent variable calculation information 6 . Data for predicting/estimating variables (not shown) is calculated.
  • the first latent variable calculation unit 11 of the learning device 10 uses the teaching data 3 of the auxiliary variables as input data to calculate the teaching data of the latent variables. Furthermore, it is different from the learning device 10 of the prediction/estimation system 100 of the first embodiment in that it also includes teacher data 2 of explanatory variables. In addition to the auxiliary variable prediction/estimation data 5, the second latent variable calculation unit 21 of the prediction/estimation device 20 uses explanatory variables is different from the prediction/estimation device 20 of the prediction/estimation system 100 of the first embodiment in that it also includes the prediction/estimation data 4 of the first embodiment.
  • the first latent variable calculation unit 11 of the learning device 10 and the second latent variable calculation unit 21 of the prediction/estimation device 20 also use the data related to the explanatory variables to obtain teacher data for each latent variable. and calculation of prediction/estimation data. Therefore, highly accurate prediction/estimation using latent variables with reduced correlation between explanatory variables and auxiliary variables is possible. Also, according to the second embodiment, more data is used to calculate latent variables, so latent variables can be calculated based on higher-dimensional and advanced algorithms. As a result, it is possible to further improve the accuracy of prediction/estimation using auxiliary variables while avoiding deterioration of prediction/estimation accuracy due to correlation.
  • FIG. 4 is an explanatory diagram showing the basic configuration of the prediction/estimation system according to the third embodiment of the present invention.
  • the second latent variable calculation unit 21 of the prediction/estimation device 20 includes predictive/estimation data 4 for explanatory variables and prediction/estimation data 4 for auxiliary variables.
  • the explanatory variable teacher data 2, the auxiliary variable teacher data 3, and the latent variable teacher data 13 calculated by the first latent variable calculator 11 of the learning device 10 Based on this, latent variable prediction/estimation data 23 is calculated.
  • the second latent variable calculation unit 21 of the prediction/estimation device 20 uses auxiliary variable
  • explanatory variable teacher data 2 is also included. It is different from the estimation system 100A.
  • the prediction/estimation data 23 of the latent variables are calculated using the teaching data 2 and 3 of the explanatory variables and the auxiliary variables. ing. Therefore, the latent variable prediction/estimation data 23 can be calculated using more data than in the second embodiment. As a result, it is possible to apply a more advanced algorithm and improve the accuracy of prediction/estimation using auxiliary variables while avoiding deterioration in prediction/estimation accuracy due to correlation.
  • FIG. 5 is an explanatory diagram showing the basic configuration of the prediction/estimation system according to the fourth embodiment of the present invention.
  • the first latent variable calculation unit 11 of the learning device 10 calculates the latent variables using regression analysis and principal component analysis as a predetermined algorithm (latent variable calculation information 6). Calculate teacher data (not shown).
  • the second latent variable calculation unit 21 of the prediction/estimation device 20 uses the algorithm (latent variable calculation information 6) used in the first latent variable calculation unit 11 to generate latent variable prediction/estimation data (not shown). ) are calculated.
  • the first latent variable calculation unit 11 of the learning device 10 converts the teacher data 3 of the auxiliary variables into the teacher data 3 of the explanatory variables.
  • a first regression analysis unit 14 performs regression analysis on data 2 to create a regression model, and a regression error 15 of the regression analysis by the first regression analysis unit 14 is subjected to principal component analysis to calculate latent variable teacher data (not shown). and a first principal component analysis unit 16 .
  • the latent variable calculation information 6 includes regression model parameters and regression equations, and principal component vectors and eigenvalues of principal component analysis.
  • the second latent variable calculation unit 21 of the prediction/estimation device 20 performs regression analysis on the auxiliary variable prediction/estimation data 5 with the explanatory variable prediction/estimation data 4 based on the latent variable calculation information 6 to create a regression model.
  • the first latent variable calculation unit 11 of the learning device 10 and the second latent variable calculation unit 21 of the prediction/estimation device 20 are the first regression analysis unit 14 and the first principal It includes a component analysis unit 16 and performs regression analysis and principal component analysis to calculate teacher data for latent variables, and the second latent variable calculation unit 21 performs a second regression analysis unit 24 and a second principal component analysis unit 26. It is different from the prediction/estimation system 100A according to the second embodiment in that the latent variable prediction/estimation data is calculated by performing regression analysis and principal component analysis.
  • the first regression analysis unit 14 of the first latent variable calculation unit 11 of the learning device 10 performs regression analysis (RA ) and a regression model is created.
  • a regression error 15 of the regression model created by the first regression analysis unit 14 is subjected to principal component analysis (PCA) by the first principal component analysis unit 16, thereby calculating teacher data of latent variables.
  • PCA principal component analysis
  • a principal component vector having a small correlation between the explanatory variable and the auxiliary variable is selected as the principal component parameter.
  • the first latent variable calculation unit 11 of the learning device 10 can calculate latent variable teacher data that has a small correlation with the explanatory variable teacher data 2 .
  • the prediction/estimation model 7 is created by, for example, machine learning using the data including the teacher data of the latent variables with small correlation calculated in this way. This makes it possible to avoid deterioration in prediction/estimation accuracy due to the correlation between the teacher data 3 of the auxiliary variable and the teacher data 2 of the explanatory variable.
  • the regression model included in the latent variable calculation information 6 may include data such as regression coefficients.
  • the principal component parameters included in the latent variable calculation information 6 may include data such as the eigenvalues of the principal component vector and the sample variance matrix.
  • the latent variable calculation information 6 including the parameters and regression formula of the regression model in the first latent variable calculation unit 11 and the principal component parameters of the principal component analysis is Used.
  • the second regression analysis unit 24 uses this latent variable calculation information 6, the second regression analysis unit 24 performs regression analysis (RA) on the auxiliary variable prediction/estimation data 5 with the explanatory variable prediction/estimation data 4 to create a regression model. be.
  • the regression error 25 of the regression model generated by the second regression analysis unit 24 is subjected to principal component analysis (PCA) by the second principal component analysis unit 26, thereby calculating latent variable prediction/estimation data. Therefore, in the prediction/estimation device 20, the latent variable prediction/estimation data having a small correlation with the explanatory variable prediction/estimation data 4 is calculated using the latent variable calculation information 6 similar to that of the learning device 10. becomes possible.
  • the prediction/estimation value 8 of the objective variable is calculated using the data including the prediction/estimation data of the latent variable with small correlation calculated in this way.
  • the deterioration of the prediction/estimation accuracy due to the correlation between the auxiliary variable prediction/estimation data 5 and the explanatory variable prediction/estimation data 4 is reduced, and the target variable prediction/estimation value 8 is increased. can be obtained with precision.
  • FIG. 6 is an explanatory diagram showing the basic configuration of the prediction/estimation system according to the fifth embodiment of the present invention.
  • the first latent variable calculation unit 11 of the learning device 10 calculates latent variable teacher data 13 using a Gaussian process latent variable model (GPLVM).
  • the latent variable calculation information 6 includes hyperparameters of a Gaussian process latent variable model (GPLVM).
  • the prediction/estimation model learning unit 12 of the learning device 10 performs, for example, machine learning using Gaussian process regression (GPR) to create the prediction/estimation model 7 of the objective variable.
  • GPR Gaussian process regression
  • the second latent variable calculation unit 21 of the prediction/estimation device 20 calculates latent variable prediction/estimation data 23 using a Gaussian process latent variable model (GPLVM), and the prediction/estimation unit 22 of the prediction/estimation device 20 calculates the predicted/estimated value 8 of the objective variable by Gaussian process regression (GPR).
  • GPLVM Gaussian process latent variable model
  • GPR Gaussian process regression
  • the first latent variable calculation unit 11 of the learning device 10 and the second latent variable calculation unit 21 of the prediction/estimation device 20 use the latent variable teacher data 13 and the latent variable
  • the Gaussian process latent variable model (GPLVM) algorithm is used to calculate the prediction/estimation data 23, and the prediction/estimation model learning unit 12 of the learning device 10 and the prediction/estimation unit 22 of the prediction/estimation device 20
  • the prediction/estimation system 100B of the third embodiment differs from the prediction/estimation system 100B of the third embodiment in that a Gaussian process regression (GPR) algorithm is used for learning the target variable prediction/estimation model 7 and calculating the target variable prediction/estimation value 8. are different.
  • GPR Gaussian process regression
  • the latent variable teacher data 13 and the latent variable prediction/estimation data 23 are converted into a Gaussian process latent variable model (GPLVM).
  • the prediction/estimation model learning unit 12 and the prediction/estimation unit 22 learn/calculate the prediction/estimation model 7 and the prediction/estimation value 8 using Gaussian process regression (GPR).
  • GPR Gaussian process regression
  • FIG. 7 is an explanatory diagram showing the basic configuration of a welding strength estimation system for laser welding to which a prediction/estimation system according to a sixth embodiment of the present invention is applied.
  • the welding strength estimation system 100E of the sixth embodiment can be configured as an estimation system to which the configurations of the prediction/estimation systems 100 to 100D according to the first to fifth embodiments can be applied.
  • the objective variable is the welding strength (welding strength data 1A) or welding quality (not shown) of laser welding by the laser welder 9.
  • the explanatory variable is the welding condition of laser welding (welding condition data 2A).
  • the auxiliary variable is a physical quantity (welding temperature data 3A) observable during or after laser welding with respect to laser welding.
  • data for prediction/estimation of explanatory variables includes welding condition data 4A set in the laser welding machine 9 .
  • Data for predicting/estimating the auxiliary variables include welding temperature data 5A, which is one of physical quantities observed in the laser welding machine 9 during or after laser welding.
  • the welding strength data 1A is determined by the allowable stress and material strength of the welded portion of the workpiece according to the type of the workpiece to be laser-welded based on the following welding condition data 2A by the laser welder 9, for example. It represents the strength F (N/mm 2 ).
  • Welding quality is a predetermined quality of welding (excellent, good, acceptable, unsatisfactory, etc.) based on, for example, the welding strength F obtained according to the type of workpiece to be laser-welded as described above. represents
  • the welding condition data 2A includes, for example, the specifications of the workpiece (material, thickness, etc.), the laser output value of the laser welder 9, the laser irradiation time, the focal position of the laser light, and pulse conditions such as the frequency and duty ratio of the laser light. , welding speed, time from start of irradiation to peak power, elapsed time from peak power to end of irradiation, lens focal length, lens focal position, laser diameter at irradiation point, fiber diameter, and spot diameter (lens, fiber, focus position combination).
  • the welding condition data 2A are arbitrary parameters set for laser welding.
  • Welding temperature data 3A represents, for example, the welding temperature detected during laser welding based on welding condition data 2A.
  • the welding condition data 4A is data relating to welding conditions actually set in the laser welder 9, and is configured in the same manner as the welding condition data 2A.
  • the welding temperature data 5A represents the welding temperature detected and acquired during actual laser welding detected by the welding temperature sensor 17 provided in the laser welder 9 .
  • Welding temperature sensor 17 is included in sensor 212 described above.
  • the welding strength data 1A, the welding condition data 2A, and the welding temperature data 3A are stored in a readable state in an external storage device or storage medium (not shown) connected to the network 90, for example.
  • the network 90 may be a medium for exchanging data, and is not limited to networks such as the Internet and LAN, but may be a bus, USB, or a portable storage medium such as an HDD that constitutes a device. There are no particular restrictions on its form.
  • the estimation system 100E includes a learning server 30 functioning as the above-described learning device 10 and an estimation edge server 40 functioning as the above-described prediction/estimation device 20, which are communicably connected to each other via a network 90.
  • the estimation system 100E also includes a storage device 50 that stores (at least one of) the latent variable calculation information 6 and the welding strength estimation model 7A.
  • the learning server 30 is also provided with a storage unit 50A having the same function as the storage device 50.
  • FIG. Although not shown, a storage unit equivalent to the storage unit 50A may be provided in the estimated edge server 40.
  • the learning server 30 has the teacher data of the objective variable, the teacher data of the explanatory variables acting on the objective variable, and the variables other than the objective variable, which are correlated with the explanatory variables and observed when the explanatory variables are given. It is configured to be able to input teacher data of auxiliary variables. In addition, the learning server 30 calculates latent variable teacher data (not shown) having a smaller correlation between or with the explanatory variable teacher data than the auxiliary variable teacher data from at least the auxiliary variable teacher data.
  • a latent variable calculation unit (first latent variable calculation unit 31) that outputs latent variable calculation information 6; Further, the learning server 30 inputs teacher data of objective variables, teacher data of explanatory variables, and teacher data of latent variables calculated by the latent variable calculator (first latent variable calculator 31).
  • a prediction/estimation model learning unit (welding strength estimation model learning unit 32) that performs machine learning and creates a prediction/estimation model (welding strength estimation model 7A) of the objective variable is provided.
  • the estimated edge server 40 has the teacher data of the objective variable, the teacher data of the explanatory variables acting on the objective variable, and the variables other than the objective variable, which have correlation with the explanatory variables, and when the explanatory variables are given, From the observed auxiliary variable teacher data, the latent variable teacher data calculated based on the latent variable calculation information 6, and the target variable prediction/estimation model (welding strength estimation model 7A) learned in advance using Based on this, the prediction/estimation device 20 calculates the prediction/estimation value of the objective variable (estimated value 8A of welding strength).
  • the estimation edge server 40 is based on the latent variable calculation information 6 from at least the data for prediction/estimation of the auxiliary variables, and the data for prediction/estimation of the explanatory variables rather than the data for prediction/estimation of the auxiliary variables.
  • a latent variable calculation unit (second latent variable calculation unit 41) for calculating prediction/estimation data (not shown) of latent variables having a small mutual correlation is provided.
  • the estimation edge server 40 generates a prediction/estimation model from the prediction/estimation data of the latent variables calculated by the latent variable calculation unit (second latent variable calculation unit 41) and the prediction/estimation data of the explanatory variables.
  • a prediction/estimation unit (welding strength estimation unit 42) that calculates a prediction/estimation value (estimation value 8A of welding strength) of an objective variable based on (welding strength estimation model 7A) is provided.
  • the learning server 30 and the estimation edge server 40 can function as the learning device 10 and the prediction/estimation device 20 described above, respectively. Therefore, the learning server 30 and the estimated edge server 40 can implement all aspects already described in the first to fifth embodiments. Therefore, hereinafter, explanations that overlap with the components of the learning device 10 and the prediction/estimation device 20 will be omitted.
  • Welding strength data 1A, welding condition data 2A, and welding temperature data 3A stored in an external storage device or storage medium are input to learning server 30 as teacher data for objective variables, explanatory variables, and auxiliary variables, respectively, and stored in storage unit 50A.
  • the learning server 30 calculates teacher data of latent variables in the first latent variable calculator 31 based on at least the welding temperature data 3A among the input data.
  • the learning server 30 inputs the welding strength data 1A, the welding condition data 2A, and the teacher data of the latent variables calculated by the first latent variable calculation unit 31 in the welding strength estimation model learning unit 32, For example, machine learning is performed to create the welding strength estimation model 7A.
  • the learning server 30 stores the latent variable calculation information 6 and the welding strength estimation model 7A determined when calculating latent variable teacher data in the storage unit 50A, and outputs them to the storage device 50 via the network 90.
  • the storage device 50 stores the input latent variable calculation information 6 and welding strength estimation model 7A.
  • the welding strength data 1A, the welding condition data 2A, and the welding temperature data 3A may be stored, for example, in the storage device 50 instead of the external storage device or storage medium.
  • laser welding is performed based on the set welding condition data 4A.
  • Welding temperature data 5A during laser welding is acquired.
  • the welding condition data 4A of the laser welder 9 and the welding temperature data 5A from the welding temperature sensor 17 are input to the estimation edge server 40 as explanatory variable prediction/estimation data and auxiliary variable prediction/estimation data, respectively.
  • the latent variable calculation information 6 and the welding strength estimation model 7A stored in the storage device 50 are also input to the estimation edge server 40 .
  • the estimated edge server 40 stores these input data in the storage unit, and from the data including at least the welding temperature data 5A, the second latent variable calculation unit 41 calculates the latent variable calculation information 6. Calculate data for predicting and estimating latent variables. In addition, in the welding strength estimation unit 42, the estimated edge server 40 uses the data for predicting/estimating the latent variables calculated by the second latent variable calculation unit 41 and the welding condition data 4A, based on the welding strength estimation model 7A. to calculate an estimated weld strength value of 8A.
  • the calculated data for prediction/estimation of the latent variables and the estimated value 8A of the weld strength are stored in the storage unit, and the estimated value 8A of the weld strength is displayed, printed, or otherwise displayed in a form that can be used as appropriate by the estimation edge server 40. can be output from
  • the latent variable teacher data is calculated based on the welding temperature data 3A, which is the auxiliary variable teacher data of the welding strength data 1A, and then the welding strength is estimated using the latent variable teacher data.
  • a model 7A is created. Further, based on the latent variable calculation information 6 determined when calculating the teacher data of the latent variables, the data for prediction/estimation of the latent variables is calculated from the welding temperature data 5A, which is the data for prediction/estimation of the auxiliary variables. Then, an estimated welding strength value 8A is calculated based on the welding strength estimation model 7A from the welding condition data 4A, which is explanatory variable prediction/estimation data, and the latent variable prediction/estimation data.
  • the welding strength of the estimation target (welded portion of the workpiece) can be non-destructively estimated from the data regarding the welding conditions of laser welding and the data regarding the temperature during welding. becomes possible.
  • the welding strength varies depending on factors such as variations in the material of the workpiece and the welding environment. Therefore, there is a problem that the weld strength cannot be measured without destroying the product.
  • the estimation system 100E of the sixth embodiment employs a configuration capable of improving prediction/estimation accuracy using more data and avoiding deterioration of prediction/estimation accuracy due to correlation. Therefore, the estimation system 100E can solve this problem and can achieve the same effects as those of the first to fifth embodiments.
  • the estimation system 100E of the sixth embodiment aims at estimating the welding strength of laser welding, it is not limited to this.
  • the estimation system 100E can also predict and estimate various physical phenomena related to welding quality, such as spatter and porosity.
  • the objective variable should be the welding quality of laser welding.
  • the welding temperature data 3A and 5A have been described as auxiliary variables, but the auxiliary variables are not limited to these.
  • the auxiliary variables may be physical quantities observed during welding, such as sound, light, and color during welding, or physical quantities observed after welding, such as the weld width, color, and number of spatters of the welded portion after welding.
  • the estimation system 100E can install the learning server 30, the estimation edge server 40, and the storage device 50, for example, centrally at the same site as the laser welding machine 9, or separately at a remote location. Therefore, the estimation system 100E can be used in a wide variety of operations, assuming global deployment, regarding the estimation of the welding strength of laser welding.
  • FIG. 8 is an explanatory diagram showing the basic configuration of a learning device of a nondestructive measurement system to which the prediction/estimation system according to the seventh embodiment of the present invention is applied.
  • FIG. 9 is an explanatory diagram showing the basic configuration of a nondestructive testing device of the nondestructive measurement system.
  • the nondestructive measurement system 100F of the seventh embodiment is configured as a nondestructive measurement system to which the configurations of the prediction/estimation systems 100 to 100D according to the first to fifth embodiments can be applied. can be
  • the nondestructive measurement system 100F includes a learning device 33 as shown in FIG. 8 and a nondestructive testing device 49 including a prediction/estimation device 43 as shown in FIG.
  • the learning device 33 includes a first latent variable calculation unit 34 and a prediction/estimation model learning unit 35 .
  • the prediction/estimation device 43 of the nondestructive testing device 49 includes a second latent variable calculator 44 and a prediction/estimation unit 45 .
  • the objective variable is the concrete strength (strength property data 1B).
  • the explanatory variable is the measurable influence factor/condition of the concrete strength (influence factor/condition data 2B).
  • the auxiliary variable is the elastic wave propagation characteristic (elastic wave propagation characteristic data 3B) at the time of intensity measurement.
  • data for prediction/estimation of explanatory variables includes influence factor/condition data 4B in concrete for strength prediction/estimation.
  • elastic wave propagation characteristic data 5B based on data acquired by a measuring device (acoustic sensor 18).
  • the strength property data 1 B, the strength influence factor/condition data 2 B, and the elastic wave propagation characteristic data 3 B are input to the learning device 33 .
  • the strength influence factor/condition data 4 B and the elastic wave propagation characteristic data 5 B are input to the prediction/estimation device 43 of the nondestructive testing device 49 .
  • the strength property data 1B can include, for example, compressive strength, tensile strength, bending strength, shear strength, bearing strength, adhesion strength, fatigue strength, etc., as data representing the strength of concrete.
  • the strength property data 1B represents the compressive strength F (N/mm 2 ) of concrete in this embodiment.
  • the strength influence factor/condition data 2B includes, for example, various types of information such as cement type, cement water ratio, cement additive, material age, temperature and humidity from concrete placement to strength measurement. However, it is not limited to these.
  • the elastic wave propagation characteristic data 3B represents elastic wave propagation velocity, elastic wave reflection characteristics, etc., but is not limited to these. Various types of elastic wave propagation characteristic data 3B can be applied as long as they are characteristic data obtained by nondestructive measurement in the nondestructive measurement system 100F.
  • the strength influence factor/condition data 4B is data relating to the strength influence factor/condition of the concrete for predicting/estimating the strength.
  • the strength influence factor/condition data 4 B is configured in the same manner as the strength influence factor/condition data 2 B input to the learning device 33 .
  • the elastic wave propagation characteristic data 5B represents elastic wave propagation characteristics derived from acoustic data detected by the acoustic sensor 18 .
  • the elastic wave propagation characteristic data 5B is configured similarly to the elastic wave propagation characteristic data 3B input to the learning device 33.
  • FIG. Note that the acoustic sensor 18 is included in the sensor 212 described above.
  • the strength property data 1B, the strength influence factor/condition data 2B, and the elastic wave propagation characteristic data 3B are input to the learning device 33 as teacher data for objective variables, explanatory variables, and auxiliary variables, respectively.
  • the learning device 33 calculates teacher data of latent variables in the first latent variable calculator 34 based on data including at least intensity influence factor/condition data 2B and elastic wave propagation characteristic data 3B among these input data.
  • the learning device 33 receives the strength property data 1B, the strength influence factor/condition data 2B, and the teacher data of the latent variables calculated by the first latent variable calculation unit 34 in the prediction/estimation model learning unit 35.
  • the learning device 33 outputs to the outside the latent variable calculation information 6 and the concrete strength prediction/estimation model 7 that are determined when calculating latent variable teacher data.
  • the nondestructive testing device 49 is equipped with the latent variable calculation information 6 and the prediction/estimation model 7 output from the learning device 33 .
  • the latent variable calculation information 6 and the prediction/estimation model 7 are stored in a storage medium possessed by the nondestructive testing device 49 or in a portable storage medium detachable from the nondestructive testing device 49, or can be transmitted via the Internet or the like. It is obtained from a medium and provided in the non-destructive testing device 49 .
  • the non-destructive testing device 49 is provided with elastic wave propagation characteristic data 5B derived based on the acoustic data detected by the acoustic sensor 18 when concrete is hit, and derived based on the acoustic data. Then, the prediction/estimation device 43 of the nondestructive testing device 49 receives the latent variable calculation information 6, the prediction/estimation model 7, the elastic wave propagation characteristic data 5B, and the strength influence factor/condition data 4B.
  • the prediction/estimation device 43 calculates the latent variable calculation information 6 in the second latent variable calculator 44 from the data including at least the strength influence factor/condition data 4B and the elastic wave propagation characteristic data 5B among the input data. Calculate data for predicting and estimating latent variables based on In the prediction/estimation unit 45, the prediction/estimation device 43 includes latent variable prediction/estimation data calculated by the second latent variable calculation unit 44, intensity influence factor/condition data 4B, and elastic wave propagation Based on the concrete strength prediction/estimation model 7, a concrete strength prediction/estimation value 8 is calculated from the characteristic data 5B. The calculated predicted/estimated value 8 can be output from the non-destructive testing device 49 in a form that can be used as appropriate, such as display or printing.
  • a latent variable After calculating the teaching data of the latent variables, a concrete strength prediction/estimating model 7 is created using the teaching data of the latent variables. Also, based on the latent variable calculation information 6 determined when calculating the latent variable teacher data, elastic wave propagation characteristic data 5B that is data for prediction/estimation of auxiliary variables and data for prediction/estimation of explanatory variables. After calculating latent variable prediction/estimation data from strength influence factor/condition data 4B, concrete Based on the strength prediction/estimation model 7, a concrete strength prediction/estimation value 8 is calculated.
  • the non-destructive measurement system 100F of the seventh embodiment data related to factors and conditions affecting the strength of concrete representing factors at the time of placing and the like and elastic wave propagation characteristics in a non-destructive test using the elastic wave method From the data, it becomes possible to predict and estimate the strength of the estimation target (concrete) non-destructively. Therefore, it is possible to improve the prediction/estimation accuracy using more data and avoid deterioration of the prediction/estimation accuracy due to correlation, and it is possible to achieve the same effects as the first to fifth embodiments. becomes.
  • various sensors or the like corresponding to the auxiliary variables are used instead of the acoustic sensor 18 to obtain the auxiliary variables. Also good.
  • FIG. 10 is an explanatory diagram showing the basic configuration of a quality judgment/prediction system for cutting quality of a laser cutting apparatus to which the prediction/estimation system according to the eighth embodiment of the present invention is applied.
  • the quality judgment prediction system 100G of the eighth embodiment can be configured as a quality judgment prediction system to which the configurations of the prediction/estimation systems 100 to 100D according to the first to fifth embodiments can be applied.
  • the quality judgment prediction system 100G includes a learning device 36 and a laser cutting device 60.
  • the learning device 36 includes a first latent variable calculation unit 37 and a quality judgment prediction model learning unit 38 .
  • the laser cutting device 60 includes a quality judgment prediction device 46 and a data storage/transfer device 61 .
  • the quality judgment prediction device 46 includes a second latent variable calculator 47 and a quality judgment prediction unit 48 .
  • the objective variable is the quality judgment result of laser cutting by the laser cutting device 60 (quality judgment result data 1C).
  • explanatory variables are cutting conditions for laser cutting (cutting condition data 2C).
  • auxiliary variables are measurable physical quantities related to laser cutting (emission intensity data 3C).
  • data for prediction/estimation of explanatory variables includes cutting condition data 4C set in the laser cutting device 60 .
  • the data for prediction/estimation of the auxiliary variables include physical quantities (luminescence intensity data 5C) observed by the laser cutting device 60 .
  • the quality judgment 59 of the cutting quality of the laser cutting device 60 means, for example, the physical state of the cut surface of the workpiece cut by the laser cutting device 60, that is, for example, surface roughness, dross adhesion state, gouging ( It is to automatically or manually determine whether or not the state of occurrence of defective cutting) can withstand practical use in using the workpiece.
  • Dross means a deposit of metals, oxides, etc. melted and adhered to the lower surface of the cut material, and is synonymous with slag.
  • gouging in laser cutting means, for example, a state in which the laser beam does not penetrate during laser cutting and melted metal is ejected onto the surface of the material, resulting in a dirty appearance.
  • the quality judgment result data 1C is provided as discrete category information such as "optimum”, “excellent”, “good”, “acceptable”, and “impossible” as a result of the quality judgment 59 as described above. can be Also, the quality determination result data 1C may be given as numerical information from 0 to 100.
  • FIG. The quality determination result data 1C represents the determined quality of laser cutting.
  • the cutting condition data 2C can include various information such as the material and/or product name of the workpiece to be laser-cut, laser output value, laser irradiation time, and cutting speed.
  • the cutting condition data 2C represents cutting conditions set in the laser cutting device 60 for laser cutting. Also, the cutting condition data 2C may include various types of information on environmental conditions such as temperature and humidity during laser cutting. Various types of information in the cutting condition data 2C are not limited to these.
  • the emission intensity data 3C represents, for example, the emission intensity during piercing performed prior to laser cutting.
  • teaching data for auxiliary variables is not limited to luminescence intensity.
  • the teaching data of the auxiliary variable may be physical quantity data that can be measured in association with laser cutting, such as sound or emission spectrum during piercing.
  • the cutting condition data 4C is, for example, data relating to the cutting conditions set in accordance with the user's operation input of the cutting conditions via the touch panel 211 .
  • the cutting condition data 4C is configured similarly to the cutting condition data 2C.
  • the emission intensity data 5C represents the emission intensity detected by the optical sensor 19 provided in the laser cutting device 60 during actual piercing. Note that the optical sensor 19 is included in the sensor 212 described above.
  • the cutting condition data 2C, and the luminous intensity data 3C are input to the learning device 36 as teacher data for explanatory variables and auxiliary variables, respectively.
  • the quality judgment result data 1C can be input to the learning device 36 as teacher data for objective variables.
  • the learning device 36 calculates teacher data of latent variables in the first latent variable calculator 37 based on the data including at least the cutting condition data 2C and the light emission intensity data 3C among the input data.
  • the learning device 36 inputs the quality determination result data 1C, the cutting condition data 2C, and the teacher data of the latent variables calculated by the first latent variable calculation unit 37 in the quality determination prediction model learning unit 38, For example, machine learning is performed to create a quality determination predictive model 7B for cutting quality of laser cutting.
  • the learning device 36 outputs to the laser cutting device 60 the latent variable calculation information 6 and the quality judgment prediction model 7B determined when calculating the teacher data of the latent variables.
  • the laser cutting device 60 is equipped with the latent variable calculation information 6 and the quality judgment prediction model 7B output from the learning device 36.
  • the latent variable calculation information 6 and the quality judgment prediction model 7B are stored in a storage medium of the laser cutting device 60 or a portable storage medium detachably attached to the laser cutting device 60, or can be downloaded from an information transmission medium such as the Internet. It is acquired and provided in the laser cutting device 60 .
  • the data storage/transfer device 61 of the laser cutting device 60 is supplied with the emission intensity data 5C during the piercing process detected by the optical sensor 19 and the cutting condition data 4C operated by the touch panel 211 and temporarily stored. ing.
  • the latent variable calculation information 6 and the quality judgment prediction model 7B are input to the quality judgment prediction device 46 of the laser cutting device 60 together with the cutting condition data 4C and the emission intensity data 5C stored in the data storage/transfer device 61. be.
  • the quality judgment predicting device 46 uses at least the cutting condition data 4C and the luminescence intensity data 5C among the input data to generate latent variable prediction/estimation data based on the latent variable calculation information 6 in the second latent variable calculator 47. Calculate In addition, the quality judgment prediction device 46 predicts the quality from the latent variable prediction/estimation data calculated by the second latent variable calculation unit 47 in the quality judgment prediction unit 48, the cutting condition data 4C, and the light emission intensity data 5C. Based on the judgment prediction model 7B, quality judgment prediction of cutting quality is performed to calculate a quality judgment prediction value 8B.
  • the calculated quality determination predicted value 8B can be output from the laser cutting device 60 in a form that can be used as appropriate, such as display or printing. Since the laser cutting device 60 can output various information about the actual cutting result 58, the quality judgment 59 described above is performed based on the various information about this cutting result 58, and the quality judgment result data 1C is created. .
  • the learning device 36 converts the cutting condition data 4C and the light emission intensity data 5C stored in the data storage/transfer device 61 into explanatory variables and auxiliary variables when calculating teacher data of latent variables and creating the quality judgment prediction model 7B. may be used in addition to the cutting condition data 2C and the emission intensity data 3C as teaching data. In this way, more data can be used to contribute to improving the accuracy of prediction/estimation. Furthermore, since the learning device 36 can additionally use the quality determination result data 1C as teacher data for the objective variable, in this case, it is possible to further improve the accuracy of prediction/estimation.
  • latent light emission intensity data 3C which is teacher data for auxiliary variables of quality judgment result data 1C
  • cutting condition data 2C which is teacher data for explanatory variables.
  • the luminous intensity data 5C which is the data for prediction/estimation of the auxiliary variables
  • the cutting condition which is the data for prediction/estimation of the explanatory variables
  • the quality prediction target (the cut portion of the workpiece) is determined before laser cutting from the data regarding the cutting conditions for laser cutting and the data regarding the emission intensity during cutting. Cut quality can be predicted.
  • the quality determination prediction system 100G of the eighth embodiment employs a configuration capable of improving the quality determination prediction accuracy using more data and avoiding deterioration of the quality determination prediction accuracy due to correlation. Therefore, the quality judgment prediction system 100G can solve this problem by predicting cutting quality before laser cutting, and can achieve the same effects as those of the first to fifth embodiments. .
  • the learning device 36 may be incorporated in the laser cutting device 60, and the quality judgment prediction device 46 may be a separate device from the laser cutting device 60. (For example, an edge server or the like) may be independent.
  • the algorithms include regression analysis (RA), principal component analysis (PCA), singular value decomposition (SVD), and linear discriminant analysis as described above.
  • LDA Independent Component Analysis
  • GPLVM Gaussian Process Latent Variable Model
  • LR Logistic Regression
  • SVM Support Vector Machine
  • DA Discriminant Analysis
  • RF Random Forest
  • RSVM Ranking Support Vector Machine
  • GB Gradient Boosting
  • NB Naive Bayes
  • K-NN K-Nearest Neighbor Algorithm
  • the learning method of the prediction/estimation model 7 and the prediction/estimation method of the prediction/estimation value 8 in the learning device 10 and the prediction/estimation device 20 may be a program for executing these methods and/or this It can be implemented as a computer-readable storage medium storing a program.
  • the learning method and the prediction/estimation method may be realized using various hardware resources such as an electronic circuit that executes these methods and a logic circuit that uses other physical media. and/or may be implemented as a device having hardware resources such as logic circuits.
  • the learning method and the prediction/estimation method are realized using various hardware resources such as a computer and/or electronic circuit equipped with a storage medium storing a program etc. to be executed as one system, and other logic circuits.
  • the learning method and the prediction/estimation method may be realized using various hardware resources such as one or more computers and/or electronic circuits each having a separate storage medium, and other logic circuits.
  • the learning method may be implemented on the cloud side and the prediction/estimation method may be implemented on the edge side, or vice versa.
  • FIG. 11 is a graph showing the relationship between welding temperature and elapsed time for explaining auxiliary variables in an example in which the prediction/estimation system according to the fourth embodiment shown in FIG. 5 is applied to actual laser welding.
  • FIG. 12 is a graph showing the relationship between estimated values and measured values and the frequency distribution of errors of estimated values with respect to estimated values in Comparative Example and Example.
  • the welding conditions (output intensity and irradiation time of the laser used for laser welding) were used as explanatory variables, and the welding strength was used as the objective variable.
  • the prediction/estimation model 7 is created using multiple regression analysis.
  • no latent variable as described above was used.
  • the temperature at the welding point varies from the start of the laser irradiation at the elapsed time T1. At the same time, it begins to rise sharply.
  • the temperature rise slows down, and at the same time the laser irradiation ends after the elapsed time T2 (elapsed time T3), the temperature drops sharply, and after the elapsed time T3 At a certain point (elapsed time T4), the temperature returns to the temperature before the start of laser irradiation.
  • the welding temperature of laser welding changes with such characteristics. Therefore, as auxiliary variables for estimating the welding strength, the temperature TP1 at the time when the temperature rise slows down (elapsed time T2) and the temperature TP2 at the end of laser irradiation (elapsed time T3) are used.
  • the estimated value of the welding strength according to the comparative example and the measured value of the actual welding strength are shown in Fig. 12(a).
  • the estimated value of the welding strength according to the example and the measured value of the actual welding strength are shown in FIG. 12(b).
  • the horizontal axis represents the measured values of the welding strength when the values of the welding conditions are changed to various conditions
  • the vertical axis represents the estimated values of the welding strength corresponding to the welding conditions. represents.
  • the plots are normalized so that the maximum welding strength is 1 for both the measured values and the estimated values.
  • FIG. 12(c) the frequency distribution of the errors of the estimated values for the measured values according to the comparative example is shown in FIG. 12(c).
  • FIG. 12(d) the error frequency distribution of the estimated values with respect to the measured values according to the example is shown in FIG. 12(d).
  • the horizontal axis represents the error range
  • the vertical axis represents the frequency corresponding to the error.
  • the errors in the examples took smaller values in both MAE and RMSE compared to the errors in the comparative examples. Also, as is clear from FIGS. 12(c) and (d), the estimated values are closer to the measured values in the example than in the comparative example, and the tail (range) of the error distribution is narrower. I understand. Therefore, in the prediction/estimation system of the example, it was proved that the accuracy of prediction/estimation was improved even when more data including auxiliary variables were used.

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Software Systems (AREA)
  • Chemical & Material Sciences (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Health & Medical Sciences (AREA)
  • Theoretical Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Mathematical Physics (AREA)
  • Optics & Photonics (AREA)
  • Evolutionary Computation (AREA)
  • Computing Systems (AREA)
  • General Engineering & Computer Science (AREA)
  • Data Mining & Analysis (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Artificial Intelligence (AREA)
  • Ceramic Engineering (AREA)
  • Mechanical Engineering (AREA)
  • Plasma & Fusion (AREA)
  • Medical Informatics (AREA)
  • Food Science & Technology (AREA)
  • Medicinal Chemistry (AREA)
  • Analytical Chemistry (AREA)
  • Biochemistry (AREA)
  • General Health & Medical Sciences (AREA)
  • Immunology (AREA)
  • Pathology (AREA)
  • Laser Beam Processing (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

One embodiment of this learning device comprises: a latent variable calculation unit for inputting teaching data about an objective variable, teaching data about an explanatory variable acting on the objective variable, and teaching data about an auxiliary variable, which is a variable other than the objective variable, has a correlation with the explanatory variable, and is observed when the explanatory variable is provided, and for calculating teaching data about a latent variable from at least the teaching data about the auxiliary variable, and outputting latent variable calculation information; and a prediction/estimation model learning unit for inputting teaching data about an objective variable, teaching data about an explanatory variable, and teaching data about a latent variable calculated by the latent variable calculation unit, and creating an objective variable prediction/estimation model.

Description

予測・推定システム、学習装置及び予測・推定装置Prediction/estimation system, learning device and prediction/estimation device
　本発明は、予測・推定システム、学習装置及び予測・推定装置に関する。 The present invention relates to a prediction/estimation system, a learning device, and a prediction/estimation device.
　教師付き機械学習を用いた目的変数の予測・推定においては、一般的に、予測・推定モデルの学習に際して、教師データとなる目的変数及び説明変数が用いられる。また、説明変数を原因としたときの結果となるような因果関係を有する変数として、予測・推定時に入手可能な、目的変数以外の変数である補助的な変数（補助変数）が用いられることもある。 In the prediction/estimation of objective variables using supervised machine learning, objective variables and explanatory variables that serve as teacher data are generally used when learning prediction/estimation models. In addition, auxiliary variables (auxiliary variables) that are available at the time of prediction/estimation and are other than the objective variable may also be used as variables that have a causal relationship that results when the explanatory variable is the cause. be.
　このような予測・推定モデルの学習方法としては、例えば、次のようなものが知られている。まず、複数の実験試料の化学物質の値を目的変数の教師データとし、説明変数の教師データである複数の実験試料の収集されたスペクトルから変換された近赤外スペクトルデータを、その一部を無作為に選択して校正セットとし、一部を検証セットとする。 For example, the following methods are known for learning such prediction/estimation models. First, the values of chemical substances in multiple experimental samples are used as teacher data for objective variables, and the near-infrared spectral data converted from the collected spectra of multiple experimental samples, which are teacher data for explanatory variables, are used as part of the data. A random selection is made into the calibration set and partly into the validation set.
　そして、これら校正セットと検証セットを主成分分析してスペクトル特性空間を得て、このスペクトル特性空間においてマハラノビス距離法により、校正セットと検証セットの各サンプルが最も近似したサンプルを校正サブセットとして選択しシンドロームセットとして集める。 Then, the calibration set and the validation set are subjected to principal component analysis to obtain a spectral feature space, and in this spectral feature space, the samples in which the calibration set and the validation set are most similar are selected as the calibration subset by the Mahalanobis distance method. Collect as a Syndrome Set.
　その後、シンドロームセットから主成分数を補助変数の教師データとして抽出し、誤差逆伝播法（Ｂａｃｋｐｒｏｐａｇａｔｉｏｎ：ＢＰ）ニューラルネットワークの入力層として回帰モデルを構築し、予測・推定モデルを学習する（特許文献１参照）。 After that, extract the number of principal components from the syndrome set as training data for auxiliary variables, build a regression model as an input layer of a backpropagation (BP) neural network, and learn a prediction/estimation model (Patent Document 1 reference).
中国特許出願公開第１０７６５５８５０号明細書Chinese Patent Application Publication No. 107655850
　しかしながら、上記特許文献１に開示されたシステムでは、説明変数の教師データである近赤外スペクトルデータの代わりに、補助変数の教師データである主成分数を利用して、回帰モデルを構築し予測・推定モデルを学習している。予測・推定の精度を向上させるためには、より多くの教師データにより予測・推定モデルを学習することが望まれる。このため、説明変数と補助変数とを共に教師データとして使用して、予測・推定モデルを学習することも考えられる。 However, in the system disclosed in Patent Document 1, instead of near-infrared spectrum data, which is teacher data for explanatory variables, the number of principal components, which is teacher data for auxiliary variables, is used to construct a regression model and make predictions.・The estimation model is learned. In order to improve the accuracy of prediction/estimation, it is desirable to learn the prediction/estimation model with more teacher data. For this reason, it is conceivable to learn a prediction/estimation model using both explanatory variables and auxiliary variables as teacher data.
　しかしながら、上述したようなシステムでは、補助変数が説明変数と相関を有するため、予測・推定の精度が却って悪化するという傾向がある。このような傾向は、特に重回帰分析では多重共線性として広く知られている。 However, in the system described above, the auxiliary variables are correlated with the explanatory variables, so the accuracy of prediction and estimation tends to deteriorate. Such a tendency is widely known as multicollinearity, especially in multiple regression analysis.
　本発明の一態様は、予測・推定の精度を向上させることが可能な予測・推定システム、学習装置及び予測・推定装置である。 One aspect of the present invention is a prediction/estimation system, a learning device, and a prediction/estimation device capable of improving the accuracy of prediction/estimation.
　本発明の一態様に係る予測・推定システムは、目的変数の教師データと、前記目的変数に作用する説明変数の教師データと、前記目的変数以外の変数で、前記説明変数と相関を有すると共に、前記説明変数が与えられたときに観測される補助変数の教師データと、を入力し、前記目的変数の予測・推定モデルを作成する学習装置と、前記目的変数を予測・推定するための前記説明変数の予測・推定用データと、前記目的変数を予測・推定するための前記補助変数の予測・推定用データと、を入力し、前記学習装置で作成された前記予測・推定モデルに基づいて、前記目的変数の予測・推定値を算出する予測・推定装置と、を備え、前記学習装置は、少なくとも前記補助変数の教師データから、潜在変数の教師データを算出し、潜在変数算出情報を出力する第１潜在変数算出部と、前記目的変数の教師データと、前記説明変数の教師データと、前記第１潜在変数算出部により算出された前記潜在変数の教師データと、を入力し、前記目的変数の予測・推定モデルを作成する予測・推定モデル学習部と、を含み、前記予測・推定装置は、少なくとも前記補助変数の予測・推定用データから、前記潜在変数算出情報に基づいて、潜在変数の予測・推定用データを算出する第２潜在変数算出部と、前記第２潜在変数算出部により算出された前記潜在変数の予測・推定用データと、前記説明変数の予測・推定用データから、前記予測・推定モデルに基づいて、前記目的変数の予測・推定値を算出する予測・推定部と、を含む。 A prediction/estimation system according to an aspect of the present invention includes teacher data of an objective variable, teacher data of an explanatory variable acting on the objective variable, and variables other than the objective variable that are correlated with the explanatory variable, a learning device for inputting teacher data of an auxiliary variable observed when the explanatory variable is given, and creating a prediction/estimation model of the objective variable; and the explanation for predicting/estimating the objective variable. Input data for prediction/estimation of variables and data for prediction/estimation of the auxiliary variables for predicting/estimating the objective variable, and based on the prediction/estimation model created by the learning device, a prediction/estimation device that calculates the prediction/estimation value of the objective variable, wherein the learning device calculates teacher data of the latent variable from at least the teacher data of the auxiliary variable, and outputs latent variable calculation information. A first latent variable calculation unit, training data of the objective variable, training data of the explanatory variable, and training data of the latent variable calculated by the first latent variable calculation unit are input, and the objective variable and a prediction/estimation model learning unit that creates a prediction/estimation model of at least the auxiliary variable, based on the latent variable calculation information, from the prediction/estimation data of the auxiliary variable. a second latent variable calculation unit that calculates prediction/estimation data; and from the prediction/estimation data of the latent variables calculated by the second latent variable calculation unit and the prediction/estimation data of the explanatory variables, the a prediction/estimation unit that calculates a prediction/estimation value of the objective variable based on the prediction/estimation model.
　本発明の一態様に係る予測・推定システムによれば、目的変数の教師データと、説明変数の教師データと、補助変数の教師データと、を入力し、少なくとも補助変数の教師データから潜在変数の教師データを算出し、潜在変数算出情報と目的変数の予測・推定モデルとが作成される。このため、説明変数の教師データとの間又は相互間の相関を補助変数よりも減らした潜在変数の教師データを使用することで、より多くの教師データを使用すること、及び、教師データ間の相関が排除されることにより、より精度の高い予測・推定モデルの作成が可能となる。また、少なくとも補助変数の予測・推定用データから、潜在変数算出情報に基づいて、潜在変数の予測・推定用データが算出され、この算出された潜在変数の予測・推定用データと、説明変数の予測・推定用データとから、予測・推定モデルに基づいて、目的変数の予測・推定値が算出される。このため、説明変数の予測・推定用データとの間又は相互間の相関を補助変数よりも減らした潜在変数の予測・推定用データを使用することで、より多くの予測・推定用データを使用すること、及び、予測・推定用データ間の相関が排除されることにより、より高精度の目的変数の予測・推定値を得ることが可能となる。 According to the prediction/estimation system according to one aspect of the present invention, the teacher data of the objective variable, the teacher data of the explanatory variables, and the teacher data of the auxiliary variables are input, and at least the teacher data of the auxiliary variables are used to predict the potential variables. Teacher data is calculated, and latent variable calculation information and a prediction/estimation model of objective variables are created. For this reason, by using teacher data of latent variables in which the correlation between explanatory variables and teacher data or between each other is reduced more than that of auxiliary variables, more teacher data can be used, and between teacher data By eliminating correlation, it becomes possible to create a more accurate prediction/estimation model. Further, from at least the data for prediction/estimation of the auxiliary variable, the data for prediction/estimation of the latent variable is calculated based on the latent variable calculation information, and the calculated data for prediction/estimation of the latent variable and the explanatory variable are combined. Based on the prediction/estimation data, the prediction/estimation value of the objective variable is calculated based on the prediction/estimation model. For this reason, more data for prediction/estimation can be used by using prediction/estimation data for latent variables whose correlation between explanatory variables and data for prediction/estimation is reduced more than for auxiliary variables. and the elimination of the correlation between the prediction/estimation data, it becomes possible to obtain a more highly accurate prediction/estimation value of the objective variable.
　本発明の一態様によれば、より多くのデータを利用して予測・推定の精度を向上させることができる。 According to one aspect of the present invention, it is possible to improve the accuracy of prediction/estimation using more data.
図１は、本発明の第１実施形態に係る予測・推定システムの基本的構成を示す説明図である。FIG. 1 is an explanatory diagram showing the basic configuration of the prediction/estimation system according to the first embodiment of the present invention. 図２は、予測・推定システムの学習装置及び／又は予測・推定装置の基本的なハードウェア構成を示す説明図である。FIG. 2 is an explanatory diagram showing a basic hardware configuration of a learning device and/or a prediction/estimation device of the prediction/estimation system. 図３は、本発明の第２実施形態に係る予測・推定システムの基本的構成を示す説明図である。FIG. 3 is an explanatory diagram showing the basic configuration of the prediction/estimation system according to the second embodiment of the present invention. 図４は、本発明の第３実施形態に係る予測・推定システムの基本的構成を示す説明図である。FIG. 4 is an explanatory diagram showing the basic configuration of the prediction/estimation system according to the third embodiment of the present invention. 図５は、本発明の第４実施形態に係る予測・推定システムの基本的構成を示す説明図である。FIG. 5 is an explanatory diagram showing the basic configuration of the prediction/estimation system according to the fourth embodiment of the present invention. 図６は、本発明の第５実施形態に係る予測・推定システムの基本的構成を示す説明図である。FIG. 6 is an explanatory diagram showing the basic configuration of the prediction/estimation system according to the fifth embodiment of the present invention. 図７は、本発明の第６実施形態に係る予測・推定システムが適用されたレーザ溶接の溶接強度の推定システムの基本的構成を示す説明図である。FIG. 7 is an explanatory diagram showing the basic configuration of a welding strength estimation system for laser welding to which a prediction/estimation system according to a sixth embodiment of the present invention is applied. 図８は、本発明の第７実施形態に係る予測・推定システムが適用される非破壊測定システムの学習装置の基本的構成を示す説明図である。FIG. 8 is an explanatory diagram showing the basic configuration of a learning device of a nondestructive measurement system to which the prediction/estimation system according to the seventh embodiment of the present invention is applied. 図９は、非破壊測定システムの非破壊試験装置の基本的構成を示す説明図である。FIG. 9 is an explanatory diagram showing the basic configuration of a nondestructive testing device of the nondestructive measurement system. 図１０は、本発明の第８実施形態に係る予測・推定システムが適用されたレーザ切断装置の切断品質の品質判定予測システムの基本的構成を示す説明図である。FIG. 10 is an explanatory diagram showing the basic configuration of a quality judgment/prediction system for cutting quality of a laser cutting apparatus to which the prediction/estimation system according to the eighth embodiment of the present invention is applied. 図１１は、図５に示した第４実施形態に係る予測・推定システムを実際のレーザ溶接に適用した実施例の補助変数を説明するための溶接温度と経過時間の関係を示すグラフである。FIG. 11 is a graph showing the relationship between welding temperature and elapsed time for explaining auxiliary variables in an example in which the prediction/estimation system according to the fourth embodiment shown in FIG. 5 is applied to actual laser welding. 図１２は、比較例及び実施例における推定値と測定値の関係と、推定値の推定値に対する誤差の度数分布を示すグラフである。FIG. 12 is a graph showing the relationship between estimated values and measured values and the frequency distribution of errors of estimated values with respect to estimated values in Comparative Example and Example.
　以下、添付の図面を参照して、本発明の実施の形態に係る予測・推定システム、学習装置及び予測・推定装置を詳細に説明する。ただし、以下の実施の形態は、各請求項に係る発明を限定するものではなく、また、実施の形態の中で説明されている特徴の組み合わせの全てが発明の解決手段に必須であるとは限らない。また、以下の実施の形態においては、各構成要素の縮尺や寸法が誇張されて示されている場合、及び一部の構成要素が省略されている場合がある。 Hereinafter, a prediction/estimation system, a learning device, and a prediction/estimation device according to embodiments of the present invention will be described in detail with reference to the accompanying drawings. However, the following embodiments do not limit the invention according to each claim, and all combinations of features described in the embodiments are essential to the solution of the invention. Not exclusively. Further, in the following embodiments, the scale and dimensions of each component may be exaggerated, and some components may be omitted.
［第１実施形態］
　図１は、本発明の第１実施形態に係る予測・推定システムの基本的構成を示す説明図である。図２は、予測・推定システムの学習装置及び／又は予測・推定装置の基本的なハードウェア構成を示す説明図である。 [First embodiment]
FIG. 1 is an explanatory diagram showing the basic configuration of the prediction/estimation system according to the first embodiment of the present invention. FIG. 2 is an explanatory diagram showing a basic hardware configuration of a learning device and/or a prediction/estimation device of the prediction/estimation system.
　図１に示すように、第１実施形態に係る予測・推定システム１００は、様々な種類の目的変数の予測・推定値８を得るためのシステムである。予測・推定システム１００は、目的変数の教師データ１と、目的変数に作用する説明変数の教師データ２と、目的変数以外の変数で、説明変数と相関を有すると共に、説明変数が与えられたときに観測される補助変数の教師データ３と、を入力し、例えば機械学習によって目的変数の予測・推定モデル７を作成する学習装置１０を備える。また、予測・推定システム１００は、目的変数を予測・推定するための説明変数の予測・推定用データ４と、目的変数を予測・推定するための補助変数の予測・推定用データ５と、を入力し、学習装置１０で作成された予測・推定モデル７に基づいて、目的変数の予測・推定値８を算出する予測・推定装置２０を備える。 As shown in FIG. 1, the prediction/estimation system 100 according to the first embodiment is a system for obtaining prediction/estimation values 8 of various types of objective variables. The prediction/estimation system 100 includes teacher data 1 of the objective variable, teacher data 2 of the explanatory variable acting on the objective variable, and variables other than the objective variable that are correlated with the explanatory variable, and when the explanatory variable is given and training data 3 of the auxiliary variables observed in the learning device 10 to create a prediction/estimation model 7 of the target variable by, for example, machine learning. In addition, the prediction/estimation system 100 includes explanatory variable prediction/estimation data 4 for predicting/estimating the objective variable, and auxiliary variable prediction/estimating data 5 for predicting/estimating the objective variable. A prediction/estimation device 20 is provided for inputting and calculating a prediction/estimation value 8 of an objective variable based on the prediction/estimation model 7 created by the learning device 10 .
　学習装置１０は、少なくとも補助変数の教師データ３から、補助変数の教師データ３よりも説明変数の教師データ２との間又は相互間の相関が小さい（相関を減じた）潜在変数の教師データ（図示せず）を算出し、潜在変数算出情報６を出力する第１潜在変数算出部１１を含む。また、学習装置１０は、目的変数の教師データ１と、説明変数の教師データ２と、第１潜在変数算出部１１により算出された潜在変数の教師データと、を入力し、例えば機械学習を行って、目的変数の予測・推定モデル７を作成する予測・推定モデル学習部１２を含む。 The learning device 10 generates, from at least the auxiliary variable teacher data 3, latent variable teacher data (reduced correlation) that has a smaller correlation (reduced correlation) with the explanatory variable teacher data 2 than the auxiliary variable teacher data 3 ( (not shown)) and outputs latent variable calculation information 6. Further, the learning device 10 inputs the teacher data 1 of the objective variable, the teacher data 2 of the explanatory variable, and the teacher data of the latent variable calculated by the first latent variable calculator 11, and performs machine learning, for example. and includes a prediction/estimation model learning unit 12 that creates a prediction/estimation model 7 of the objective variable.
　予測・推定装置２０は、少なくとも補助変数の予測・推定用データ５から、潜在変数算出情報６に基づいて、補助変数の予測・推定用データ５よりも説明変数の予測・推定用データ４との間又は相互間の相関が小さい（相関を減じた）潜在変数の予測・推定用データ（図示せず）を算出する第２潜在変数算出部２１を含む。また、予測・推定装置２０は、第２潜在変数算出部２１により算出された潜在変数の予測・推定用データと、説明変数の予測・推定用データ４とから、予測・推定モデル７に基づいて、目的変数の予測・推定値８を算出する予測・推定部２２を含む。 The prediction/estimation device 20 extracts at least the auxiliary variable prediction/estimation data 5 from the explanatory variable prediction/estimation data 4 rather than the auxiliary variable prediction/estimation data 5 based on the latent variable calculation information 6. It includes a second latent variable calculation unit 21 that calculates prediction/estimation data (not shown) of latent variables with small inter- or inter-correlation (reduced correlation). Further, the prediction/estimation device 20 uses the prediction/estimation data of the latent variables calculated by the second latent variable calculation unit 21 and the prediction/estimation data 4 of the explanatory variables based on the prediction/estimation model 7. , a prediction/estimation unit 22 for calculating the prediction/estimation value 8 of the objective variable.
　なお、予測・推定システム１００は、上述したように様々な種類の目的変数の予測・推定値を得ることが可能なシステムである。この予測・推定システム１００を、一例として後述するレーザ溶接の溶接強度の推定システムに適用した場合、例えば目的変数としては、溶接強度Ｆ（Ｎ／ｍｍ２）が挙げられる。また、例えば説明変数としては、溶接条件（レーザ出力値、レーザ照射時間等）が挙げられる。さらに、説明変数と相関を有する補助変数としては、例えば溶接時又は溶接後に観測される物理量（溶接温度、音、光、色等）が挙げられる。なお、予測・推定システム１００で用いられる目的変数、説明変数及び補助変数は、これら例示したものに限定されるものではない。 The prediction/estimation system 100 is a system capable of obtaining prediction/estimation values of various types of objective variables as described above. When this prediction/estimation system 100 is applied to, as an example, a system for estimating the welding strength of laser welding, which will be described later, the objective variable is, for example, the welding strength F (N/mm 2 ). Further, for example, explanatory variables include welding conditions (laser output value, laser irradiation time, etc.). Further, the auxiliary variables correlated with the explanatory variables include, for example, physical quantities observed during or after welding (welding temperature, sound, light, color, etc.). Note that the objective variable, explanatory variable, and auxiliary variable used in the prediction/estimation system 100 are not limited to these examples.
　また、学習装置１０の第１潜在変数算出部１１及び予測・推定装置２０の第２潜在変数算出部２１で算出される潜在変数の教師データ及び潜在変数の予測・推定用データは、それぞれ補助変数よりも説明変数との間又は相互間の相関を減じるように補助変数が、又は補助変数及び説明変数が、例えば次元削減又は次元圧縮されたものである。 Further, the latent variable teacher data and the latent variable prediction/estimation data calculated by the first latent variable calculation unit 11 of the learning device 10 and the second latent variable calculation unit 21 of the prediction/estimation device 20 are respectively used as auxiliary variables An auxiliary variable, or an auxiliary variable and an explanatory variable, are, for example, dimensionality-reduced or dimensionality-compressed so as to reduce the correlation between or between the explanatory variables than the explanatory variables.
　すなわち、潜在変数は、本実施形態においては、説明変数と同様に目的変数を特徴付ける変数であり、直接は観測されないが観測された変数（補助変数）から推定される変数である。言い換えれば、潜在変数は、観測された変数を特徴付ける変数であって、少なくとも補助変数から次元削減又は次元圧縮されたものを意味する。 That is, in this embodiment, the latent variable is a variable that characterizes the objective variable in the same way as the explanatory variable, and is a variable that is not directly observed but is estimated from the observed variable (auxiliary variable). In other words, a latent variable means a variable that characterizes the observed variable and is dimensionality-reduced or dimensionality-compressed from at least the auxiliary variable.
　予測・推定システム１００で用いられる説明変数、目的変数、潜在変数、並びに潜在変数算出情報６は、各々１つ以上の変数又はパラメータから構成され得る。本明細書においては、「目的変数の予測・推定」とは、「目的変数の予測」又は「目的変数の推定」の意味で用いられる。「目的変数の予測」は、未来（将来）に実現すると考えられる目的変数を想定することを意味する。「目的変数の推定」は、現在実現しているが、直接観測することのできない目的変数を推し量ることを意味する。「相関」とは、複数の変数の間の線形の関係に限定せず、線形、非線形にかかわらず、複数の変数の間で、１つの変数が変化すれば他の変数が変化するという関係を意味する。 The explanatory variables, objective variables, latent variables, and latent variable calculation information 6 used in the prediction/estimation system 100 can each consist of one or more variables or parameters. In this specification, "prediction/estimation of the objective variable" is used to mean "prediction of the objective variable" or "estimation of the objective variable". "Prediction of objective variable" means to assume an objective variable that is expected to be realized in the future (future). "Estimating the objective variable" means estimating an objective variable that is currently realized but not directly observable. "Correlation" is not limited to a linear relationship between multiple variables, but regardless of whether it is linear or non-linear, a relationship between multiple variables in which a change in one variable causes a change in the other variables. means.
　学習装置１０の第１潜在変数算出部１１は、学習装置１０に入力された目的変数の教師データ１、説明変数の教師データ２及び補助変数の教師データ３を含むデータのうち、少なくとも補助変数の教師データ３を含むデータから潜在変数の教師データを算出する。第１潜在変数算出部１１は、潜在変数の教師データの算出を、例えば所定のアルゴリズムを用いて行う。アルゴリズムは、例えば、回帰分析（Ｒｅｇｒｅｓｓｉｏｎ　Ａｎａｌｙｓｉｓ：ＲＡ）、主成分分析（Ｐｒｉｎｃｉｐａｌ　Ｃｏｍｐｏｎｅｎｔ　Ａｎａｌｙｓｉｓ：ＰＣＡ）、特異値分解（Ｓｉｎｇｕｌａｒ　Ｖａｌｕｅ　Ｄｅｃｏｍｐｏｓｉｔｉｏｎ：ＳＶＤ）、線形判別分析（Ｌｉｎｅａｒ　Ｄｉｓｃｒｉｍｉｎａｎｔ　Ａｎａｌｙｓｉｓ：ＬＤＡ）、独立成分分析（Ｉｎｄｅｐｅｎｄｅｎｔ　Ｃｏｍｐｏｎｅｎｔ　Ａｎａｌｙｓｉｓ：ＩＣＡ）、及びガウス過程潜在変数モデル（Ｇａｕｓｓｉａｎ　Ｐｒｏｃｅｓｓ　Ｌａｔｅｎｔ　Ｖａｒｉａｂｌｅ　Ｍｏｄｅｌ：ＧＰＬＶＭ）の少なくとも一つを含む。なお、アルゴリズムは、これらに限定されるものではない。潜在変数算出情報６は、第１潜在変数算出部１１において、潜在変数の教師データの算出に際して決定され、追加の潜在変数の算出に際して用いられる各種情報を意味する。潜在変数算出情報６には、例えば各種パラメータ、各種式及び／又はアルゴリズムが含まれる。 The first latent variable calculation unit 11 of the learning device 10 calculates at least the auxiliary variable out of the data including the objective variable teacher data 1, the explanatory variable teacher data 2, and the auxiliary variable teacher data 3 input to the learning device 10. The teacher data of the latent variables are calculated from the data including the teacher data 3 . The first latent variable calculator 11 calculates latent variable training data using, for example, a predetermined algorithm. Algorithms include, for example, regression analysis (RA), principal component analysis (PCA), singular value decomposition (SVD), linear discriminant analysis (LDA), independent component analysis (Independent Component Analysis: ICA), and at least one of Gaussian Process Latent Variable Model (GPLVM). Note that the algorithms are not limited to these. The latent variable calculation information 6 means various kinds of information that is determined when calculating latent variable teacher data in the first latent variable calculation unit 11 and used when calculating additional latent variables. The latent variable calculation information 6 includes various parameters, various formulas and/or algorithms, for example.
　学習装置１０の予測・推定モデル学習部１２は、学習装置１０に入力された目的変数の教師データ１、説明変数の教師データ２、及び第１潜在変数算出部１１で算出された潜在変数の教師データを入力して、目的変数の予測・推定モデル７の作成を、例えば機械学習によって行う。学習方法は、回帰、分類、クラスタリング、判別、補間、特徴量抽出、及び時系列モデリング等のアルゴリズムを含むが、これに限定されるものではない。予測・推定モデル学習部１２で学習された予測・推定モデル７は、学習モデルを特徴付ける予測・推定のための各種パラメータ、各種式及び／又はアルゴリズムを含む。そして、学習装置１０は、少なくとも潜在変数算出情報６と予測・推定モデル７と、を予測・推定装置２０に対して出力する。 The prediction/estimation model learning unit 12 of the learning device 10 receives the objective variable teacher data 1 and the explanatory variable teacher data 2 input to the learning device 10, and the latent variable teacher data calculated by the first latent variable calculator 11. By inputting data, the target variable prediction/estimation model 7 is created by, for example, machine learning. Learning methods include, but are not limited to, algorithms such as regression, classification, clustering, discrimination, interpolation, feature quantity extraction, and time series modeling. The prediction/estimation model 7 learned by the prediction/estimation model learning unit 12 includes various parameters, various formulas and/or algorithms for prediction/estimation that characterize the learning model. Then, the learning device 10 outputs at least the latent variable calculation information 6 and the prediction/estimation model 7 to the prediction/estimation device 20 .
　一方、予測・推定装置２０の第２潜在変数算出部２１は、少なくとも補助変数の予測・推定用データ５から、潜在変数算出情報６に基づいて、潜在変数の予測・推定用データを算出する。従って、潜在変数算出情報６がアルゴリズムを含んでいる場合、第２潜在変数算出部２１は、学習装置１０の第１潜在変数算出部１１で潜在変数の教師データの算出に用いられたアルゴリズムと同じアルゴリズムを用いて、潜在変数の予測・推定用データの算出を行う。このように、予測・推定時においても、学習時と同じアルゴリズムを用いて潜在変数を算出することで、同一の予測・推定モデル７を用いた予測・推定が可能になる。 On the other hand, the second latent variable calculation unit 21 of the prediction/estimation device 20 calculates prediction/estimation data for latent variables based on the latent variable calculation information 6 from at least the prediction/estimation data 5 for the auxiliary variables. Therefore, when the latent variable calculation information 6 includes an algorithm, the second latent variable calculation unit 21 uses the same algorithm as the one used to calculate latent variable teacher data in the first latent variable calculation unit 11 of the learning device 10. Calculate data for predicting and estimating latent variables using algorithms. In this way, prediction/estimation using the same prediction/estimation model 7 becomes possible by calculating latent variables using the same algorithm as that used in learning during prediction/estimation.
　予測・推定装置２０の予測・推定部２２は、予測・推定装置２０に入力された説明変数の予測・推定用データ４、予測・推定モデル７、及び第２潜在変数算出部２１で算出された潜在変数の予測・推定用データに基づいて、目的変数の予測・推定値８を算出し、出力する。 The prediction/estimation unit 22 of the prediction/estimation device 20 uses the prediction/estimation data 4 of the explanatory variables input to the prediction/estimation device 20, the prediction/estimation model 7, and the second latent variable calculation unit 21. Based on the latent variable prediction/estimation data, the target variable prediction/estimation value 8 is calculated and output.
　なお、学習装置１０側から予測・推定装置２０側へ渡される潜在変数算出情報６は、学習装置１０又は予測・推定装置２０で潜在変数の算出に適切なものが選択され得る。例えば、学習装置１０における潜在変数の教師データの算出が主成分分析によって行われる場合、潜在変数パラメータとして、主成分ベクトル及び固有値であって良く、これらに加え特定の補助変数の教師データ３の寄与率が所定値よりも高い主成分ベクトルを除外した潜在変数パラメータを選択するようにしても良い。これにより、補助変数よりも説明変数との間又は相互間の相関が小さい潜在変数を説明変数と共に教師データ及び予測・推定用データに用いることができるので、多重共線性に起因する予測・推定精度の悪化が回避可能となる。 It should be noted that the latent variable calculation information 6 passed from the learning device 10 side to the prediction/estimation device 20 side can be selected by the learning device 10 or the prediction/estimation device 20 to be suitable for calculating latent variables. For example, when the learning device 10 calculates the teacher data of the latent variables by principal component analysis, the latent variable parameters may be principal component vectors and eigenvalues. It is also possible to select latent variable parameters excluding principal component vectors whose rates are higher than a predetermined value. As a result, it is possible to use the latent variables that have a smaller correlation with or between the explanatory variables than the auxiliary variables, together with the explanatory variables, for the teacher data and prediction/estimation data. aggravation can be avoided.
　予測・推定システム１００における目的変数の教師データ１、説明変数の教師データ２、補助変数の教師データ３、説明変数の予測・推定用データ４、及び補助変数の予測・推定用データ５の各データは、例えば図示しない据置型若しくは可搬性を有する記憶装置又は記憶媒体に記憶され得る。また、各データは、例えばインターネット等の情報通信媒体を介して送受信され得るもので、図示しないセンサ等の測定装置によって取得された生データであっても良い。また、潜在変数算出情報６及び予測・推定モデル７は、学習装置１０及び予測・推定装置２０間で上記記憶媒体又は情報通信媒体を介して入出力されても良い。 Objective variable teacher data 1, explanatory variable teacher data 2, auxiliary variable teacher data 3, explanatory variable prediction/estimation data 4, and auxiliary variable prediction/estimation data 5 in the prediction/estimation system 100. can be stored, for example, in a stationary or portable storage device or storage medium (not shown). Further, each data can be transmitted and received via an information communication medium such as the Internet, and may be raw data acquired by a measuring device such as a sensor (not shown). Further, the latent variable calculation information 6 and the prediction/estimation model 7 may be input/output between the learning device 10 and the prediction/estimation device 20 via the above storage medium or information communication medium.
　図２に示すように、予測・推定システム１００の学習装置１０及び／又は予測・推定装置２０は、基本的なハードウェア構成として、例えばＣＰＵ２０１と、ＲＡＭ２０２と、ＲＯＭ２０３と、ＨＤＤ（ハードディスクドライブ）２０４と、ＳＳＤ（ソリッドステートドライブ）２０５と、メモリカード２０６と、を備える。また、学習装置１０及び／又は予測・推定装置２０は、例えば入力Ｉ／Ｆ（インタフェース）２０７と、出力Ｉ／Ｆ（インタフェース）２０８と、通信Ｉ／Ｆ（インタフェース）２０９と、を備える。各構成部２０１～２０９は、それぞれバス２００によって相互に接続されている。 As shown in FIG. 2, the learning device 10 and/or the prediction/estimation device 20 of the prediction/estimation system 100 has a basic hardware configuration such as a CPU 201, a RAM 202, a ROM 203, and a HDD (hard disk drive) 204. , an SSD (Solid State Drive) 205 and a memory card 206 . The learning device 10 and/or the prediction/estimation device 20 also includes an input I/F (interface) 207, an output I/F (interface) 208, and a communication I/F (interface) 209, for example. Each component 201 to 209 is interconnected by a bus 200, respectively.
　ＣＰＵ２０１は、ＲＡＭ２０２、ＲＯＭ２０３、ＨＤＤ２０４、ＳＳＤ２０５等に記憶された各種プログラムを実行することで、学習装置１０及び／又は予測・推定装置２０を制御する。ＣＰＵ２０１は、学習装置１０においては学習プログラムを実行することで、上記第１潜在変数算出部１１及び予測・推定モデル学習部１２の機能を実現する。また、ＣＰＵ２０１は、予測・推定装置２０においては予測・判定プログラムを実行することで、上記第２潜在変数算出部２１及び予測・推定部２２の機能を実現する。なお、学習装置１０及び予測・推定装置２０の各ＣＰＵ２０１が協働することで、予測・推定システム１００の全体を制御するように構成し得る。 The CPU 201 controls the learning device 10 and/or the prediction/estimation device 20 by executing various programs stored in the RAM 202, ROM 203, HDD 204, SSD 205, and the like. The CPU 201 implements the functions of the first latent variable calculation unit 11 and the prediction/estimation model learning unit 12 by executing a learning program in the learning device 10 . Further, the CPU 201 implements the functions of the second latent variable calculation unit 21 and the prediction/estimation unit 22 by executing the prediction/determination program in the prediction/estimation device 20 . Note that the CPUs 201 of the learning device 10 and the prediction/estimation device 20 can be configured to control the entire prediction/estimation system 100 by cooperating.
　ＲＡＭ２０２は、ＣＰＵ２０１の演算処理の作業領域として使用され得る。ＲＯＭ２０３は、上記の各種プログラムを少なくとも読み出し可能に格納する。ＨＤＤ２０４及びＳＳＤ２０５は、上述した各種のデータを読み書き可能に記憶する。メモリカード２０６は、これら各種のデータを読み書き可能に記憶すると共に、各装置１０，２０に対して着脱自在な記憶媒体を構成する。ＨＤＤ２０４、ＳＳＤ２０５及びメモリカード２０６は、上述した記憶装置又は記憶媒体の機能を実現する。 The RAM 202 can be used as a work area for arithmetic processing of the CPU 201. The ROM 203 stores at least the various programs described above in a readable manner. The HDD 204 and SSD 205 store the various data described above in a readable and writable manner. The memory card 206 stores these various data in a readable and writable manner, and constitutes a removable storage medium for each device 10 , 20 . The HDD 204, SSD 205, and memory card 206 implement the functions of the storage device or storage medium described above.
　入力Ｉ／Ｆ２０７には、例えばセンサ２１２が接続されて検出情報が取得される。センサ２１２は、温度センサ、光センサ、音響センサ、画像センサ等の各種センサが含まれる。なお、入力Ｉ／Ｆ２０７は、学習装置１０及び／又は予測・推定装置２０の操作部又は入力部として機能するタッチパネル２１１が接続され、予測・推定システム１００のユーザからの操作入力に伴う情報を受け付ける。入力Ｉ／Ｆ２０７には、図示しないキーボード及びマウス（トラックボールマウスを含む）等の各種の入力デバイスも接続され得る。 For example, a sensor 212 is connected to the input I/F 207 to acquire detection information. The sensor 212 includes various sensors such as a temperature sensor, an optical sensor, an acoustic sensor, and an image sensor. The input I/F 207 is connected to the touch panel 211 functioning as an operation unit or an input unit of the learning device 10 and/or the prediction/estimation device 20, and receives information accompanying an operation input from the user of the prediction/estimation system 100. . Various input devices such as a keyboard and a mouse (including a trackball mouse) (not shown) can also be connected to the input I/F 207 .
　出力Ｉ／Ｆ２０８には、例えば表示装置としてのディスプレイ２１０が接続され、学習装置１０及び／又は予測・推定装置２０でモニタ表示される各種情報が出力される。タッチパネル２１１は、ディスプレイ２１０上に設けられていても良い。また、学習装置１０及び／又は予測・推定装置２０は、通信Ｉ／Ｆ２０９を介して、図示しないインターネット等のネットワークに接続されたサーバ装置及び外部機器等と間接的又は直接的に接続され得る。 A display 210 as a display device, for example, is connected to the output I/F 208, and various types of information displayed on the monitor by the learning device 10 and/or the prediction/estimation device 20 are output. The touch panel 211 may be provided on the display 210 . Also, the learning device 10 and/or the prediction/estimation device 20 can be indirectly or directly connected to a server device and external devices connected to a network such as the Internet (not shown) via the communication I/F 209 .
　第１実施形態の予測・推定システム１００では、学習装置１０の第１潜在変数算出部１１で、少なくとも補助変数の教師データ３を含むデータから潜在変数の教師データを算出し、この潜在変数の教師データを含むデータを用いて予測・推定モデル学習部１２で、予測・推定モデル７の学習・作成を行う。そして、学習装置１０で潜在変数の教師データの算出で決定された潜在変数算出情報６を、予測・推定装置２０に与える。潜在変数算出情報６が与えられた予測・推定装置２０の第２潜在変数算出部２１では、第１潜在変数算出部１１が利用したアルゴリズムと同じアルゴリズムを用いて、少なくとも補助変数の予測・推定用データ５を含むデータから潜在変数の予測・推定用データを算出する。そして、この潜在変数の予測・推定用データを含むデータを用いて、予測・推定部２２で目的変数の予測・推定値８を算出する。これにより、第１実施形態の予測・推定システム１００によれば、補助変数を潜在変数に変換することによって、予測・推定の精度を向上させることができる。 In the prediction/estimation system 100 of the first embodiment, the first latent variable calculation unit 11 of the learning device 10 calculates latent variable teacher data from data including at least the auxiliary variable teacher data 3, and the latent variable teacher data is calculated. A prediction/estimation model learning unit 12 learns and creates a prediction/estimation model 7 using data including data. Then, the latent variable calculation information 6 determined by the calculation of the teacher data of the latent variables in the learning device 10 is provided to the prediction/estimation device 20 . The second latent variable calculation unit 21 of the prediction/estimation device 20 to which the latent variable calculation information 6 is provided uses the same algorithm as that used by the first latent variable calculation unit 11 to calculate at least auxiliary variables for prediction/estimation. Data for prediction/estimation of latent variables are calculated from data including data 5 . Then, using the data including the latent variable prediction/estimation data, the prediction/estimation unit 22 calculates the prediction/estimation value 8 of the objective variable. Thus, according to the prediction/estimation system 100 of the first embodiment, the accuracy of prediction/estimation can be improved by converting an auxiliary variable into a latent variable.
［第２実施形態］
　図３は、本発明の第２実施形態に係る予測・推定システムの基本的構成を示す説明図である。なお、図３を含む以降の説明においては、第１の実施形態及びその変形例と同一の構成要素に関しては同一の符号を付しているので、以下では重複する説明は省略する。 [Second embodiment]
FIG. 3 is an explanatory diagram showing the basic configuration of the prediction/estimation system according to the second embodiment of the present invention. In the following description including FIG. 3, the same reference numerals are given to the same constituent elements as those of the first embodiment and its modification, so redundant description will be omitted below.
　図３に示すように、第２実施形態に係る予測・推定システム１００Ａでは、学習装置１０の第１潜在変数算出部１１は、説明変数の教師データ２と、補助変数の教師データ３とを入力し、潜在変数の教師データ（図示せず）を算出し、潜在変数算出情報６を出力する。また、予測・推定装置２０の第２潜在変数算出部２１は、説明変数の予測・推定用データ４と、補助変数の予測・推定用データ５とを入力し、潜在変数算出情報６に基づき潜在変数の予測・推定用データ（図示せず）を算出する。 As shown in FIG. 3, in the prediction/estimation system 100A according to the second embodiment, the first latent variable calculation unit 11 of the learning device 10 receives teacher data 2 of explanatory variables and teacher data 3 of auxiliary variables. , latent variable teacher data (not shown) is calculated, and latent variable calculation information 6 is output. Further, the second latent variable calculation unit 21 of the prediction/estimation device 20 inputs the prediction/estimation data 4 of the explanatory variables and the prediction/estimation data 5 of the auxiliary variables, and calculates the latent variables based on the latent variable calculation information 6 . Data for predicting/estimating variables (not shown) is calculated.
　すなわち、第２実施形態の予測・推定システム１００Ａでは、学習装置１０の第１潜在変数算出部１１が、潜在変数の教師データを算出するために入力するデータとして、補助変数の教師データ３の他に、説明変数の教師データ２も含む点で、第１実施形態の予測・推定システム１００の学習装置１０とは相違している。また、予測・推定装置２０の第２潜在変数算出部２１が、潜在変数の予測・推定用データを算出するために入力するデータとして、補助変数の予測・推定用データ５の他に、説明変数の予測・推定用データ４も含む点で、第１実施形態の予測・推定システム１００の予測・推定装置２０とは相違している。 That is, in the prediction/estimation system 100A of the second embodiment, the first latent variable calculation unit 11 of the learning device 10 uses the teaching data 3 of the auxiliary variables as input data to calculate the teaching data of the latent variables. Furthermore, it is different from the learning device 10 of the prediction/estimation system 100 of the first embodiment in that it also includes teacher data 2 of explanatory variables. In addition to the auxiliary variable prediction/estimation data 5, the second latent variable calculation unit 21 of the prediction/estimation device 20 uses explanatory variables is different from the prediction/estimation device 20 of the prediction/estimation system 100 of the first embodiment in that it also includes the prediction/estimation data 4 of the first embodiment.
　第２実施形態によれば、学習装置１０の第１潜在変数算出部１１及び予測・推定装置２０の第２潜在変数算出部２１において、それぞれ説明変数に関するデータも利用して各潜在変数の教師データ及び予測・推定用データを算出している。このため、説明変数と補助変数との間の相関を減じた潜在変数を用いた高精度な予測・推定が可能になる。また、第２実施形態によれば、潜在変数の算出のために、より多くのデータを使用するので、より高次元及び高度なアルゴリズムに基づいて潜在変数を算出することができる。これにより、相関による予測・推定精度の悪化を回避しつつ、補助変数を利用した予測・推定の精度をより向上させることができる。 According to the second embodiment, the first latent variable calculation unit 11 of the learning device 10 and the second latent variable calculation unit 21 of the prediction/estimation device 20 also use the data related to the explanatory variables to obtain teacher data for each latent variable. and calculation of prediction/estimation data. Therefore, highly accurate prediction/estimation using latent variables with reduced correlation between explanatory variables and auxiliary variables is possible. Also, according to the second embodiment, more data is used to calculate latent variables, so latent variables can be calculated based on higher-dimensional and advanced algorithms. As a result, it is possible to further improve the accuracy of prediction/estimation using auxiliary variables while avoiding deterioration of prediction/estimation accuracy due to correlation.
［第３実施形態］
　図４は、本発明の第３実施形態に係る予測・推定システムの基本的構成を示す説明図である。図４に示すように、第３実施形態に係る予測・推定システム１００Ｂでは、予測・推定装置２０の第２潜在変数算出部２１は、説明変数の予測・推定用データ４及び補助変数の予測・推定用データ５に加えて、更に、説明変数の教師データ２と、補助変数の教師データ３と、学習装置１０の第１潜在変数算出部１１で算出された潜在変数の教師データ１３と、に基づき潜在変数の予測・推定用データ２３を算出する。 [Third embodiment]
FIG. 4 is an explanatory diagram showing the basic configuration of the prediction/estimation system according to the third embodiment of the present invention. As shown in FIG. 4, in the prediction/estimation system 100B according to the third embodiment, the second latent variable calculation unit 21 of the prediction/estimation device 20 includes predictive/estimation data 4 for explanatory variables and prediction/estimation data 4 for auxiliary variables. In addition to the estimation data 5, the explanatory variable teacher data 2, the auxiliary variable teacher data 3, and the latent variable teacher data 13 calculated by the first latent variable calculator 11 of the learning device 10, Based on this, latent variable prediction/estimation data 23 is calculated.
　すなわち、第３実施形態の予測・推定システム１００Ｂでは、予測・推定装置２０の第２潜在変数算出部２１が、潜在変数の予測・推定用データ２３を算出するための入力データとして、補助変数の予測・推定用データ５及び説明変数の予測・推定用データ４と共に、説明変数の教師データ２、補助変数の教師データ３及び潜在変数の教師データ１３も含む点で、第２実施形態の予測・推定システム１００Ａとは相違している。 That is, in the prediction/estimation system 100B of the third embodiment, the second latent variable calculation unit 21 of the prediction/estimation device 20 uses auxiliary variable In addition to prediction/estimation data 5 and explanatory variable prediction/estimation data 4, explanatory variable teacher data 2, auxiliary variable teacher data 3, and latent variable teacher data 13 are also included. It is different from the estimation system 100A.
　第３実施形態によれば、予測・推定装置２０の第２潜在変数算出部２１において、説明変数及び補助変数の教師データ２，３も利用して潜在変数の予測・推定用データ２３を算出している。このため、第２実施形態よりも多くのデータを用いて潜在変数の予測・推定用データ２３を算出することができる。これにより、更に高度なアルゴリズムを適用し、相関による予測・推定精度の悪化を回避しつつ、補助変数を利用した予測・推定の精度をより向上させることができる。 According to the third embodiment, in the second latent variable calculation unit 21 of the prediction/estimation device 20, the prediction/estimation data 23 of the latent variables are calculated using the teaching data 2 and 3 of the explanatory variables and the auxiliary variables. ing. Therefore, the latent variable prediction/estimation data 23 can be calculated using more data than in the second embodiment. As a result, it is possible to apply a more advanced algorithm and improve the accuracy of prediction/estimation using auxiliary variables while avoiding deterioration in prediction/estimation accuracy due to correlation.
［第４実施形態］
　図５は、本発明の第４実施形態に係る予測・推定システムの基本的構成を示す説明図である。第４実施形態に係る予測・推定システム１００Ｃでは、学習装置１０の第１潜在変数算出部１１は、所定のアルゴリズム（潜在変数算出情報６）として、回帰分析及び主成分分析を用いて潜在変数の教師データ（図示せず）を算出する。また、予測・推定装置２０の第２潜在変数算出部２１は、第１潜在変数算出部１１で用いられたアルゴリズム（潜在変数算出情報６）を用いて潜在変数の予測・推定用データ（図示せず）を算出する。 [Fourth embodiment]
FIG. 5 is an explanatory diagram showing the basic configuration of the prediction/estimation system according to the fourth embodiment of the present invention. In the prediction/estimation system 100C according to the fourth embodiment, the first latent variable calculation unit 11 of the learning device 10 calculates the latent variables using regression analysis and principal component analysis as a predetermined algorithm (latent variable calculation information 6). Calculate teacher data (not shown). The second latent variable calculation unit 21 of the prediction/estimation device 20 uses the algorithm (latent variable calculation information 6) used in the first latent variable calculation unit 11 to generate latent variable prediction/estimation data (not shown). ) are calculated.
　より具体的には、図５に示すように、第４実施形態に係る予測・推定システム１００Ｃでは、学習装置１０の第１潜在変数算出部１１は、補助変数の教師データ３を説明変数の教師データ２で回帰分析し回帰モデルを作成する第１回帰分析部１４と、第１回帰分析部１４による回帰分析の回帰誤差１５を主成分分析し潜在変数の教師データ（図示せず）を算出する第１主成分分析部１６と、を含む。潜在変数算出情報６は、回帰モデルのパラメータ及び回帰式と、主成分分析の主成分ベクトル及び固有値と、を含む。また、予測・推定装置２０の第２潜在変数算出部２１は、潜在変数算出情報６に基づき補助変数の予測・推定用データ５を説明変数の予測・推定用データ４で回帰分析し回帰モデルを作成する第２回帰分析部２４と、潜在変数算出情報６に基づき第２回帰分析部２４による回帰誤差２５を主成分分析して潜在変数の予測・推定用データ（図示せず）を算出する第２主成分分析部２６と、を含む。 More specifically, as shown in FIG. 5, in the prediction/estimation system 100C according to the fourth embodiment, the first latent variable calculation unit 11 of the learning device 10 converts the teacher data 3 of the auxiliary variables into the teacher data 3 of the explanatory variables. A first regression analysis unit 14 performs regression analysis on data 2 to create a regression model, and a regression error 15 of the regression analysis by the first regression analysis unit 14 is subjected to principal component analysis to calculate latent variable teacher data (not shown). and a first principal component analysis unit 16 . The latent variable calculation information 6 includes regression model parameters and regression equations, and principal component vectors and eigenvalues of principal component analysis. Further, the second latent variable calculation unit 21 of the prediction/estimation device 20 performs regression analysis on the auxiliary variable prediction/estimation data 5 with the explanatory variable prediction/estimation data 4 based on the latent variable calculation information 6 to create a regression model. A second regression analysis unit 24 to create, and a second regression analysis unit 24 for calculating latent variable prediction/estimation data (not shown) by principal component analysis of regression errors 25 by the second regression analysis unit 24 based on the latent variable calculation information 6 and a two-principal component analysis unit 26 .
　すなわち、第４実施形態の予測・推定システム１００Ｃは、学習装置１０の第１潜在変数算出部１１及び予測・推定装置２０の第２潜在変数算出部２１が第１回帰分析部１４及び第１主成分分析部１６を含み、回帰分析及び主成分分析を行って潜在変数の教師データを算出する点、並びに第２潜在変数算出部２１が第２回帰分析部２４及び第２主成分分析部２６を含み、回帰分析及び主成分分析を行って潜在変数の予測・推定用データを算出する点で、第２実施形態に係る予測・推定システム１００Ａとは相違している。 That is, in the prediction/estimation system 100C of the fourth embodiment, the first latent variable calculation unit 11 of the learning device 10 and the second latent variable calculation unit 21 of the prediction/estimation device 20 are the first regression analysis unit 14 and the first principal It includes a component analysis unit 16 and performs regression analysis and principal component analysis to calculate teacher data for latent variables, and the second latent variable calculation unit 21 performs a second regression analysis unit 24 and a second principal component analysis unit 26. It is different from the prediction/estimation system 100A according to the second embodiment in that the latent variable prediction/estimation data is calculated by performing regression analysis and principal component analysis.
　第４実施形態の予測・推定システム１００Ｃでは、学習装置１０の第１潜在変数算出部１１の第１回帰分析部１４において、補助変数の教師データ３を説明変数の教師データ２で回帰分析（ＲＡ）し、回帰モデルが作成される。第１回帰分析部１４で作成された回帰モデルの回帰誤差１５は、第１主成分分析部１６において主成分分析（ＰＣＡ）され、これにより潜在変数の教師データが算出される。このとき、例えば主成分パラメータとして、説明変数と補助変数との間の相関が小さい主成分ベクトルを選択する。これにより、学習装置１０の第１潜在変数算出部１１においては、説明変数の教師データ２と相関が小さい潜在変数の教師データを算出することができる。 In the prediction/estimation system 100C of the fourth embodiment, the first regression analysis unit 14 of the first latent variable calculation unit 11 of the learning device 10 performs regression analysis (RA ) and a regression model is created. A regression error 15 of the regression model created by the first regression analysis unit 14 is subjected to principal component analysis (PCA) by the first principal component analysis unit 16, thereby calculating teacher data of latent variables. At this time, for example, a principal component vector having a small correlation between the explanatory variable and the auxiliary variable is selected as the principal component parameter. As a result, the first latent variable calculation unit 11 of the learning device 10 can calculate latent variable teacher data that has a small correlation with the explanatory variable teacher data 2 .
　予測・推定モデル学習部１２では、このように算出された相関の小さな潜在変数の教師データを含むデータを用いて予測・推定モデル７の作成が、例えば機械学習により行われる。これにより、補助変数の教師データ３と説明変数の教師データ２の相関に起因する予測・推定精度の悪化を避けることが可能となる。なお、この場合、潜在変数算出情報６に含まれる回帰モデルは、回帰係数等のデータを含んでいても良い。また、潜在変数算出情報６に含まれる主成分パラメータは、主成分ベクトル及び標本分散行列の固有値等のデータを含んでいても良い。 In the prediction/estimation model learning unit 12, the prediction/estimation model 7 is created by, for example, machine learning using the data including the teacher data of the latent variables with small correlation calculated in this way. This makes it possible to avoid deterioration in prediction/estimation accuracy due to the correlation between the teacher data 3 of the auxiliary variable and the teacher data 2 of the explanatory variable. In this case, the regression model included in the latent variable calculation information 6 may include data such as regression coefficients. Also, the principal component parameters included in the latent variable calculation information 6 may include data such as the eigenvalues of the principal component vector and the sample variance matrix.
　そして、予測・推定装置２０の第２潜在変数算出部２１において、第１潜在変数算出部１１での回帰モデルのパラメータ及び回帰式、並びに主成分分析の主成分パラメータを含む潜在変数算出情報６が用いられる。この潜在変数算出情報６を用いて、第２回帰分析部２４において、補助変数の予測・推定用データ５を説明変数の予測・推定用データ４で回帰分析（ＲＡ）し、回帰モデルが作成される。第２回帰分析部２４で作成された回帰モデルの回帰誤差２５は、第２主成分分析部２６において主成分分析（ＰＣＡ）され、これにより潜在変数の予測・推定用データが算出される。従って、予測・推定装置２０においては、説明変数の予測・推定用データ４と相関が小さい潜在変数の予測・推定用データの算出を、学習装置１０と同様の潜在変数算出情報６を用いて行うことが可能となる。 Then, in the second latent variable calculation unit 21 of the prediction/estimation device 20, the latent variable calculation information 6 including the parameters and regression formula of the regression model in the first latent variable calculation unit 11 and the principal component parameters of the principal component analysis is Used. Using this latent variable calculation information 6, the second regression analysis unit 24 performs regression analysis (RA) on the auxiliary variable prediction/estimation data 5 with the explanatory variable prediction/estimation data 4 to create a regression model. be. The regression error 25 of the regression model generated by the second regression analysis unit 24 is subjected to principal component analysis (PCA) by the second principal component analysis unit 26, thereby calculating latent variable prediction/estimation data. Therefore, in the prediction/estimation device 20, the latent variable prediction/estimation data having a small correlation with the explanatory variable prediction/estimation data 4 is calculated using the latent variable calculation information 6 similar to that of the learning device 10. becomes possible.
　予測・推定部２２では、このように算出された相関の小さな潜在変数の予測・推定用データを含むデータを用いて目的変数の予測・推定値８が算出される。これにより、補助変数の予測・推定用データ５と説明変数の予測・推定用データ４の相関に起因する予測・推定精度の悪化を低減した上で、目的変数の予測・推定値８をより高精度に得ることが可能となる。 In the prediction/estimation unit 22, the prediction/estimation value 8 of the objective variable is calculated using the data including the prediction/estimation data of the latent variable with small correlation calculated in this way. As a result, the deterioration of the prediction/estimation accuracy due to the correlation between the auxiliary variable prediction/estimation data 5 and the explanatory variable prediction/estimation data 4 is reduced, and the target variable prediction/estimation value 8 is increased. can be obtained with precision.
［第５実施形態］
　図６は、本発明の第５実施形態に係る予測・推定システムの基本的構成を示す説明図である。図６に示すように、第５実施形態に係る予測・推定システム１００Ｄでは、学習装置１０の第１潜在変数算出部１１は、ガウス過程潜在変数モデル（ＧＰＬＶＭ）により潜在変数の教師データ１３を算出し、潜在変数算出情報６は、ガウス過程潜在変数モデル（ＧＰＬＶＭ）のハイパーパラメータを含む。また、学習装置１０の予測・推定モデル学習部１２は、ガウス過程回帰（ＧＰＲ）により、例えば機械学習を行って、目的変数の予測・推定モデル７を作成する。また、予測・推定装置２０の第２潜在変数算出部２１は、ガウス過程潜在変数モデル（ＧＰＬＶＭ）により潜在変数の予測・推定用データ２３を算出し、予測・推定装置２０の予測・推定部２２は、ガウス過程回帰（ＧＰＲ）により目的変数の予測・推定値８を算出する。 [Fifth embodiment]
FIG. 6 is an explanatory diagram showing the basic configuration of the prediction/estimation system according to the fifth embodiment of the present invention. As shown in FIG. 6, in the prediction/estimation system 100D according to the fifth embodiment, the first latent variable calculation unit 11 of the learning device 10 calculates latent variable teacher data 13 using a Gaussian process latent variable model (GPLVM). and the latent variable calculation information 6 includes hyperparameters of a Gaussian process latent variable model (GPLVM). Also, the prediction/estimation model learning unit 12 of the learning device 10 performs, for example, machine learning using Gaussian process regression (GPR) to create the prediction/estimation model 7 of the objective variable. Further, the second latent variable calculation unit 21 of the prediction/estimation device 20 calculates latent variable prediction/estimation data 23 using a Gaussian process latent variable model (GPLVM), and the prediction/estimation unit 22 of the prediction/estimation device 20 calculates the predicted/estimated value 8 of the objective variable by Gaussian process regression (GPR).
　すなわち、第５実施形態の予測・推定システム１００Ｄでは、学習装置１０の第１潜在変数算出部１１及び予測・推定装置２０の第２潜在変数算出部２１が、潜在変数の教師データ１３及び潜在変数の予測・推定用データ２３の算出にガウス過程潜在変数モデル（ＧＰＬＶＭ）のアルゴリズムを用いている点、並びに学習装置１０の予測・推定モデル学習部１２及び予測・推定装置２０の予測・推定部２２が、目的変数の予測・推定モデル７の学習及び目的変数の予測・推定値８の算出にガウス過程回帰（ＧＰＲ）のアルゴリズムを用いている点で、第３実施形態の予測・推定システム１００Ｂとは相違している。 That is, in the prediction/estimation system 100D of the fifth embodiment, the first latent variable calculation unit 11 of the learning device 10 and the second latent variable calculation unit 21 of the prediction/estimation device 20 use the latent variable teacher data 13 and the latent variable The Gaussian process latent variable model (GPLVM) algorithm is used to calculate the prediction/estimation data 23, and the prediction/estimation model learning unit 12 of the learning device 10 and the prediction/estimation unit 22 of the prediction/estimation device 20 However, the prediction/estimation system 100B of the third embodiment differs from the prediction/estimation system 100B of the third embodiment in that a Gaussian process regression (GPR) algorithm is used for learning the target variable prediction/estimation model 7 and calculating the target variable prediction/estimation value 8. are different.
　第５実施形態によれば、第１潜在変数算出部１１及び第２潜在変数算出部２１において潜在変数の教師データ１３及び潜在変数の予測・推定用データ２３をガウス過程潜在変数モデル（ＧＰＬＶＭ）を用いて算出し、予測・推定モデル学習部１２及び予測・推定部２２において予測・推定モデル７及び予測・推定値８をガウス過程回帰（ＧＰＲ）を用いて学習・算出している。これにより、第５実施形態では、第３実施形態の予測・推定システム１００Ｂと同様の作用効果を奏することができると共に、主成分分析（ＰＣＡ）や独立成分分析（ＩＣＡ）のような線形モデルではなく、非線形モデルを用いた予測・推定に特化したシステムを実現することができる。 According to the fifth embodiment, in the first latent variable calculation unit 11 and the second latent variable calculation unit 21, the latent variable teacher data 13 and the latent variable prediction/estimation data 23 are converted into a Gaussian process latent variable model (GPLVM). The prediction/estimation model learning unit 12 and the prediction/estimation unit 22 learn/calculate the prediction/estimation model 7 and the prediction/estimation value 8 using Gaussian process regression (GPR). As a result, in the fifth embodiment, it is possible to achieve the same effects as the prediction/estimation system 100B of the third embodiment, and in linear models such as principal component analysis (PCA) and independent component analysis (ICA) It is possible to realize a system specialized for prediction/estimation using a nonlinear model.
［第６実施形態］
　図７は、本発明の第６実施形態に係る予測・推定システムが適用されたレーザ溶接の溶接強度の推定システムの基本的構成を示す説明図である。図７に示すように、第６実施形態の溶接強度の推定システム１００Ｅは、第１～第５実施形態に係る予測・推定システム１００～１００Ｄの構成を適用可能な推定システムとして構成され得る。 [Sixth embodiment]
FIG. 7 is an explanatory diagram showing the basic configuration of a welding strength estimation system for laser welding to which a prediction/estimation system according to a sixth embodiment of the present invention is applied. As shown in FIG. 7, the welding strength estimation system 100E of the sixth embodiment can be configured as an estimation system to which the configurations of the prediction/estimation systems 100 to 100D according to the first to fifth embodiments can be applied.
　なお、第６実施形態の推定システム１００Ｅにおいて、目的変数は、レーザ溶接機９によるレーザ溶接の溶接強度（溶接強度データ１Ａ）又は溶接品質（図示せず）である。また、説明変数は、レーザ溶接の溶接条件（溶接条件データ２Ａ）である。更に、補助変数は、レーザ溶接に関してレーザ溶接時又は溶接後に観測可能な物理量（溶接温度データ３Ａ）である。また、例えば説明変数の予測・推定用データとしては、レーザ溶接機９に設定される溶接条件データ４Ａが挙げられる。また、補助変数の予測・推定用データとしては、レーザ溶接機９においてレーザ溶接時又は溶接後に観測される物理量の一つである溶接温度データ５Ａが挙げられる。 In the estimation system 100E of the sixth embodiment, the objective variable is the welding strength (welding strength data 1A) or welding quality (not shown) of laser welding by the laser welder 9. The explanatory variable is the welding condition of laser welding (welding condition data 2A). Further, the auxiliary variable is a physical quantity (welding temperature data 3A) observable during or after laser welding with respect to laser welding. Further, for example, data for prediction/estimation of explanatory variables includes welding condition data 4A set in the laser welding machine 9 . Data for predicting/estimating the auxiliary variables include welding temperature data 5A, which is one of physical quantities observed in the laser welding machine 9 during or after laser welding.
　溶接強度データ１Ａは、例えばレーザ溶接機９により下記溶接条件データ２Ａに基づきレーザ溶接が施される被加工物の種類に応じて、被加工物の溶接部の許容応力度と材料強度により定まる溶接強度Ｆ（Ｎ／ｍｍ２）を表す。溶接品質は、例えば上記のようなレーザ溶接が施される被加工物の種類に応じて求められた溶接強度Ｆに基づいて、予め定められた溶接の品質（優良、良、可、不可等）を表す。 The welding strength data 1A is determined by the allowable stress and material strength of the welded portion of the workpiece according to the type of the workpiece to be laser-welded based on the following welding condition data 2A by the laser welder 9, for example. It represents the strength F (N/mm 2 ). Welding quality is a predetermined quality of welding (excellent, good, acceptable, unsatisfactory, etc.) based on, for example, the welding strength F obtained according to the type of workpiece to be laser-welded as described above. represents
　溶接条件データ２Ａは、例えば被加工物の仕様（材質、厚さ等）、レーザ溶接機９のレーザ出力値、レーザ照射時間、レーザ光の焦点位置、レーザ光の周波数やデューティ比等のパルス条件、溶接速度、照射開始からピークパワーまでの到達時間、ピークパワーから照射終了までの経過時間、レンズ焦点距離、レンズ焦点位置、照射点のレーザ径、ファイバ径、及びスポット径（レンズ・ファイバ・焦点位置の組み合わせ）の各種情報を含む。溶接条件データ２Ａは、レーザ溶接のために設定される任意のパラメータである。なお、溶接温度データ３Ａは、例えば溶接条件データ２Ａに基づくレーザ溶接時に検出される溶接温度を表す。 The welding condition data 2A includes, for example, the specifications of the workpiece (material, thickness, etc.), the laser output value of the laser welder 9, the laser irradiation time, the focal position of the laser light, and pulse conditions such as the frequency and duty ratio of the laser light. , welding speed, time from start of irradiation to peak power, elapsed time from peak power to end of irradiation, lens focal length, lens focal position, laser diameter at irradiation point, fiber diameter, and spot diameter (lens, fiber, focus position combination). The welding condition data 2A are arbitrary parameters set for laser welding. Welding temperature data 3A represents, for example, the welding temperature detected during laser welding based on welding condition data 2A.
　溶接条件データ４Ａは、レーザ溶接機９に実際に設定される溶接条件に関するデータであり、溶接条件データ２Ａと同様に構成される。溶接温度データ５Ａは、レーザ溶接機９に備えられた溶接温度センサ１７で検出された実際のレーザ溶接時に検出され取得された溶接温度を表す。なお、溶接温度センサ１７は上述したセンサ２１２に含まれる。また、溶接強度データ１Ａ、溶接条件データ２Ａ及び溶接温度データ３Ａは、例えばネットワーク９０に接続された図示しない外部の記憶装置又は記憶媒体に、読み出し可能な状態で記憶されている。なお、ネットワーク９０は、データを受け渡しするための媒体であれば良く、インターネット、ＬＡＮ等のネットワークに止まらず、機器を構成するバス、ＵＳＢ、或いはＨＤＤ等の可搬性を有する記憶媒体等であっても良く、その形態に特に制約はない。 The welding condition data 4A is data relating to welding conditions actually set in the laser welder 9, and is configured in the same manner as the welding condition data 2A. The welding temperature data 5A represents the welding temperature detected and acquired during actual laser welding detected by the welding temperature sensor 17 provided in the laser welder 9 . Welding temperature sensor 17 is included in sensor 212 described above. The welding strength data 1A, the welding condition data 2A, and the welding temperature data 3A are stored in a readable state in an external storage device or storage medium (not shown) connected to the network 90, for example. Note that the network 90 may be a medium for exchanging data, and is not limited to networks such as the Internet and LAN, but may be a bus, USB, or a portable storage medium such as an HDD that constitutes a device. There are no particular restrictions on its form.
　推定システム１００Ｅは、ネットワーク９０を介して互いに通信可能に接続された上述した学習装置１０として機能する学習サーバ３０と、上述した予測・推定装置２０として機能する推定エッジサーバ４０と、を備える。また、推定システム１００Ｅは、潜在変数算出情報６及び溶接強度推定モデル７Ａ（の少なくとも一つ）を記憶する記憶装置５０を備える。なお、本実施形態では、学習サーバ３０にも、記憶装置５０と同様の機能を有する記憶部５０Ａが備えられている。また、図示は省略するが、記憶部５０Ａと同等の記憶部は、推定エッジサーバ４０に備えられていても良い。 The estimation system 100E includes a learning server 30 functioning as the above-described learning device 10 and an estimation edge server 40 functioning as the above-described prediction/estimation device 20, which are communicably connected to each other via a network 90. The estimation system 100E also includes a storage device 50 that stores (at least one of) the latent variable calculation information 6 and the welding strength estimation model 7A. In this embodiment, the learning server 30 is also provided with a storage unit 50A having the same function as the storage device 50. FIG. Although not shown, a storage unit equivalent to the storage unit 50A may be provided in the estimated edge server 40. FIG.
　学習サーバ３０は、目的変数の教師データと、目的変数に作用する説明変数の教師データと、目的変数以外の変数で、説明変数と相関を有すると共に、説明変数が与えられたときに観測される補助変数の教師データと、を入力可能に構成される。また、学習サーバ３０は、少なくとも補助変数の教師データから、補助変数の教師データよりも説明変数の教師データとの間又は相互間の相関が小さい潜在変数の教師データ（図示せず）を算出し、潜在変数算出情報６を出力する潜在変数算出部（第１潜在変数算出部３１）を備える。また、学習サーバ３０は、目的変数の教師データと、説明変数の教師データと、潜在変数算出部（第１潜在変数算出部３１）により算出された潜在変数の教師データと、を入力し、例えば機械学習を行って、目的変数の予測・推定モデル（溶接強度推定モデル７Ａ）を作成する予測・推定モデル学習部（溶接強度推定モデル学習部３２）を備える。 The learning server 30 has the teacher data of the objective variable, the teacher data of the explanatory variables acting on the objective variable, and the variables other than the objective variable, which are correlated with the explanatory variables and observed when the explanatory variables are given. It is configured to be able to input teacher data of auxiliary variables. In addition, the learning server 30 calculates latent variable teacher data (not shown) having a smaller correlation between or with the explanatory variable teacher data than the auxiliary variable teacher data from at least the auxiliary variable teacher data. , a latent variable calculation unit (first latent variable calculation unit 31) that outputs latent variable calculation information 6; Further, the learning server 30 inputs teacher data of objective variables, teacher data of explanatory variables, and teacher data of latent variables calculated by the latent variable calculator (first latent variable calculator 31). A prediction/estimation model learning unit (welding strength estimation model learning unit 32) that performs machine learning and creates a prediction/estimation model (welding strength estimation model 7A) of the objective variable is provided.
　一方、推定エッジサーバ４０は、目的変数の教師データと、目的変数に作用する説明変数の教師データと、目的変数以外の変数で、説明変数と相関を有すると共に、説明変数が与えられたときに観測される補助変数の教師データから、潜在変数算出情報６に基づき算出された、潜在変数の教師データと、を用いて予め学習された目的変数の予測・推定モデル（溶接強度推定モデル７Ａ）に基づいて、目的変数の予測・推定値（溶接強度の推定値８Ａ）を算出する予測・推定装置２０である。また、推定エッジサーバ４０は、少なくとも補助変数の予測・推定用データから、潜在変数算出情報６に基づいて、補助変数の予測・推定用データよりも説明変数の予測・推定用データとの間又は相互間の相関が小さい潜在変数の予測・推定用データ（図示せず）を算出する潜在変数算出部（第２潜在変数算出部４１）を備える。また、推定エッジサーバ４０は、潜在変数算出部（第２潜在変数算出部４１）により算出された潜在変数の予測・推定用データと、説明変数の予測・推定用データとから、予測・推定モデル（溶接強度推定モデル７Ａ）に基づいて、目的変数の予測・推定値（溶接強度の推定値８Ａ）を算出する予測・推定部（溶接強度推定部４２）を備える。 On the other hand, the estimated edge server 40 has the teacher data of the objective variable, the teacher data of the explanatory variables acting on the objective variable, and the variables other than the objective variable, which have correlation with the explanatory variables, and when the explanatory variables are given, From the observed auxiliary variable teacher data, the latent variable teacher data calculated based on the latent variable calculation information 6, and the target variable prediction/estimation model (welding strength estimation model 7A) learned in advance using Based on this, the prediction/estimation device 20 calculates the prediction/estimation value of the objective variable (estimated value 8A of welding strength). In addition, the estimation edge server 40 is based on the latent variable calculation information 6 from at least the data for prediction/estimation of the auxiliary variables, and the data for prediction/estimation of the explanatory variables rather than the data for prediction/estimation of the auxiliary variables. A latent variable calculation unit (second latent variable calculation unit 41) for calculating prediction/estimation data (not shown) of latent variables having a small mutual correlation is provided. In addition, the estimation edge server 40 generates a prediction/estimation model from the prediction/estimation data of the latent variables calculated by the latent variable calculation unit (second latent variable calculation unit 41) and the prediction/estimation data of the explanatory variables. A prediction/estimation unit (welding strength estimation unit 42) that calculates a prediction/estimation value (estimation value 8A of welding strength) of an objective variable based on (welding strength estimation model 7A) is provided.
　なお、学習サーバ３０及び推定エッジサーバ４０は、それぞれ上述した学習装置１０及び予測・推定装置２０として機能することができる。このため、学習サーバ３０及び推定エッジサーバ４０は、第１～第５実施形態において既に説明した全ての態様を実現することが可能である。このため、以降においては、学習装置１０及び予測・推定装置２０の各構成要素と重複する説明については省略する。 The learning server 30 and the estimation edge server 40 can function as the learning device 10 and the prediction/estimation device 20 described above, respectively. Therefore, the learning server 30 and the estimated edge server 40 can implement all aspects already described in the first to fifth embodiments. Therefore, hereinafter, explanations that overlap with the components of the learning device 10 and the prediction/estimation device 20 will be omitted.
［推定システムの動作］
　外部の記憶装置又は記憶媒体に記憶された溶接強度データ１Ａ、溶接条件データ２Ａ及び溶接温度データ３Ａは、それぞれ目的変数、説明変数及び補助変数の教師データとして、学習サーバ３０に入力され記憶部５０Ａに記憶される。学習サーバ３０は、これらの入力されたデータのうち、少なくとも溶接温度データ３Ａを含むデータに基づき、第１潜在変数算出部３１において潜在変数の教師データを算出する。また、学習サーバ３０は、溶接強度推定モデル学習部３２において、溶接強度データ１Ａと、溶接条件データ２Ａと、第１潜在変数算出部３１により算出された潜在変数の教師データと、を入力し、例えば機械学習を行って、溶接強度推定モデル７Ａを作成する。学習サーバ３０は、潜在変数の教師データの算出に際して決定された潜在変数算出情報６及び溶接強度推定モデル７Ａを、記憶部５０Ａに記憶すると共に、ネットワーク９０を介して記憶装置５０に出力する。記憶装置５０は、入力された潜在変数算出情報６及び溶接強度推定モデル７Ａを記憶する。なお、溶接強度データ１Ａ、溶接条件データ２Ａ及び溶接温度データ３Ａは、外部の記憶装置又は記憶媒体ではなく、例えば記憶装置５０に記憶されていても良い。 [Operation of estimation system]
Welding strength data 1A, welding condition data 2A, and welding temperature data 3A stored in an external storage device or storage medium are input to learning server 30 as teacher data for objective variables, explanatory variables, and auxiliary variables, respectively, and stored in storage unit 50A. stored in The learning server 30 calculates teacher data of latent variables in the first latent variable calculator 31 based on at least the welding temperature data 3A among the input data. In addition, the learning server 30 inputs the welding strength data 1A, the welding condition data 2A, and the teacher data of the latent variables calculated by the first latent variable calculation unit 31 in the welding strength estimation model learning unit 32, For example, machine learning is performed to create the welding strength estimation model 7A. The learning server 30 stores the latent variable calculation information 6 and the welding strength estimation model 7A determined when calculating latent variable teacher data in the storage unit 50A, and outputs them to the storage device 50 via the network 90. The storage device 50 stores the input latent variable calculation information 6 and welding strength estimation model 7A. The welding strength data 1A, the welding condition data 2A, and the welding temperature data 3A may be stored, for example, in the storage device 50 instead of the external storage device or storage medium.
　一方、レーザ溶接機９においては、設定された溶接条件データ４Ａに基づいてレーザ溶接が実行され、レーザ溶接機９に付属の溶接温度センサ１７によって、推定対象（例えば、被加工物の溶接部）のレーザ溶接時の溶接温度データ５Ａが取得される。レーザ溶接機９の溶接条件データ４Ａ及び溶接温度センサ１７からの溶接温度データ５Ａは、それぞれ説明変数の予測・推定用データ及び補助変数の予測・推定用データとして、推定エッジサーバ４０に入力される。また、記憶装置５０に記憶された潜在変数算出情報６及び溶接強度推定モデル７Ａも、推定エッジサーバ４０に入力される。 On the other hand, in the laser welder 9, laser welding is performed based on the set welding condition data 4A. Welding temperature data 5A during laser welding is acquired. The welding condition data 4A of the laser welder 9 and the welding temperature data 5A from the welding temperature sensor 17 are input to the estimation edge server 40 as explanatory variable prediction/estimation data and auxiliary variable prediction/estimation data, respectively. . The latent variable calculation information 6 and the welding strength estimation model 7A stored in the storage device 50 are also input to the estimation edge server 40 .
　推定エッジサーバ４０は、これら入力されたデータを記憶部に記憶すると共に、これらのデータのうち、少なくとも溶接温度データ５Ａを含むデータから、第２潜在変数算出部４１において潜在変数算出情報６に基づき潜在変数の予測・推定用データを算出する。また、推定エッジサーバ４０は、溶接強度推定部４２において、第２潜在変数算出部４１により算出された潜在変数の予測・推定用データと、溶接条件データ４Ａとから、溶接強度推定モデル７Ａに基づいて、溶接強度の推定値８Ａを算出する。算出された潜在変数の予測・推定用データと溶接強度の推定値８Ａは、記憶部に記憶されると共に、溶接強度の推定値８Ａは、表示、印刷等適宜利用可能な形態で推定エッジサーバ４０から出力され得る。 The estimated edge server 40 stores these input data in the storage unit, and from the data including at least the welding temperature data 5A, the second latent variable calculation unit 41 calculates the latent variable calculation information 6. Calculate data for predicting and estimating latent variables. In addition, in the welding strength estimation unit 42, the estimated edge server 40 uses the data for predicting/estimating the latent variables calculated by the second latent variable calculation unit 41 and the welding condition data 4A, based on the welding strength estimation model 7A. to calculate an estimated weld strength value of 8A. The calculated data for prediction/estimation of the latent variables and the estimated value 8A of the weld strength are stored in the storage unit, and the estimated value 8A of the weld strength is displayed, printed, or otherwise displayed in a form that can be used as appropriate by the estimation edge server 40. can be output from
　第６実施形態の推定システム１００Ｅでは、溶接強度データ１Ａの補助変数の教師データである溶接温度データ３Ａに基づき潜在変数の教師データを算出した上で、潜在変数の教師データを用いた溶接強度推定モデル７Ａが作成される。また、潜在変数の教師データの算出の際に決定された潜在変数算出情報６に基づき、補助変数の予測・推定用データである溶接温度データ５Ａから潜在変数の予測・推定用データを算出した上で、説明変数の予測・推定用データである溶接条件データ４Ａと潜在変数の予測・推定用データとから溶接強度推定モデル７Ａに基づいて、溶接強度の推定値８Ａが算出される。 In the estimation system 100E of the sixth embodiment, the latent variable teacher data is calculated based on the welding temperature data 3A, which is the auxiliary variable teacher data of the welding strength data 1A, and then the welding strength is estimated using the latent variable teacher data. A model 7A is created. Further, based on the latent variable calculation information 6 determined when calculating the teacher data of the latent variables, the data for prediction/estimation of the latent variables is calculated from the welding temperature data 5A, which is the data for prediction/estimation of the auxiliary variables. Then, an estimated welding strength value 8A is calculated based on the welding strength estimation model 7A from the welding condition data 4A, which is explanatory variable prediction/estimation data, and the latent variable prediction/estimation data.
　従って、第６実施形態の推定システム１００Ｅによれば、レーザ溶接の溶接条件に関するデータと溶接時の温度に関するデータから、非破壊で推定対象（被加工物の溶接部）の溶接強度を推定することが可能となる。一般的にレーザ溶接においては、同一の溶接条件でレーザ溶接を施した場合であっても、被加工物の材質、溶接環境のばらつき等の要因によって溶接強度は変化する。従って、製品を破壊しなければ溶接強度を測定することはできないという問題がある。しかし、第６実施形態の推定システム１００Ｅは、より多くのデータを利用した予測・推定精度の向上及び相関による予測・推定精度の悪化の回避を図ることができる構成を採用する。従って、推定システム１００Ｅは、この問題を解決することができると共に、第１～第５実施形態と同様の作用効果を奏することが可能となる。 Therefore, according to the estimation system 100E of the sixth embodiment, the welding strength of the estimation target (welded portion of the workpiece) can be non-destructively estimated from the data regarding the welding conditions of laser welding and the data regarding the temperature during welding. becomes possible. Generally, in laser welding, even when laser welding is performed under the same welding conditions, the welding strength varies depending on factors such as variations in the material of the workpiece and the welding environment. Therefore, there is a problem that the weld strength cannot be measured without destroying the product. However, the estimation system 100E of the sixth embodiment employs a configuration capable of improving prediction/estimation accuracy using more data and avoiding deterioration of prediction/estimation accuracy due to correlation. Therefore, the estimation system 100E can solve this problem and can achieve the same effects as those of the first to fifth embodiments.
　なお、第６実施形態の推定システム１００Ｅは、レーザ溶接の溶接強度の推定を目的としているが、これに限定されない。推定システム１００Ｅは、例えばスパッタやポロシティ等の溶接品質に関する各種の物理現象の予測・推定を行うことも可能である。この場合、目的変数をレーザ溶接の溶接品質とすれば良い。また、補助変数として、溶接温度データ３Ａ，５Ａを例にして説明したが、補助変数はこれに限定されるものではない。補助変数は、溶接時の音、光、色等の溶接時に観測される物理量、或いは溶接後の溶接部の溶接幅、色、スパッタの個数等の溶接後に観測される物理量であっても良い。推定システム１００Ｅは、学習サーバ３０、推定エッジサーバ４０、及び記憶装置５０を、例えばそれぞれレーザ溶接機９の設置箇所と同じ現場に集中して或いは遠隔地に別々に設置可能である。従って、推定システム１００Ｅは、レーザ溶接の溶接強度の推定に関して、グローバルな展開をも想定した多種多様な運用が可能となる。 Although the estimation system 100E of the sixth embodiment aims at estimating the welding strength of laser welding, it is not limited to this. The estimation system 100E can also predict and estimate various physical phenomena related to welding quality, such as spatter and porosity. In this case, the objective variable should be the welding quality of laser welding. Also, the welding temperature data 3A and 5A have been described as auxiliary variables, but the auxiliary variables are not limited to these. The auxiliary variables may be physical quantities observed during welding, such as sound, light, and color during welding, or physical quantities observed after welding, such as the weld width, color, and number of spatters of the welded portion after welding. The estimation system 100E can install the learning server 30, the estimation edge server 40, and the storage device 50, for example, centrally at the same site as the laser welding machine 9, or separately at a remote location. Therefore, the estimation system 100E can be used in a wide variety of operations, assuming global deployment, regarding the estimation of the welding strength of laser welding.
［第７実施形態］
　図８は、本発明の第７実施形態に係る予測・推定システムが適用される非破壊測定システムの学習装置の基本的構成を示す説明図である。図９は、非破壊測定システムの非破壊試験装置の基本的構成を示す説明図である。図８及び図９に示すように、第７実施形態の非破壊測定システム１００Ｆは、第１～第５実施形態に係る予測・推定システム１００～１００Ｄの構成を適用可能な非破壊測定システムとして構成され得る。 [Seventh Embodiment]
FIG. 8 is an explanatory diagram showing the basic configuration of a learning device of a nondestructive measurement system to which the prediction/estimation system according to the seventh embodiment of the present invention is applied. FIG. 9 is an explanatory diagram showing the basic configuration of a nondestructive testing device of the nondestructive measurement system. As shown in FIGS. 8 and 9, the nondestructive measurement system 100F of the seventh embodiment is configured as a nondestructive measurement system to which the configurations of the prediction/estimation systems 100 to 100D according to the first to fifth embodiments can be applied. can be
　非破壊測定システム１００Ｆは、図８に示すような学習装置３３と、図９に示すような予測・推定装置４３を含む非破壊試験装置４９と、を備える。学習装置３３は、第１潜在変数算出部３４と、予測・推定モデル学習部３５と、を備える。非破壊試験装置４９の予測・推定装置４３は、第２潜在変数算出部４４と、予測・推定部４５と、を備える。 The nondestructive measurement system 100F includes a learning device 33 as shown in FIG. 8 and a nondestructive testing device 49 including a prediction/estimation device 43 as shown in FIG. The learning device 33 includes a first latent variable calculation unit 34 and a prediction/estimation model learning unit 35 . The prediction/estimation device 43 of the nondestructive testing device 49 includes a second latent variable calculator 44 and a prediction/estimation unit 45 .
　なお、非破壊測定システム１００Ｆにおいて、目的変数は、コンクリートの強度（強度性状データ１Ｂ）である。また、説明変数は、測定可能なコンクリートの強度の影響要因・条件（影響要因・条件データ２Ｂ）である。更に、補助変数は、強度の測定時の弾性波伝搬特性（弾性波伝搬特性データ３Ｂ）である。また、例えば説明変数の予測・推定用データとしては、強度の予測・推定を行うコンクリートにおける影響要因・条件データ４Ｂが挙げられる。また、補助変数の予測・推定用データとしては、測定装置（音響センサ１８）で取得されたデータに基づく弾性波伝搬特性データ５Ｂが挙げられる。強度性状データ１Ｂ、強度の影響要因・条件データ２Ｂ及び弾性波伝搬特性データ３Ｂは、学習装置３３に入力される。強度の影響要因・条件データ４Ｂ及び弾性波伝搬特性データ５Ｂは、非破壊試験装置４９の予測・推定装置４３に入力される。 In the nondestructive measurement system 100F, the objective variable is the concrete strength (strength property data 1B). Further, the explanatory variable is the measurable influence factor/condition of the concrete strength (influence factor/condition data 2B). Further, the auxiliary variable is the elastic wave propagation characteristic (elastic wave propagation characteristic data 3B) at the time of intensity measurement. Further, for example, data for prediction/estimation of explanatory variables includes influence factor/condition data 4B in concrete for strength prediction/estimation. Further, as data for prediction/estimation of auxiliary variables, there is elastic wave propagation characteristic data 5B based on data acquired by a measuring device (acoustic sensor 18). The strength property data 1 B, the strength influence factor/condition data 2 B, and the elastic wave propagation characteristic data 3 B are input to the learning device 33 . The strength influence factor/condition data 4 B and the elastic wave propagation characteristic data 5 B are input to the prediction/estimation device 43 of the nondestructive testing device 49 .
　強度性状データ１Ｂは、例えばコンクリートの強度を表すものとして、圧縮強度、引張強度、曲げ強度、せん断強度、支圧強度、付着強度、疲労強度等を含み得る。強度性状データ１Ｂは、本実施形態ではコンクリートの圧縮強度Ｆ（Ｎ／ｍｍ２）を表す。強度の影響要因・条件データ２Ｂは、例えばコンクリートの材料であるセメント種別、セメント水比、セメント添加剤、材齢、コンクリートの打設時から強度測定時までの温度及び湿度等の各種情報を含むが、これらに限定されるものではない。 The strength property data 1B can include, for example, compressive strength, tensile strength, bending strength, shear strength, bearing strength, adhesion strength, fatigue strength, etc., as data representing the strength of concrete. The strength property data 1B represents the compressive strength F (N/mm 2 ) of concrete in this embodiment. The strength influence factor/condition data 2B includes, for example, various types of information such as cement type, cement water ratio, cement additive, material age, temperature and humidity from concrete placement to strength measurement. However, it is not limited to these.
　弾性波伝搬特性データ３Ｂは、弾性波伝搬速度、弾性波反射特性等を表すが、これらに限定されるものではない。弾性波伝搬特性データ３Ｂは、非破壊測定システム１００Ｆにおける非破壊測定で得られる特性データであれば、種々のものが適用可能である。強度の影響要因・条件データ４Ｂは、強度を予測・推定するコンクリートの強度の影響要因・条件に関するデータである。強度の影響要因・条件データ４Ｂは、学習装置３３に入力される強度の影響要因・条件データ２Ｂと同様に構成される。弾性波伝搬特性データ５Ｂは、音響センサ１８で検出された音響データから導出された弾性波伝搬特性を表す。弾性波伝搬特性データ５Ｂは、学習装置３３に入力される弾性波伝搬特性データ３Ｂと同様に構成される。なお、音響センサ１８は上述したセンサ２１２に含まれる。 The elastic wave propagation characteristic data 3B represents elastic wave propagation velocity, elastic wave reflection characteristics, etc., but is not limited to these. Various types of elastic wave propagation characteristic data 3B can be applied as long as they are characteristic data obtained by nondestructive measurement in the nondestructive measurement system 100F. The strength influence factor/condition data 4B is data relating to the strength influence factor/condition of the concrete for predicting/estimating the strength. The strength influence factor/condition data 4 B is configured in the same manner as the strength influence factor/condition data 2 B input to the learning device 33 . The elastic wave propagation characteristic data 5B represents elastic wave propagation characteristics derived from acoustic data detected by the acoustic sensor 18 . The elastic wave propagation characteristic data 5B is configured similarly to the elastic wave propagation characteristic data 3B input to the learning device 33. FIG. Note that the acoustic sensor 18 is included in the sensor 212 described above.
［非破壊測定システムの動作］
　強度性状データ１Ｂ、強度の影響要因・条件データ２Ｂ及び弾性波伝搬特性データ３Ｂは、それぞれ目的変数、説明変数及び補助変数の教師データとして学習装置３３に入力される。学習装置３３は、これら入力されたデータのうち、少なくとも強度の影響要因・条件データ２Ｂ及び弾性波伝搬特性データ３Ｂを含むデータに基づき第１潜在変数算出部３４において潜在変数の教師データを算出する。また、学習装置３３は、予測・推定モデル学習部３５において強度性状データ１Ｂと、強度の影響要因・条件データ２Ｂと、第１潜在変数算出部３４により算出された潜在変数の教師データと、を入力し、例えば機械学習を行って、コンクリート強度の予測・推定モデル７を作成する。学習装置３３は、潜在変数の教師データの算出に際して決定された潜在変数算出情報６及びコンクリート強度の予測・推定モデル７を、外部に出力する。 [Operation of non-destructive measurement system]
The strength property data 1B, the strength influence factor/condition data 2B, and the elastic wave propagation characteristic data 3B are input to the learning device 33 as teacher data for objective variables, explanatory variables, and auxiliary variables, respectively. The learning device 33 calculates teacher data of latent variables in the first latent variable calculator 34 based on data including at least intensity influence factor/condition data 2B and elastic wave propagation characteristic data 3B among these input data. . In addition, the learning device 33 receives the strength property data 1B, the strength influence factor/condition data 2B, and the teacher data of the latent variables calculated by the first latent variable calculation unit 34 in the prediction/estimation model learning unit 35. Then, for example, machine learning is performed to create a concrete strength prediction/estimation model 7 . The learning device 33 outputs to the outside the latent variable calculation information 6 and the concrete strength prediction/estimation model 7 that are determined when calculating latent variable teacher data.
　一方、非破壊試験装置４９には、学習装置３３から出力された潜在変数算出情報６及び予測・推定モデル７が備えられる。なお、これら潜在変数算出情報６及び予測・推定モデル７は、非破壊試験装置４９が有する記憶媒体又は非破壊試験装置４９に着脱自在な可搬性の記憶媒体に記憶されたり、インターネット等の情報伝達媒体から取得されたりして、非破壊試験装置４９に備えられる。 On the other hand, the nondestructive testing device 49 is equipped with the latent variable calculation information 6 and the prediction/estimation model 7 output from the learning device 33 . The latent variable calculation information 6 and the prediction/estimation model 7 are stored in a storage medium possessed by the nondestructive testing device 49 or in a portable storage medium detachable from the nondestructive testing device 49, or can be transmitted via the Internet or the like. It is obtained from a medium and provided in the non-destructive testing device 49 .
　また、非破壊試験装置４９には、音響センサ１８により検出されたコンクリート打撃時の音響データが入力され、この音響データに基づき導出された弾性波伝搬特性データ５Ｂが備えられる。そして、非破壊試験装置４９の予測・推定装置４３には、潜在変数算出情報６、予測・推定モデル７、及び弾性波伝搬特性データ５Ｂと共に、強度の影響要因・条件データ４Ｂが入力される。 In addition, the non-destructive testing device 49 is provided with elastic wave propagation characteristic data 5B derived based on the acoustic data detected by the acoustic sensor 18 when concrete is hit, and derived based on the acoustic data. Then, the prediction/estimation device 43 of the nondestructive testing device 49 receives the latent variable calculation information 6, the prediction/estimation model 7, the elastic wave propagation characteristic data 5B, and the strength influence factor/condition data 4B.
　予測・推定装置４３は、これら入力されたデータのうち、少なくとも強度の影響要因・条件データ４Ｂ及び弾性波伝搬特性データ５Ｂを含むデータから、第２潜在変数算出部４４において、潜在変数算出情報６に基づき潜在変数の予測・推定用データを算出する。また、予測・推定装置４３は、予測・推定部４５において、第２潜在変数算出部４４により算出された潜在変数の予測・推定用データと、強度の影響要因・条件データ４Ｂと、弾性波伝搬特性データ５Ｂとから、コンクリート強度の予測・推定モデル７に基づいて、コンクリート強度の予測・推定値８を算出する。算出された予測・推定値８は、表示、印刷等適宜利用可能な形態で非破壊試験装置４９から出力され得る。 The prediction/estimation device 43 calculates the latent variable calculation information 6 in the second latent variable calculator 44 from the data including at least the strength influence factor/condition data 4B and the elastic wave propagation characteristic data 5B among the input data. Calculate data for predicting and estimating latent variables based on In the prediction/estimation unit 45, the prediction/estimation device 43 includes latent variable prediction/estimation data calculated by the second latent variable calculation unit 44, intensity influence factor/condition data 4B, and elastic wave propagation Based on the concrete strength prediction/estimation model 7, a concrete strength prediction/estimation value 8 is calculated from the characteristic data 5B. The calculated predicted/estimated value 8 can be output from the non-destructive testing device 49 in a form that can be used as appropriate, such as display or printing.
　第７実施形態の非破壊測定システム１００Ｆでは、強度性状データ１Ｂの補助変数の教師データである弾性波伝搬特性データ３Ｂ及び説明変数の教師データである強度の影響要因・条件データ２Ｂに基づき潜在変数の教師データを算出した上で、潜在変数の教師データを用いたコンクリート強度の予測・推定モデル７が作成される。また、潜在変数の教師データの算出の際に決定された潜在変数算出情報６に基づき、補助変数の予測・推定用データである弾性波伝搬特性データ５Ｂ及び説明変数の予測・推定用データである強度の影響要因・条件データ４Ｂから潜在変数の予測・推定用データを算出した上で、強度の影響要因・条件データ４Ｂ、弾性波伝搬特性データ５Ｂ、及び潜在変数の予測・推定用データからコンクリート強度の予測・推定モデル７に基づいて、コンクリート強度の予測・推定値８が算出される。 In the non-destructive measurement system 100F of the seventh embodiment, a latent variable After calculating the teaching data of the latent variables, a concrete strength prediction/estimating model 7 is created using the teaching data of the latent variables. Also, based on the latent variable calculation information 6 determined when calculating the latent variable teacher data, elastic wave propagation characteristic data 5B that is data for prediction/estimation of auxiliary variables and data for prediction/estimation of explanatory variables. After calculating latent variable prediction/estimation data from strength influence factor/condition data 4B, concrete Based on the strength prediction/estimation model 7, a concrete strength prediction/estimation value 8 is calculated.
　従って、第７実施形態の非破壊測定システム１００Ｆによれば、打設時の要因等を表すコンクリートの強度の影響要因・条件に関するデータと弾性波法を用いた非破壊試験における弾性波伝搬特性に関するデータから、非破壊で推定対象（コンクリート）の強度を予測・推定することが可能となる。このため、より多くのデータを利用した予測・推定精度の向上及び相関による予測・推定精度の悪化の回避を図ることができ、第１～第５実施形態と同様の作用効果を奏することが可能となる。なお、補助変数として弾性波伝搬特性データ３Ｂ，５Ｂ以外のデータを利用する場合は、音響センサ１８に代わり補助変数に応じた種々のセンサ等を利用して、補助変数を得るように構成しても良い。 Therefore, according to the non-destructive measurement system 100F of the seventh embodiment, data related to factors and conditions affecting the strength of concrete representing factors at the time of placing and the like and elastic wave propagation characteristics in a non-destructive test using the elastic wave method From the data, it becomes possible to predict and estimate the strength of the estimation target (concrete) non-destructively. Therefore, it is possible to improve the prediction/estimation accuracy using more data and avoid deterioration of the prediction/estimation accuracy due to correlation, and it is possible to achieve the same effects as the first to fifth embodiments. becomes. When data other than elastic wave propagation characteristic data 3B and 5B are used as auxiliary variables, various sensors or the like corresponding to the auxiliary variables are used instead of the acoustic sensor 18 to obtain the auxiliary variables. Also good.
［第８実施形態］
　図１０は、本発明の第８実施形態に係る予測・推定システムが適用されたレーザ切断装置の切断品質の品質判定予測システムの基本的構成を示す説明図である。図１０に示すように、第８実施形態の品質判定予測システム１００Ｇは、第１～第５実施形態に係る予測・推定システム１００～１００Ｄの構成を適用可能な品質判定予測システムとして構成され得る。 [Eighth embodiment]
FIG. 10 is an explanatory diagram showing the basic configuration of a quality judgment/prediction system for cutting quality of a laser cutting apparatus to which the prediction/estimation system according to the eighth embodiment of the present invention is applied. As shown in FIG. 10, the quality judgment prediction system 100G of the eighth embodiment can be configured as a quality judgment prediction system to which the configurations of the prediction/estimation systems 100 to 100D according to the first to fifth embodiments can be applied.
　品質判定予測システム１００Ｇは、学習装置３６と、レーザ切断装置６０と、を備える。学習装置３６は、第１潜在変数算出部３７と、品質判定予測モデル学習部３８と、を備える。レーザ切断装置６０は、品質判定予測装置４６と、データ格納・転送装置６１と、を備える。品質判定予測装置４６は、第２潜在変数算出部４７と、品質判定予測部４８と、を備える。 The quality judgment prediction system 100G includes a learning device 36 and a laser cutting device 60. The learning device 36 includes a first latent variable calculation unit 37 and a quality judgment prediction model learning unit 38 . The laser cutting device 60 includes a quality judgment prediction device 46 and a data storage/transfer device 61 . The quality judgment prediction device 46 includes a second latent variable calculator 47 and a quality judgment prediction unit 48 .
　なお、品質判定予測システム１００Ｇにおいて、目的変数は、レーザ切断装置６０によるレーザ切断の品質判定結果（品質判定結果データ１Ｃ）である。また、説明変数は、レーザ切断の切断条件（切断条件データ２Ｃ）である。更に、補助変数は、レーザ切断に関する測定可能な物理量（発光強度データ３Ｃ）である。また、例えば説明変数の予測・推定用データとしては、レーザ切断装置６０に設定される切断条件データ４Ｃが挙げられる。また、補助変数の予測・推定用データとしては、レーザ切断装置６０で観測される物理量（発光強度データ５Ｃ）が挙げられる。 In the quality judgment prediction system 100G, the objective variable is the quality judgment result of laser cutting by the laser cutting device 60 (quality judgment result data 1C). Also, explanatory variables are cutting conditions for laser cutting (cutting condition data 2C). Further auxiliary variables are measurable physical quantities related to laser cutting (emission intensity data 3C). Further, for example, data for prediction/estimation of explanatory variables includes cutting condition data 4C set in the laser cutting device 60 . Further, the data for prediction/estimation of the auxiliary variables include physical quantities (luminescence intensity data 5C) observed by the laser cutting device 60 .
　ここで、レーザ切断装置６０の切断品質の品質判定５９とは、例えばレーザ切断装置６０によって切断された被加工物の切断面の物理的状態、すなわち例えば表面粗さ、ドロスの付着状況、ガウジング（切断不良）の発生状況等が、その被加工物を使用する上で実用に耐え得るものであるか否かを、装置により自動的に又は人的に判定することである。なお、ドロスとは、切断した材料の下面に溶融付着した金属や酸化物等が堆積したものを意味し、スラグと同義である。また、レーザ切断におけるガウジングとは、例えばレーザ切断の途中にレーザ光が貫通せずに溶融した金属が材料表面に噴出して外観上も汚くなった状態のことを意味する。 Here, the quality judgment 59 of the cutting quality of the laser cutting device 60 means, for example, the physical state of the cut surface of the workpiece cut by the laser cutting device 60, that is, for example, surface roughness, dross adhesion state, gouging ( It is to automatically or manually determine whether or not the state of occurrence of defective cutting) can withstand practical use in using the workpiece. Dross means a deposit of metals, oxides, etc. melted and adhered to the lower surface of the cut material, and is synonymous with slag. Further, gouging in laser cutting means, for example, a state in which the laser beam does not penetrate during laser cutting and melted metal is ejected onto the surface of the material, resulting in a dirty appearance.
　品質判定結果データ１Ｃは、上記のような品質判定５９の結果として、例えば、「最適」、「優良」、「良」、「可」、「不可」のような離散的なカテゴリー情報として与えられても良い。また、品質判定結果データ１Ｃは、０～１００までの数値的な情報で与えられても良い。品質判定結果データ１Ｃは、判定されたレーザ切断の品質を表す。切断条件データ２Ｃは、例えばレーザ切断を行う被加工物の材質及び／又は製品名、レーザ出力値、レーザ照射時間、切断速度等の各種情報を含んで構成され得る。切断条件データ２Ｃは、レーザ切断に際してレーザ切断装置６０に設定する切断条件を表す。また、切断条件データ２Ｃは、レーザ切断時の気温及び湿度等の環境条件の各種情報を含んでも良い。なお、切断条件データ２Ｃにおける各種情報は、これらに限定されるものではない。 The quality judgment result data 1C is provided as discrete category information such as "optimum", "excellent", "good", "acceptable", and "impossible" as a result of the quality judgment 59 as described above. can be Also, the quality determination result data 1C may be given as numerical information from 0 to 100. FIG. The quality determination result data 1C represents the determined quality of laser cutting. The cutting condition data 2C can include various information such as the material and/or product name of the workpiece to be laser-cut, laser output value, laser irradiation time, and cutting speed. The cutting condition data 2C represents cutting conditions set in the laser cutting device 60 for laser cutting. Also, the cutting condition data 2C may include various types of information on environmental conditions such as temperature and humidity during laser cutting. Various types of information in the cutting condition data 2C are not limited to these.
　発光強度データ３Ｃは、例えばレーザ切断に先立って行われるピアス加工時の発光強度を表す。ただし、補助変数の教師データは、発光強度に限られない。補助変数の教師データは、例えばピアス加工時の音或いは発光スペクトル等、レーザ切断に伴って測定され得る物理量データであれば良い。切断条件データ４Ｃは、例えばタッチパネル２１１を介してユーザにより行われた切断条件の操作入力に伴い設定された切断条件に関するデータである。切断条件データ４Ｃは、切断条件データ２Ｃと同様に構成される。発光強度データ５Ｃは、レーザ切断装置６０に備えられた光センサ１９で検出された実際のピアス加工時に検出された発光強度を表す。なお、光センサ１９は上述したセンサ２１２に含まれる。 The emission intensity data 3C represents, for example, the emission intensity during piercing performed prior to laser cutting. However, teaching data for auxiliary variables is not limited to luminescence intensity. The teaching data of the auxiliary variable may be physical quantity data that can be measured in association with laser cutting, such as sound or emission spectrum during piercing. The cutting condition data 4C is, for example, data relating to the cutting conditions set in accordance with the user's operation input of the cutting conditions via the touch panel 211 . The cutting condition data 4C is configured similarly to the cutting condition data 2C. The emission intensity data 5C represents the emission intensity detected by the optical sensor 19 provided in the laser cutting device 60 during actual piercing. Note that the optical sensor 19 is included in the sensor 212 described above.
［品質判定予測システムの動作］
　品質判定結果データ１Ｃ、切断条件データ２Ｃ及び発光強度データ３Ｃのうち、少なくとも切断条件データ２Ｃ及び発光強度データ３Ｃは、それぞれ説明変数及び補助変数の教師データとして学習装置３６に入力される。品質判定結果データ１Ｃは、目的変数の教師データとして学習装置３６に入力可能である。学習装置３６は、これら入力されたデータのうち、少なくとも切断条件データ２Ｃ及び発光強度データ３Ｃを含むデータに基づき第１潜在変数算出部３７において潜在変数の教師データを算出する。また、学習装置３６は、品質判定予測モデル学習部３８において品質判定結果データ１Ｃと、切断条件データ２Ｃと、第１潜在変数算出部３７により算出された潜在変数の教師データと、を入力し、例えば機械学習を行って、レーザ切断の切断品質の品質判定予測モデル７Ｂを作成する。学習装置３６は、潜在変数の教師データの算出に際して決定された潜在変数算出情報６及び品質判定予測モデル７Ｂを、レーザ切断装置６０に出力する。 [Operation of quality judgment prediction system]
Of the quality determination result data 1C, the cutting condition data 2C, and the luminous intensity data 3C, at least the cutting condition data 2C and the luminous intensity data 3C are input to the learning device 36 as teacher data for explanatory variables and auxiliary variables, respectively. The quality judgment result data 1C can be input to the learning device 36 as teacher data for objective variables. The learning device 36 calculates teacher data of latent variables in the first latent variable calculator 37 based on the data including at least the cutting condition data 2C and the light emission intensity data 3C among the input data. In addition, the learning device 36 inputs the quality determination result data 1C, the cutting condition data 2C, and the teacher data of the latent variables calculated by the first latent variable calculation unit 37 in the quality determination prediction model learning unit 38, For example, machine learning is performed to create a quality determination predictive model 7B for cutting quality of laser cutting. The learning device 36 outputs to the laser cutting device 60 the latent variable calculation information 6 and the quality judgment prediction model 7B determined when calculating the teacher data of the latent variables.
　レーザ切断装置６０には、学習装置３６から出力された潜在変数算出情報６及び品質判定予測モデル７Ｂが備えられる。なお、これら潜在変数算出情報６及び品質判定予測モデル７Ｂは、レーザ切断装置６０が有する記憶媒体又はレーザ切断装置６０に着脱自在な可搬性の記憶媒体に記憶されたり、インターネット等の情報伝達媒体から取得されたりして、レーザ切断装置６０に備えられる。 The laser cutting device 60 is equipped with the latent variable calculation information 6 and the quality judgment prediction model 7B output from the learning device 36. The latent variable calculation information 6 and the quality judgment prediction model 7B are stored in a storage medium of the laser cutting device 60 or a portable storage medium detachably attached to the laser cutting device 60, or can be downloaded from an information transmission medium such as the Internet. It is acquired and provided in the laser cutting device 60 .
　また、レーザ切断装置６０のデータ格納・転送装置６１には、光センサ１９により検出されたピアス加工時の発光強度データ５Ｃ及びタッチパネル２１１により操作入力された切断条件データ４Ｃが入力され、一旦格納されている。そして、レーザ切断装置６０の品質判定予測装置４６には、データ格納・転送装置６１に格納された切断条件データ４Ｃ及び発光強度データ５Ｃと共に、潜在変数算出情報６及び品質判定予測モデル７Ｂが入力される。 Further, the data storage/transfer device 61 of the laser cutting device 60 is supplied with the emission intensity data 5C during the piercing process detected by the optical sensor 19 and the cutting condition data 4C operated by the touch panel 211 and temporarily stored. ing. The latent variable calculation information 6 and the quality judgment prediction model 7B are input to the quality judgment prediction device 46 of the laser cutting device 60 together with the cutting condition data 4C and the emission intensity data 5C stored in the data storage/transfer device 61. be.
　品質判定予測装置４６は、これら入力されたデータのうち、少なくとも切断条件データ４Ｃ及び発光強度データ５Ｃから、第２潜在変数算出部４７において潜在変数算出情報６に基づき潜在変数の予測・推定用データを算出する。また、品質判定予測装置４６は、品質判定予測部４８において第２潜在変数算出部４７により算出された潜在変数の予測・推定用データと、切断条件データ４Ｃと、発光強度データ５Ｃとから、品質判定予測モデル７Ｂに基づいて、切断品質の品質判定予測を行い、品質判定予測値８Ｂを算出する。算出された品質判定予測値８Ｂは、表示、印刷等適宜利用可能な形態でレーザ切断装置６０から出力され得る。なお、レーザ切断装置６０は、実際の切断結果５８に関する各種情報を出力し得るので、上述した品質判定５９は、この切断結果５８に関する各種情報に基づき行われ、品質判定結果データ１Ｃが作成される。 The quality judgment predicting device 46 uses at least the cutting condition data 4C and the luminescence intensity data 5C among the input data to generate latent variable prediction/estimation data based on the latent variable calculation information 6 in the second latent variable calculator 47. Calculate In addition, the quality judgment prediction device 46 predicts the quality from the latent variable prediction/estimation data calculated by the second latent variable calculation unit 47 in the quality judgment prediction unit 48, the cutting condition data 4C, and the light emission intensity data 5C. Based on the judgment prediction model 7B, quality judgment prediction of cutting quality is performed to calculate a quality judgment prediction value 8B. The calculated quality determination predicted value 8B can be output from the laser cutting device 60 in a form that can be used as appropriate, such as display or printing. Since the laser cutting device 60 can output various information about the actual cutting result 58, the quality judgment 59 described above is performed based on the various information about this cutting result 58, and the quality judgment result data 1C is created. .
　また、学習装置３６は、潜在変数の教師データの算出及び品質判定予測モデル７Ｂの作成に際し、データ格納・転送装置６１に格納された切断条件データ４Ｃ及び発光強度データ５Ｃを、説明変数及び補助変数の教師データとして切断条件データ２Ｃ及び発光強度データ３Ｃに追加して用いるようにしても良い。このようにすれば、より多くのデータを利用して予測・推定の精度向上に寄与することができる。さらに、学習装置３６は、品質判定結果データ１Ｃを目的変数の教師データとして追加で利用することもできるので、この場合は、更に予測・推定の精度向上を図ることが可能となる。 Further, the learning device 36 converts the cutting condition data 4C and the light emission intensity data 5C stored in the data storage/transfer device 61 into explanatory variables and auxiliary variables when calculating teacher data of latent variables and creating the quality judgment prediction model 7B. may be used in addition to the cutting condition data 2C and the emission intensity data 3C as teaching data. In this way, more data can be used to contribute to improving the accuracy of prediction/estimation. Furthermore, since the learning device 36 can additionally use the quality determination result data 1C as teacher data for the objective variable, in this case, it is possible to further improve the accuracy of prediction/estimation.
　第８実施形態の品質判定予測システム１００Ｇでは、品質判定結果データ１Ｃの補助変数の教師データである発光強度データ３Ｃ（５Ｃ）及び説明変数の教師データである切断条件データ２Ｃ（４Ｃ）に基づき潜在変数の教師データを算出した上で、潜在変数の教師データを用いた切断品質の品質判定予測モデル７Ｂが作成される。また、潜在変数の教師データの算出の際に決定された潜在変数算出情報６に基づき、補助変数の予測・推定用データである発光強度データ５Ｃ及び説明変数の予測・推定用データである切断条件データ４Ｃから潜在変数の予測・推定用データを算出した上で、切断条件データ４Ｃ、発光強度データ５Ｃ、及び潜在変数の予測・推定用データから品質判定予測モデル７Ｂに基づいて、切断品質の品質判定予測値８Ｂが算出される。 In the quality judgment prediction system 100G of the eighth embodiment, latent light emission intensity data 3C (5C), which is teacher data for auxiliary variables of quality judgment result data 1C, and cutting condition data 2C (4C), which is teacher data for explanatory variables. After calculating the teacher data of the variables, the quality judgment prediction model 7B of the cutting quality using the teacher data of the latent variables is created. Further, based on the latent variable calculation information 6 determined when calculating the supervised data of the latent variables, the luminous intensity data 5C, which is the data for prediction/estimation of the auxiliary variables, and the cutting condition, which is the data for prediction/estimation of the explanatory variables After calculating latent variable prediction/estimation data from data 4C, cutting condition data 4C, luminous intensity data 5C, and latent variable prediction/estimation data are used to determine the quality of cutting quality based on quality judgment prediction model 7B. A judgment predicted value 8B is calculated.
　従って、第８実施形態の品質判定予測システム１００Ｇによれば、レーザ切断の切断条件に関するデータと切断時の発光強度に関するデータから、レーザ切断前に品質予測対象（被加工物の被切断部）の切断品質を予測することが可能となる。一般的にレーザ切断においては、同一の切断条件でレーザ切断を施した場合であっても、被加工物の材質、切断環境のばらつき等の要因によって切断品質は変化する。従って、実際にレーザ切断を行わなければ切断品質を判定することはできないという問題がある。しかし、第８実施形態の品質判定予測システム１００Ｇは、より多くのデータを利用した品質判定予測精度の向上及び相関による品質判定予測精度の悪化の回避を図ることができる構成を採用する。このため、品質判定予測システム１００Ｇは、レーザ切断前に切断品質の予測を行ってこの問題を解決することができると共に、第１～第５実施形態と同様の作用効果を奏することが可能となる。 Therefore, according to the quality judgment prediction system 100G of the eighth embodiment, the quality prediction target (the cut portion of the workpiece) is determined before laser cutting from the data regarding the cutting conditions for laser cutting and the data regarding the emission intensity during cutting. Cut quality can be predicted. Generally, in laser cutting, even when laser cutting is performed under the same cutting conditions, the cutting quality varies depending on factors such as variations in the material of the workpiece and the cutting environment. Therefore, there is a problem that cutting quality cannot be judged unless laser cutting is actually performed. However, the quality determination prediction system 100G of the eighth embodiment employs a configuration capable of improving the quality determination prediction accuracy using more data and avoiding deterioration of the quality determination prediction accuracy due to correlation. Therefore, the quality judgment prediction system 100G can solve this problem by predicting cutting quality before laser cutting, and can achieve the same effects as those of the first to fifth embodiments. .
　なお、第８実施形態の品質判定予測システム１００Ｇにおいては、学習装置３６がレーザ切断装置６０に組み込まれた態様であっても良く、品質判定予測装置４６がレーザ切断装置６０とは別体の装置（例えば、エッジサーバ等）として独立したものであっても良い。学習装置３６及び品質判定予測装置４６における機械学習及び品質判定予測に際しては、アルゴリズムとしては、上述したような回帰分析（ＲＡ）、主成分分析（ＰＣＡ）、特異値分解（ＳＶＤ）、線形判別分析（ＬＤＡ）、独立成分分析（ＩＣＡ）、ガウス過程潜在変数モデル（ＧＰＬＶＭ）の他に、ロジスティクス回帰（Ｌｏｇｉｓｔｉｃ　Ｒｅｇｒｅｓｓｉｏｎ：ＬＲ）、サポートベクターマシン（Ｓｕｐｐｏｒｔ　Ｖｅｃｔｏｒ　Ｍａｃｈｉｎｅ：ＳＶＭ）、判別分析（Ｄｉｓｃｒｉｍｉｎａｎｔ　Ａｎａｌｙｓｉｓ：ＤＡ）、ランダムフォレスト（Ｒａｎｄｏｍ　Ｆｏｒｅｓｔ：ＲＦ）、ランキングＳＶＭ（Ｒａｎｋｉｎｇ　Ｓｕｐｐｏｒｔ　Ｖｅｃｔｏｒ　Ｍａｃｈｉｎｅ：ＲＳＶＭ）、勾配ブースティング（Ｇｒａｄｉｅｎｔ　Ｂｏｏｓｔｉｎｇ：ＧＢ）、ナイーブベイズ（Ｎａｉｖｅ　Ｂａｙｅｓ：ＮＢ）、Ｋ近接法（Ｋ－Ｎｅａｒｅｓｔ　Ｎｅｉｇｈｂｏｒ　Ａｌｇｏｒｉｔｈｍ：Ｋ－ＮＮ）等の各種のアルゴリズムを利用することができる。 In the quality judgment prediction system 100G of the eighth embodiment, the learning device 36 may be incorporated in the laser cutting device 60, and the quality judgment prediction device 46 may be a separate device from the laser cutting device 60. (For example, an edge server or the like) may be independent. For machine learning and quality judgment prediction in the learning device 36 and the quality judgment prediction device 46, the algorithms include regression analysis (RA), principal component analysis (PCA), singular value decomposition (SVD), and linear discriminant analysis as described above. (LDA), Independent Component Analysis (ICA), Gaussian Process Latent Variable Model (GPLVM), Logistic Regression (LR), Support Vector Machine (SVM), Discriminant Analysis (DA) ), Random Forest (RF), Ranking Support Vector Machine (RSVM), Gradient Boosting (GB), Naive Bayes (NB), K-Nearest Neighbor Algorithm : K-NN) can be used.
［他の実施形態］
　上述した第１実施形態において、学習装置１０及び予測・推定装置２０における予測・推定モデル７の学習方法及び予測・推定値８の予測・推定方法は、これらの方法を実行するプログラム及び／又はこのプログラムを記憶したコンピュータに読み取り可能な記憶媒体として実現され得る。また、学習方法及び予測・推定方法は、これらの方法を実行する電子回路、その他物理媒体を利用した論理回路等、各種のハードウェア資源を用いて実現されても良く、これらプログラム等、電子回路及び／又は論理回路等のハードウェア資源を備える装置として実現されていても良い。また、学習方法及び予測・推定方法は、１つのシステムとして実行するプログラム等を記憶した記憶媒体を備える電子計算機及び／又は電子回路、その他論理回路等の各種のハードウェア資源を用いて実現されていても良い。また、学習方法及び予測・推定方法は、それぞれが別の記憶媒体を備える１つ以上の電子計算機及び／又は電子回路、その他論理回路等の各種のハードウェア資源を用いて実現されていても良い。また、１つのシステムとして実行される場合は、例えば学習方法がクラウド側で実現され、予測・推定方法がエッジ側で実現されても良く、その逆であっても良い。 [Other embodiments]
In the above-described first embodiment, the learning method of the prediction/estimation model 7 and the prediction/estimation method of the prediction/estimation value 8 in the learning device 10 and the prediction/estimation device 20 may be a program for executing these methods and/or this It can be implemented as a computer-readable storage medium storing a program. In addition, the learning method and the prediction/estimation method may be realized using various hardware resources such as an electronic circuit that executes these methods and a logic circuit that uses other physical media. and/or may be implemented as a device having hardware resources such as logic circuits. In addition, the learning method and the prediction/estimation method are realized using various hardware resources such as a computer and/or electronic circuit equipped with a storage medium storing a program etc. to be executed as one system, and other logic circuits. can be In addition, the learning method and the prediction/estimation method may be realized using various hardware resources such as one or more computers and/or electronic circuits each having a separate storage medium, and other logic circuits. . In the case of execution as one system, for example, the learning method may be implemented on the cloud side and the prediction/estimation method may be implemented on the edge side, or vice versa.
［実施例］
　図１１は、図５に示した第４実施形態に係る予測・推定システムを実際のレーザ溶接に適用した実施例の補助変数を説明するための溶接温度と経過時間の関係を示すグラフである。図１２は、比較例及び実施例における推定値と測定値の関係と、推定値の推定値に対する誤差の度数分布を示すグラフである。 [Example]
FIG. 11 is a graph showing the relationship between welding temperature and elapsed time for explaining auxiliary variables in an example in which the prediction/estimation system according to the fourth embodiment shown in FIG. 5 is applied to actual laser welding. FIG. 12 is a graph showing the relationship between estimated values and measured values and the frequency distribution of errors of estimated values with respect to estimated values in Comparative Example and Example.
　実施例のレーザ溶接においては、説明変数を溶接条件（レーザ溶接に用いたレーザの出力強度及び照射時間）とし、目的変数を溶接強度とした。学習装置１０においては重回帰分析を用いて予測・推定モデル７を作成することとした。比較例においては上述したような潜在変数を用いていない。 In the laser welding of the example, the welding conditions (output intensity and irradiation time of the laser used for laser welding) were used as explanatory variables, and the welding strength was used as the objective variable. In the learning device 10, the prediction/estimation model 7 is created using multiple regression analysis. In the comparative example, no latent variable as described above was used.
　図１１に示すように、縦軸にレーザ溶接の溶接点の溶接温度を、横軸にレーザ溶接の経過時間を示したグラフによれば、溶接点の温度は、経過時間Ｔ１のレーザ照射開始と同時に急激に上昇を始める。そして、経過時間Ｔ１の後のある時点（経過時間Ｔ２）において温度上昇が鈍化し、そのまま経過時間Ｔ２の後のレーザ照射終了（経過時間Ｔ３）と同時に急激に下降し、経過時間Ｔ３の後のある時点（経過時間Ｔ４）においてレーザ照射開始前の温度に戻る。レーザ溶接の溶接温度は、このような特性を持って推移する。そこで、溶接強度を推定するために用いる補助変数として、温度上昇が鈍化した時点（経過時間Ｔ２）での温度ＴＰ１及びレーザ照射終了時（経過時間Ｔ３）での温度ＴＰ２を用いた。 As shown in FIG. 11, according to a graph in which the vertical axis represents the welding temperature at the welding point of the laser welding and the horizontal axis represents the elapsed time of the laser welding, the temperature at the welding point varies from the start of the laser irradiation at the elapsed time T1. At the same time, it begins to rise sharply. Then, at a certain point after the elapsed time T1 (elapsed time T2), the temperature rise slows down, and at the same time the laser irradiation ends after the elapsed time T2 (elapsed time T3), the temperature drops sharply, and after the elapsed time T3 At a certain point (elapsed time T4), the temperature returns to the temperature before the start of laser irradiation. The welding temperature of laser welding changes with such characteristics. Therefore, as auxiliary variables for estimating the welding strength, the temperature TP1 at the time when the temperature rise slows down (elapsed time T2) and the temperature TP2 at the end of laser irradiation (elapsed time T3) are used.
　比較例による溶接強度の推定値と実際の溶接強度の測定値は、図１２（ａ）に示すようになった。一方、実施例による溶接強度の推定値と実際の溶接強度の測定値は、図１２（ｂ）に示すようになった。図１２（ａ）及び（ｂ）においては、横軸は様々な条件に溶接条件の値を変えたときの溶接強度の測定値を表し、縦軸はその溶接条件に対応する溶接強度の推定値を表している。なお、図１２（ａ）及び（ｂ）では、測定値及び推定値共に最大の溶接強度が１となるように規格化してプロットがされている。 　The estimated value of the welding strength according to the comparative example and the measured value of the actual welding strength are shown in Fig. 12(a). On the other hand, the estimated value of the welding strength according to the example and the measured value of the actual welding strength are shown in FIG. 12(b). In FIGS. 12(a) and (b), the horizontal axis represents the measured values of the welding strength when the values of the welding conditions are changed to various conditions, and the vertical axis represents the estimated values of the welding strength corresponding to the welding conditions. represents. In FIGS. 12A and 12B, the plots are normalized so that the maximum welding strength is 1 for both the measured values and the estimated values.
　また、比較例による推定値の測定値に対する誤差の度数分布は、図１２（ｃ）に示すようになった。一方、実施例による推定値の測定値に対する誤差の度数分布は、図１２（ｄ）に示すようになった。図１２（ｃ）及び（ｄ）においては、横軸に誤差の範囲を表し、縦軸にその誤差に対応する度数を表している。 Also, the frequency distribution of the errors of the estimated values for the measured values according to the comparative example is shown in FIG. 12(c). On the other hand, the error frequency distribution of the estimated values with respect to the measured values according to the example is shown in FIG. 12(d). In FIGS. 12C and 12D, the horizontal axis represents the error range, and the vertical axis represents the frequency corresponding to the error.
　そして、比較例による誤差と実施例による誤差を、平均絶対誤差（ＭＡＥ：Ｍｅａｎ　Ａｂｓｏｌｕｔｅ　Ｅｒｒｏｒ）と平均平方二乗誤差（ＲＭＳＥ：Ｒｏｏｔ　Ｍｅａｎ　Ｓｑｕａｒｅｄ　Ｅｒｒｏｒ）で評価した結果は、以下の表１に示すようになった。 Then, the error by the comparative example and the error by the example were evaluated by mean absolute error (MAE: Mean Absolute Error) and mean squared error (RMSE: Root Mean Squared Error), as shown in Table 1 below. became.
Figure JPOXMLDOC01-appb-T000001
  
Figure JPOXMLDOC01-appb-T000001
  
　実施例による誤差は、比較例による誤差と比べて、ＭＡＥ及びＲＭＳＥのいずれにおいても小さな値を取った。また、図１２（ｃ）及び（ｄ）からも明らかなように、実施例の方が比較例に比べて、推定値が測定値に近づき、誤差の分布の裾（範囲）が狭くなっていることが分かる。従って、実施例の予測・推定システムでは、補助変数も含めたより多くのデータを利用しても予測・推定の精度が改善されていることが証明された。 The errors in the examples took smaller values in both MAE and RMSE compared to the errors in the comparative examples. Also, as is clear from FIGS. 12(c) and (d), the estimated values are closer to the measured values in the example than in the comparative example, and the tail (range) of the error distribution is narrower. I understand. Therefore, in the prediction/estimation system of the example, it was proved that the accuracy of prediction/estimation was improved even when more data including auxiliary variables were used.
　以上、本発明のいくつかの実施の形態を説明したが、これらの実施の形態は、例として提示したものであり、発明の範囲を限定することは意図していない。これらの新規な実施の形態は、その他の様々な形態で実施されることが可能であり、発明の要旨を逸脱しない範囲で、種々の省略、置き換え、変更を行うことができる。これら実施の形態やその変形は、発明の範囲や要旨に含まれると共に、特許請求の範囲に記載された発明とその均等の範囲に含まれる。 Although several embodiments of the present invention have been described above, these embodiments are presented as examples and are not intended to limit the scope of the invention. These novel embodiments can be embodied in various other forms, and various omissions, replacements, and modifications can be made without departing from the scope of the invention. These embodiments and their modifications are included in the scope and gist of the invention, and are included in the scope of the invention described in the claims and equivalents thereof.

Claims (12)

  1. 　目的変数の教師データと、前記目的変数に作用する説明変数の教師データと、前記目的変数以外の変数で、前記説明変数と相関を有すると共に、前記説明変数が与えられたときに観測される補助変数の教師データと、を入力し、前記目的変数の予測・推定モデルを作成する学習装置と、
    　前記目的変数を予測・推定するための前記説明変数の予測・推定用データと、前記目的変数を予測・推定するための前記補助変数の予測・推定用データと、を入力し、前記学習装置で作成された前記予測・推定モデルに基づいて、前記目的変数の予測・推定値を算出する予測・推定装置と、
    　を備え、
    　前記学習装置は、
    　少なくとも前記補助変数の教師データから、潜在変数の教師データを算出し、潜在変数算出情報を出力する第１潜在変数算出部と、
    　前記目的変数の教師データと、前記説明変数の教師データと、前記第１潜在変数算出部により算出された前記潜在変数の教師データと、を入力し、前記目的変数の予測・推定モデルを作成する予測・推定モデル学習部と、
    　を含み、
    　前記予測・推定装置は、
    　少なくとも前記補助変数の予測・推定用データから、前記潜在変数算出情報に基づいて、潜在変数の予測・推定用データを算出する第２潜在変数算出部と、
    　前記第２潜在変数算出部により算出された前記潜在変数の予測・推定用データと、前記説明変数の予測・推定用データとから、前記予測・推定モデルに基づいて、前記目的変数の予測・推定値を算出する予測・推定部と、
    　を含む予測・推定システム。     teacher data of an objective variable, teacher data of an explanatory variable acting on the objective variable, and auxiliary variables other than the objective variable that are correlated with the explanatory variable and observed when the explanatory variable is given. a learning device that inputs teacher data of variables and creates a prediction/estimation model of the objective variable;
    input data for prediction/estimation of the explanatory variable for predicting/estimating the objective variable and prediction/estimation data for the auxiliary variable for predicting/estimating the objective variable; a prediction/estimation device that calculates a prediction/estimation value of the objective variable based on the created prediction/estimation model;
    with
    The learning device
    a first latent variable calculation unit that calculates latent variable teacher data from at least the auxiliary variable teacher data and outputs latent variable calculation information;
    The teacher data of the objective variable, the teacher data of the explanatory variable, and the teacher data of the latent variable calculated by the first latent variable calculation unit are input to create a prediction/estimation model of the objective variable. a prediction/estimation model learning unit;
    including
    The prediction/estimation device is
    a second latent variable calculation unit that calculates prediction/estimation data of a latent variable based on the latent variable calculation information from at least the prediction/estimation data of the auxiliary variable;
    Prediction/estimation of the objective variable based on the prediction/estimation model from the prediction/estimation data of the latent variables calculated by the second latent variable calculation unit and the prediction/estimation data of the explanatory variables a prediction/estimation unit that calculates a value;
    Forecasting and estimating systems, including
  2. 　前記学習装置の前記第１潜在変数算出部は、前記説明変数の教師データと、前記補助変数の教師データと、に基づき前記潜在変数の教師データを算出し、
    　前記予測・推定装置の前記第２潜在変数算出部は、前記説明変数の予測・推定用データと、前記補助変数の予測・推定用データと、に基づき前記潜在変数の予測・推定用データを算出する
    　請求項１記載の予測・推定システム。     The first latent variable calculation unit of the learning device calculates teacher data of the latent variables based on teacher data of the explanatory variables and teacher data of the auxiliary variables,
    The second latent variable calculation unit of the prediction/estimation device calculates prediction/estimation data of the latent variables based on the prediction/estimation data of the explanatory variables and the prediction/estimation data of the auxiliary variables. The prediction/estimation system according to claim 1.
  3. 　前記予測・推定装置の前記第２潜在変数算出部は、更に、前記説明変数の教師データと、前記補助変数の教師データと、前記潜在変数の教師データと、に基づき前記潜在変数の予測・推定用データを算出する
    　請求項２記載の予測・推定システム。     The second latent variable calculation unit of the prediction/estimation device further predicts/estimates the latent variables based on the teacher data of the explanatory variables, the teacher data of the auxiliary variables, and the teacher data of the latent variables. The prediction/estimation system according to claim 2, wherein the data for the calculation is calculated.
  4. 　前記潜在変数算出情報は、アルゴリズム、式及び／又はパラメータを含み、
    　前記アルゴリズムは、次元削減又は次元圧縮の処理を含む
    　請求項１～３のいずれか１項記載の予測・推定システム。     The latent variable calculation information includes algorithms, formulas and/or parameters,
    The prediction/estimation system according to any one of claims 1 to 3, wherein the algorithm includes dimensionality reduction or dimensionality compression processing.
  5. 　前記アルゴリズムは、回帰分析（ＲＡ）、主成分分析（ＰＣＡ）、特異値分解（ＳＶＤ）、線形判別分析（ＬＤＡ）、独立成分分析（ＩＣＡ）、及びガウス過程潜在変数モデル（ＧＰＬＶＭ）の少なくとも一つを含む
    　請求項４記載の予測・推定システム。     The algorithm comprises at least one of regression analysis (RA), principal component analysis (PCA), singular value decomposition (SVD), linear discriminant analysis (LDA), independent component analysis (ICA), and Gaussian process latent variable model (GPLVM). The prediction/estimation system of claim 4, comprising:
  6. 　前記学習装置の前記第１潜在変数算出部は、前記補助変数の教師データを前記説明変数の教師データで回帰分析し回帰モデルを作成する第１回帰分析部と、前記第１回帰分析部による回帰分析の回帰誤差を主成分分析し前記潜在変数の教師データを算出する第１主成分分析部と、を含み、
    　前記潜在変数算出情報は、前記回帰モデルのパラメータ及び回帰式と、前記主成分分析の主成分ベクトル及び固有値と、を含み、
    　前記予測・推定装置の前記第２潜在変数算出部は、前記潜在変数算出情報に基づき前記補助変数の予測・推定用データを前記説明変数の予測・推定用データで回帰分析し回帰モデルを作成する第２回帰分析部と、前記潜在変数算出情報に基づき前記第２回帰分析部による回帰誤差を主成分分析して前記潜在変数の予測・推定用データを算出する第２主成分分析部と、を含む
    　請求項２記載の予測・推定システム。     The first latent variable calculation unit of the learning device includes a first regression analysis unit that performs regression analysis on the teacher data of the auxiliary variables with the teacher data of the explanatory variables to create a regression model, and regression by the first regression analysis unit. a first principal component analysis unit that performs principal component analysis on the regression error of the analysis to calculate teacher data for the latent variable;
    The latent variable calculation information includes parameters and regression equations of the regression model and principal component vectors and eigenvalues of the principal component analysis,
    The second latent variable calculation unit of the prediction/estimation device performs regression analysis on the prediction/estimation data of the auxiliary variables with the prediction/estimation data of the explanatory variables to create a regression model based on the latent variable calculation information. a second regression analysis unit, and a second principal component analysis unit for calculating prediction/estimation data of the latent variables by performing principal component analysis on the regression error by the second regression analysis unit based on the latent variable calculation information. The prediction/estimation system according to claim 2.
  7. 　前記学習装置の前記第１潜在変数算出部は、ガウス過程潜在変数モデル（ＧＰＬＶＭ）により前記潜在変数の教師データを算出し、
    　前記潜在変数算出情報は、前記ガウス過程潜在変数モデル（ＧＰＬＶＭ）のハイパーパラメータを含み、
    　前記学習装置の前記予測・推定モデル学習部は、ガウス過程回帰（ＧＰＲ）により前記目的変数の予測・推定モデルを作成し、
    　前記予測・推定装置の前記第２潜在変数算出部は、前記ガウス過程潜在変数モデル（ＧＰＬＶＭ）により前記潜在変数の予測・推定用データを算出し、
    　前記予測・推定装置の前記予測・推定部は、前記ガウス過程回帰（ＧＰＲ）により前記目的変数の予測・推定値を算出する
    　請求項２記載の予測・推定システム。     The first latent variable calculation unit of the learning device calculates teacher data of the latent variables by a Gaussian process latent variable model (GPLVM),
    The latent variable calculation information includes hyperparameters of the Gaussian process latent variable model (GPLVM),
    The prediction/estimation model learning unit of the learning device creates a prediction/estimation model of the objective variable by Gaussian process regression (GPR),
    The second latent variable calculation unit of the prediction/estimation device calculates data for prediction/estimation of the latent variable by the Gaussian process latent variable model (GPLVM),
    The prediction/estimation system according to claim 2, wherein the prediction/estimation unit of the prediction/estimation device calculates the prediction/estimation value of the objective variable by the Gaussian process regression (GPR).
  8. 　前記目的変数は、レーザ溶接機によるレーザ溶接の溶接強度又は溶接品質であり、
    　前記説明変数は、前記レーザ溶接の溶接条件であり、
    　前記補助変数は、前記レーザ溶接に関してレーザ溶接時又は溶接後に観測可能な物理量である
    　請求項１～７のいずれか１項記載の予測・推定システム。     The objective variable is the welding strength or welding quality of laser welding by a laser welder,
    The explanatory variable is a welding condition of the laser welding,
    The prediction/estimation system according to any one of claims 1 to 7, wherein the auxiliary variable is a physical quantity observable during or after laser welding with respect to the laser welding.
  9. 　前記目的変数は、コンクリートの強度であり、
    　前記説明変数は、測定可能な前記コンクリートの強度の影響要因・条件であり、
    　前記補助変数は、前記強度の測定時の弾性波伝搬特性である
    　請求項１～７のいずれか１項記載の予測・推定システム。     The objective variable is the strength of concrete,
    The explanatory variable is a measurable factor/condition affecting the strength of the concrete,
    The prediction/estimation system according to any one of claims 1 to 7, wherein the auxiliary variable is elastic wave propagation characteristics when measuring the intensity.
  10. 　前記目的変数は、レーザ切断装置によるレーザ切断の品質判定結果であり、
    　前記説明変数は、前記レーザ切断の切断条件であり、
    　前記補助変数は、前記レーザ切断に関する測定可能な物理量である、
    　請求項１～７のいずれか１項記載の予測・推定システム。     The objective variable is a quality judgment result of laser cutting by a laser cutting device,
    The explanatory variable is a cutting condition for the laser cutting,
    the auxiliary variable is a measurable physical quantity related to the laser cutting;
    The prediction/estimation system according to any one of claims 1 to 7.
  11. 　目的変数の教師データと、前記目的変数に作用する説明変数の教師データと、前記目的変数以外の変数で、前記説明変数と相関を有すると共に、前記説明変数が与えられたときに観測される補助変数の教師データと、を入力し、
    　少なくとも前記補助変数の教師データから、潜在変数の教師データを算出し、潜在変数算出情報を出力する潜在変数算出部と、
    　前記目的変数の教師データと、前記説明変数の教師データと、前記潜在変数算出部により算出された前記潜在変数の教師データと、を入力し、前記目的変数の予測・推定モデルを作成する予測・推定モデル学習部と、
    　を備えた学習装置。     teacher data of an objective variable, teacher data of an explanatory variable acting on the objective variable, and auxiliary variables other than the objective variable that are correlated with the explanatory variable and observed when the explanatory variable is given. Enter the variable teacher data and
    a latent variable calculation unit that calculates latent variable teacher data from at least the auxiliary variable teacher data and outputs latent variable calculation information;
    A prediction/estimation model for creating a prediction/estimation model for the objective variable by inputting the teacher data for the objective variable, the teacher data for the explanatory variable, and the teacher data for the latent variable calculated by the latent variable calculator. an estimation model learning unit;
    A learning device with
  12. 　目的変数の教師データと、前記目的変数に作用する説明変数の教師データと、前記目的変数以外の変数で、前記説明変数と相関を有すると共に、前記説明変数が与えられたときに観測される補助変数の教師データから、潜在変数算出情報に基づき算出された、潜在変数の教師データと、を用いて予め学習された前記目的変数の予測・推定モデルに基づいて、前記目的変数の予測・推定値を算出する予測・推定装置であって、
    　少なくとも前記補助変数の予測・推定用データから、前記潜在変数算出情報に基づいて、前記潜在変数の予測・推定用データを算出する潜在変数算出部と、
    　前記潜在変数算出部により算出された前記潜在変数の予測・推定用データと、前記説明変数の予測・推定用データとから、前記予測・推定モデルに基づいて、前記目的変数の予測・推定値を算出する予測・推定部と、
    　を備えた予測・推定装置。     teacher data of an objective variable, teacher data of an explanatory variable acting on the objective variable, and auxiliary variables other than the objective variable that are correlated with the explanatory variable and observed when the explanatory variable is given. Predicted/estimated value of the objective variable based on the predictive/estimated model of the objective variable learned in advance using the latent variable tutored data calculated based on the latent variable calculation information from the variable tutor data A prediction/estimation device that calculates
    a latent variable calculation unit that calculates prediction/estimation data of the latent variable based on the latent variable calculation information from at least the prediction/estimation data of the auxiliary variable;
    Based on the prediction/estimation model, the prediction/estimation value of the objective variable is calculated from the prediction/estimation data of the latent variable calculated by the latent variable calculation unit and the prediction/estimation data of the explanatory variable. a prediction/estimation unit that calculates;
    Prediction/estimation device with
PCT/JP2022/038127 2021-10-19 2022-10-12 Prediction/estimation system, learning device, and prediction/estimation device WO2023068148A1 (en)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
JP2021171200A JP2023061289A (en) 2021-10-19 2021-10-19 Prediction and estimation system, learning device, and prediction and estimation device
JP2021-171200 2021-10-19

Publications (1)

Publication Number Publication Date
WO2023068148A1 true WO2023068148A1 (en) 2023-04-27

Family

ID=86059138

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/JP2022/038127 WO2023068148A1 (en) 2021-10-19 2022-10-12 Prediction/estimation system, learning device, and prediction/estimation device

Country Status (2)

Country Link
JP (1) JP2023061289A (en)
WO (1) WO2023068148A1 (en)

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2018151771A (en) * 2017-03-10 2018-09-27 荏原環境プラント株式会社 Process-control supporting device and method
JP2019198876A (en) * 2018-05-15 2019-11-21 ファナック株式会社 Machining condition adjusting device and machine learning device
JP6818970B1 (en) * 2020-05-20 2021-01-27 三菱電機株式会社 Data creation device, machine learning system and machining state estimation system
CN113033923A (en) * 2021-04-30 2021-06-25 中国建筑材料科学研究总院有限公司 Method, device and system for predicting, evaluating and optimizing performance of cement clinker

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2018151771A (en) * 2017-03-10 2018-09-27 荏原環境プラント株式会社 Process-control supporting device and method
JP2019198876A (en) * 2018-05-15 2019-11-21 ファナック株式会社 Machining condition adjusting device and machine learning device
JP6818970B1 (en) * 2020-05-20 2021-01-27 三菱電機株式会社 Data creation device, machine learning system and machining state estimation system
CN113033923A (en) * 2021-04-30 2021-06-25 中国建筑材料科学研究总院有限公司 Method, device and system for predicting, evaluating and optimizing performance of cement clinker

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
WU DI; HUANG YIMING; ZHANG PEILEI; YU ZHISHUI; CHEN HUABIN; CHEN SHANBEN: "Visual-Acoustic Penetration Recognition in Variable Polarity Plasma Arc Welding Process Using Hybrid Deep Learning Approach", IEEE ACCESS, IEEE, USA, vol. 8, 27 June 2020 (2020-06-27), USA , pages 120417 - 120428, XP011797649, DOI: 10.1109/ACCESS.2020.3005822 *

Also Published As

Publication number Publication date
JP2023061289A (en) 2023-05-01

Similar Documents

Publication Publication Date Title
JP6625914B2 (en) Machine learning device, laser processing system and machine learning method
Asif et al. Machine learning model to predict welding quality using air-coupled acoustic emission and weld inputs
Pal et al. Artificial neural network modeling of weld joint strength prediction of a pulsed metal inert gas welding process using arc signals
US10796226B2 (en) Laser processing apparatus and machine learning device
Liu et al. Prognostics of damage growth in composite materials using machine learning techniques
CN110549005B (en) Machining condition adjustment device and machine learning device
Mustafa Modelling of the hole quality characteristics by Extreme Learning Machine in fiber laser drilling of Ti-6Al-4V
EP2342040B1 (en) System and process for automatic determination of welding parameters for automated friction stir welding
Younis et al. Prediction of fatigue crack growth rate in aircraft aluminum alloys using radial basis function neural network
Park et al. Prediction modeling framework with bootstrap aggregating for noisy resistance spot welding data
WO2023068148A1 (en) Prediction/estimation system, learning device, and prediction/estimation device
Chen et al. Data-Driven welding expert system structure based on internet of things
CN110893515B (en) Machining condition adjustment device and machine learning device
Aldrin et al. Assessing the reliability of nondestructive evaluation methods for damage characterization
WO2023068147A1 (en) Welding system and welding result determination device
EP3888839B1 (en) Method and system for monitoring and identifying the weld quality of a welding performed by a welding machinery on metallic components
WO2023068146A1 (en) Welding system and welding monitor device
Liu et al. Surface roughness prediction using multi-source heterogeneous data and Bayesian quantile regression in milling process
US11367020B2 (en) Signal selection device, learning device, and signal selection method and program
Christian et al. Robust empirical predictions of residual performance of damaged composites with quantified uncertainties
El Ouafi et al. Dynamic resistance based model for on-line resistance spot welding quality assessment
JP2020128975A (en) Method for generating prediction model, method for predicting corrosion amount of metallic material, program for generating prediction model, and device of generating prediction model
Ansari et al. Modelling of Friction Stir Extrusion using Artificial Neural Network (ANN).
JP2021001851A (en) Vibration evaluation device, and vibration evaluation system
Liu et al. Adaptive modeling of the weld pool geometry in gas tungsten arc welding

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 22883452

Country of ref document: EP

Kind code of ref document: A1