CN115685949A - Method and device for adjusting data sampling frequency in discrete machining production process - Google Patents
Method and device for adjusting data sampling frequency in discrete machining production process Download PDFInfo
- Publication number
- CN115685949A CN115685949A CN202211705982.5A CN202211705982A CN115685949A CN 115685949 A CN115685949 A CN 115685949A CN 202211705982 A CN202211705982 A CN 202211705982A CN 115685949 A CN115685949 A CN 115685949A
- Authority
- CN
- China
- Prior art keywords
- data
- sampling frequency
- sensor
- discrete
- workpiece
- Prior art date
- Legal status (The legal status 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 status listed.)
- Pending
Links
- 238000005070 sampling Methods 0.000 title claims abstract description 170
- 238000000034 method Methods 0.000 title claims abstract description 76
- 238000004519 manufacturing process Methods 0.000 title claims abstract description 51
- 238000003754 machining Methods 0.000 title claims abstract description 49
- 230000008569 process Effects 0.000 claims abstract description 34
- 238000003062 neural network model Methods 0.000 claims abstract description 33
- 238000012545 processing Methods 0.000 claims abstract description 31
- 238000012549 training Methods 0.000 claims abstract description 30
- 230000006870 function Effects 0.000 claims description 24
- 230000002159 abnormal effect Effects 0.000 claims description 18
- 238000004891 communication Methods 0.000 claims description 15
- 230000003247 decreasing effect Effects 0.000 claims description 9
- 238000004590 computer program Methods 0.000 claims description 7
- 238000007781 pre-processing Methods 0.000 claims description 6
- 230000007423 decrease Effects 0.000 claims description 3
- 230000008030 elimination Effects 0.000 claims description 3
- 238000003379 elimination reaction Methods 0.000 claims description 3
- 238000003860 storage Methods 0.000 claims description 3
- 230000008859 change Effects 0.000 abstract description 14
- 239000000243 solution Substances 0.000 description 4
- 230000009471 action Effects 0.000 description 3
- 238000005520 cutting process Methods 0.000 description 3
- 239000006185 dispersion Substances 0.000 description 3
- 238000001746 injection moulding Methods 0.000 description 3
- 230000005540 biological transmission Effects 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000001914 filtration Methods 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- 238000003672 processing method Methods 0.000 description 2
- 230000001133 acceleration Effects 0.000 description 1
- 230000003044 adaptive effect Effects 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 238000005311 autocorrelation function Methods 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 239000003292 glue Substances 0.000 description 1
- 239000013072 incoming material Substances 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003595 spectral effect Effects 0.000 description 1
- 238000005507 spraying Methods 0.000 description 1
- 238000012706 support-vector machine Methods 0.000 description 1
- 239000002699 waste material Substances 0.000 description 1
Images
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Landscapes
- Feedback Control In General (AREA)
Abstract
The application relates to a method and a device for adjusting data sampling frequency in a discrete machining production process, wherein the method comprises the following steps: predicting the production data of the current workpiece to be machined of the discrete machine through a prediction model to obtain first data, wherein the prediction model is used for predicting the next production data based on a fitting function, and the fitting function is a function obtained by fitting a plurality of historical data; inputting data generated in the process of discrete machining a workpiece, which is acquired currently, into a neural network model, and outputting second data; the neural network model is obtained by training an initial neural network model based on a target training set; and adjusting the sampling frequency of the sensor according to the difference value of the first data and the second data. Through the application, the problem that a discrete machine in the prior art adopts fixed sampling frequency to sample data in the workpiece processing production process, so that the dynamic change requirement of data volume cannot be met is solved.
Description
Technical Field
The application relates to the field of intelligent equipment processing, in particular to a method and a device for adjusting data sampling frequency in a discrete machining production process.
Background
With the enhancement of manufacturing capability of discrete machines, the current production frequency is gradually increased, and part of the production frequency exceeds 200ppm (piece per minute) or even approaches 1000ppm. However, the requirement for production quality is not reduced, so that a monitoring system is required to monitor the production of each part, so as to prevent the abnormal production and abnormal part batch caused by unstable equipment power due to the uneven incoming material of equipment and tools (such as a punch, an injection molding glue spraying head, a CNC (computer numerical control) tool, electric power and other factors.
While currently directed to discrete production plants (discrete machines): stamping equipment, injection molding equipment, CNC cutting equipment and the like can be monitored by utilizing a systematized sensing network, namely, a communication system with intelligent sensing and edge calculation, which is formed by a large number of tiny sensors with edge calculation, is used for completing monitoring and coordinated production in a production process. However, the sampling frequency of the existing sensor is fixed, and if the data volume is large in the production and processing process, the requirement cannot be met, and if the sampling frequency is high in the case of small number in the production and processing process, the resource waste can be caused.
In view of the above problems in the related art, no effective solution exists at present.
Disclosure of Invention
The application provides a method and a device for adjusting data sampling frequency in a machining production process of a dispersion machine, which are used for solving the problem that the dispersion machine in the prior art cannot adapt to the dynamic change requirement of data quantity because data sampling is carried out by adopting fixed sampling frequency in the machining production process of a workpiece.
In a first aspect, the present application provides a method for adjusting data sampling frequency during a discrete machining process, comprising: predicting production data of a current workpiece to be machined of a discrete machine through a prediction model to obtain first data, wherein the prediction model is used for predicting next production data based on a fitting function, the fitting function is a function obtained by fitting a plurality of historical data, and the historical data is data which are collected in a historical time period and are generated in the process of machining the workpiece by the discrete machine; inputting data generated in the process of discrete machining a workpiece, which is acquired currently, into a neural network model, and outputting second data; the neural network model is obtained by training an initial neural network model based on a target training set, wherein the target training set comprises data generated in the process of machining workpieces by the discrete machine in a historical time period; and adjusting the sampling frequency of a sensor according to the difference value of the first data and the second data, wherein the sensor is used for collecting data generated in the discrete machining workpiece process based on the sampling frequency.
In a second aspect, the present application provides an apparatus for adjusting data sampling frequency during discrete machining production, comprising: the device comprises a first processing module, a second processing module and a control module, wherein the first processing module is used for predicting the production data of a workpiece to be machined currently by a discrete machine through a prediction model to obtain first data, the prediction model is used for predicting the next production data based on a fitting function, the fitting function is a function obtained by fitting a plurality of historical data, and the historical data is acquired in a historical time period and generated in the workpiece machining process of the discrete machine; the second processing module is used for inputting the data generated in the process of discrete machining the workpiece, which is acquired currently, into the neural network model and outputting second data; the neural network model is obtained by training an initial neural network model based on a target training set, wherein the target training set comprises data generated in the process of machining workpieces by the discrete machine in a historical time period; and the adjusting module is used for adjusting the sampling frequency of the sensor according to the difference value of the first data and the second data, wherein the sensor is used for collecting the data generated in the discrete machining workpiece process based on the sampling frequency.
In a third aspect, an air conditioner control device is provided, which comprises a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory are communicated with each other through the communication bus;
a memory for storing a computer program;
a processor adapted to perform the method steps of any of the embodiments of the first aspect when executing a program stored in the memory.
In a fourth aspect, a computer-readable storage medium is provided, on which a computer program is stored which, when being executed by a processor, carries out the method steps of any of the embodiments of the first aspect.
Compared with the prior art, the technical scheme provided by the embodiment of the application has the following advantages:
according to the method provided by the embodiment of the application, the first data of the current workpiece to be machined of the discrete machine can be predicted through the prediction model, the corresponding second data is obtained through the neural network model, and then the sampling frequency of the sensor is adjusted according to the difference value of the first data and the second data instead of fixing the sampling frequency of the sensor. That is to say, in this application, the sampling frequency can be adjusted according to the state change of the discrete machine, for example, if the difference is large, it indicates that the state of the current discrete machine is jittered, and the probability of abnormal data occurring at this time is large, so that the sampling frequency can be increased to increase the amount of the sampled data, if the difference is small, it indicates that the state of the current discrete machine is gentle, and the probability of abnormal data occurring at this time is small to reduce the amount of the sampled data, thereby solving the problem that the discrete machine in the prior art adopts a fixed sampling frequency to perform data sampling in the process of processing and producing workpieces, so that the dynamic change requirement of the data amount cannot be adapted.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the invention and together with the description, serve to explain the principles of the invention.
In order to more clearly illustrate the embodiments or technical solutions in the prior art of the present invention, the drawings used in the description of the embodiments or the prior art will be briefly described below, and it is obvious for those skilled in the art to obtain other drawings without inventive labor.
FIG. 1 is a schematic flow chart illustrating a method for adjusting data sampling frequency during discrete machining operations according to an embodiment of the present disclosure;
FIG. 2 is a schematic structural diagram of an apparatus for adjusting a data sampling frequency in a discrete machining process according to an embodiment of the present disclosure;
fig. 3 is a schematic structural diagram of an electronic device according to an embodiment of the present application.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are some embodiments of the present application, but not all embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
Fig. 1 is a schematic flowchart of a method for adjusting a data sampling frequency in a discrete machining production process according to an embodiment of the present application, where as shown in fig. 1, the method includes the steps of:
it should be noted that, the discrete machine in the embodiment of the present application refers to a discrete production device, such as a stamping device, an injection molding device, a CNC cutting device, and the like, and the discrete machine preferably applies a discrete production scenario of an ultra-high frequency machining cycle, such as a machining frequency: discrete production scenario >100 ppm.
In addition, the historical time period in the embodiment of the present application may refer to three days in the past, or a week in the past, or a month in the past, and may be specifically set according to actual conditions. If the current discrete machine has a high working frequency and generates more data in a short time, the data fitting can be performed without using data in a long time period, and the time for setting the historical time period is shorter. After obtaining data generated by the dispersion machine over a historical period of time, a smooth curve may be connected to obtain a fitted curve at a series of points on a predetermined plane. The fitted curve may generally be represented by a function, i.e. a fitting function.
and 106, adjusting the sampling frequency of the sensor according to the difference value of the first data and the second data, wherein the sensor is used for collecting data generated in the discrete machining workpiece process based on the sampling frequency.
It should be noted that the prediction model in the embodiment of the present application is obtained by predicting the production data of the current workpiece to be processed by the discrete machine to obtain a prediction data, that is, the prediction data is equivalent to data estimated based on historical data, and the data obtained by the neural network model is current real data. Therefore, the difference between the first data obtained according to the prediction model and the second data obtained based on the neural network model is equivalent to the difference between the inferred data and the real data, if the difference is large, the current discrete machine state is jittered, the probability of abnormal data is high, and if the difference is small, the current discrete machine state is gentle, and the probability of abnormal data is low. In addition, the sensor in the embodiment of the application can be a vibration sensor, a noise sensor, an ultrasonic sensor, an acceleration sensor, a stress-strain sensor, a high-precision temperature sensor and the like, and the sensor can be selected correspondingly according to actual requirements.
Based on the above steps 102 to 106, the first data of the workpiece to be processed currently by the discrete machine can be predicted through the prediction model, the corresponding second data is obtained through the neural network model, and then the sampling frequency of the sensor is adjusted according to the difference value between the first data and the second data, rather than being fixed. That is to say, in the present application, the sampling frequency may be adjusted according to the state change of the discrete machine, for example, if the difference is large, it indicates that the state of the current discrete machine is jittered, and at this time, the possibility of abnormal data is large, so that the sampling frequency may be increased to increase the amount of the sampled data, and if the difference is small, it indicates that the state of the current discrete machine is gentle, and at this time, the possibility of abnormal data is small, so that the amount of the sampled data is reduced, thereby solving the problem that the discrete machine in the prior art adopts a fixed sampling frequency to perform data sampling in the process of processing and producing workpieces, so that the dynamic change demand of the data amount cannot be adapted.
In an optional implementation manner of the embodiment of the present application, regarding the manner of adjusting the sampling frequency of the sensor according to the difference between the first data and the second data, which is referred to in the step 104, the method further may include:
step 11, under the condition that the absolute value of the difference value between the first data and the second data is larger than a preset threshold, adjusting the sampling frequency of the sensor to be a first sampling frequency based on the absolute value;
and step 12, under the condition that the absolute value of the difference value between the first data and the second data is smaller than a preset threshold value, adjusting the sampling frequency of the sensor to be a second sampling frequency based on the absolute value.
The sampling frequencies corresponding to different absolute values are different, and the first sampling frequency is greater than the second sampling frequency.
In the embodiment of the present application, the preset threshold may be used to indicate whether the state of the current discrete machine is relatively jittered, and the preset threshold may be set according to actual situations. If the absolute value exceeds the preset threshold value, the state of the current disperser is relatively jittered, the amplitude between the sampling frequencies corresponding to different absolute values larger than the preset threshold value is relatively large, and if the absolute value is smaller than the preset threshold value, the state of the current disperser is relatively flat, the amplitude between the sampling frequencies corresponding to different absolute values smaller than the preset threshold value is relatively small. Therefore, on the basis of further adjusting the sampling frequency of the sensor according to the state of the discrete machine, the sampling frequency can be adaptively adjusted according to the state change trend of the discrete machine, so that the sampling data is more reasonable.
In an optional implementation manner of the embodiment of the present application, after the manner of adjusting the sampling frequency of the sensor to the first sampling frequency based on the absolute value, which is referred to in step 11, the method further includes:
step 21, continuously increasing the current sampling frequency of the sensor under the condition that the absolute value is continuously increased; or the like, or a combination thereof,
and step 22, reducing the current sampling frequency of the sensor under the condition that the absolute value is continuously reduced.
As can be seen from the above steps 21 to 22, if the absolute value is continuously increased (the first data and the second data are more different) after the current sampling frequency is the first sampling frequency, which indicates that the current discrete machine is more jittery, the sampling frequency of the sensor can be continuously increased to ensure the data sampling quality. Of course, if the state of the current scatterer is still jittering, but the current sampling frequency can be reduced after the current scatterer is not jittered, that is, the sampling frequency can be adaptively adjusted according to the state of the actual scatterer to ensure the data sampling quality, so that the balance between the system efficiency and the data acquisition quality is realized.
In an optional implementation manner of the embodiment of the present application, after the adjusting the sampling frequency of the sensor to the second sampling frequency based on the absolute value, which is referred to in step 12, the method further includes:
step 31, continuously reducing the current sampling frequency of the sensor under the condition that the absolute value is continuously reduced; or,
in the case of a continuously increasing absolute value, the current sampling frequency of the sensor is increased, step 32.
As can be seen from the above steps 31 to 32, if the absolute value is continuously decreased (the first data and the second data are closer) after the current sampling frequency is the second sampling frequency, which indicates that the current discrete machine is more gentle, the sampling frequency of the sensor can be continuously decreased. Of course, if the state of the current scatterer is even, the current sampling frequency can be reduced to reduce the generation and transmission of redundant data compared with the state that the current scatterer does not tend to jitter before, that is, the sampling frequency can be adaptively adjusted according to the state of the actual scatterer to ensure the data sampling quality, so that the balance between the system efficiency and the data acquisition quality is realized.
In the case that the sampling frequency of the sensor is increased to the third sampling frequency, the sampling frequency is maintained to be the third sampling frequency; and keeping the sampling frequency as the fourth sampling frequency under the condition that the sampling frequency of the sensor is reduced to the fourth sampling frequency; in a specific example, the third sampling frequency may be a preset maximum sampling frequency and the fourth sampling frequency may be a preset minimum sampling frequency. That is, in the embodiment of the present application, the upper limit and the lower limit of the sampling frequency can be set to avoid exceeding the normal load of the sensor due to the too high or too low sampling frequency.
In this embodiment of the present application, the predicting, by the prediction model, the production data of the workpiece to be processed currently by the discrete machine, which is referred to in the step 102, to obtain the first data, may further include:
predicting the production data of the current workpiece to be machined of the discrete machine based on a linear Autoregressive (AR) model to obtain first data;
wherein the fitting function formula in the linear autoregressive AR model is as follows:
wherein, X p [n]Is the predicted data (first data), X r [n]Is history data, a i [n]Are coefficients of each order of the AR model.
In an alternative implementation of the embodiment of the present application, the increased sampling frequency may be determined by the following formula:
the reduced sampling frequency is determined by the following equation:
wherein, f i+1 For increased or decreased sampling frequency, f i For the current sampling frequency, sigma is a preset adjustable parameter, e is a natural constant, e i+1 I is the order of the AR model, which is the difference between the first data and the second data.
In the specific example, the AR model is taken as a second-order model as an example, and the predicted valueThe expression is as follows:
wherein, X i For historical true values, alpha and beta are model parameters, e i+1 Is the value of the error and,is the average of the past L historical data. For a given number L of historical data, the parameters α and β can be calculated from the sample autocorrelation function as follows:
wherein,then predict data (first data) and true numberThe difference between the data (second data) is:
In another optional implementation manner of the embodiment of the present application, the method in the embodiment of the present application may further include:
step 108, acquiring third data generated in the process of discrete machining of the workpiece, acquired by a sensor in a historical time period;
step 110, preprocessing the third data to obtain fourth data, wherein the preprocessing is used for processing abnormal data in the third data, and performing time alignment and noise elimination processing on the processed data on a time domain;
in a specific example, the abnormal value identification method such as three sigma and boxplot cutting may capture the abnormal value, and further, the captured abnormal value may be processed, and the processing method may be an average value replacement method, a moving average method, or the like as follows. In addition, the time series data processing method may be: time-alignment, DTW, etc. to time-align the data, and noise cancellation using filtering techniques such as high di-pass filtering, wavelet techniques, etc.
the time domain feature processing in the embodiment of the present application may be performed by means of a mean value, a variance, a maximum and minimum value, a peak-to-peak value, a skewness, a kurtosis coefficient, a margin coefficient, and the like. Meanwhile, the filtered data can be subjected to Fast Fourier Transform (FFT) to extract frequency domain characteristics, wherein the frequency domain characteristics can be barycentric frequency, mean square frequency, frequency variance, short-time power spectral density and the like.
And step 114, training the initial neural network model based on the target training set to obtain the neural network model.
It should be noted that the neural network model in the application embodiment may be a supervised model or an unsupervised model; wherein, the supervision model may be: linear classifiers, naive bayes, support vector machines, K-nearest neighbors, decision (regression) trees, ensemble models, and the like. The unsupervised model may be: k-means, DBSCAN (sensitivity-Based Spatial Clustering of Applications with Noise), GMM (Adaptive background mix models for real-time tracking), hierarchical Clustering, isolated forest, etc.
Therefore, in the embodiment of the application, the sampling frequency can be changed according to the state change condition of the object to be observed (discrete machine), and when the state change of the object to be observed is jittery, namely the difference between the real data (second data) and the predicted data (first data) is greater than a preset threshold, the sampling frequency is increased, which indicates that the production state has great change, and the data quality should be improved, namely the sampling frequency is improved. Because the probability of generating abnormal data during the jitter period is also increased, the algorithm can obtain more abnormal information by using a larger sampling frequency, that is, the sampling frequency is increased during the jitter period, so that the data sampling quality can be ensured, and the balance between the system efficiency and the data acquisition quality is realized. If the sampling frequency is decreased when the state change of the observed object is relatively gentle, that is, the difference between the real data (second data) and the predicted data (first data) is smaller than the preset threshold, indicating that the production state has relatively large change at this time, the sampling frequency should be decreased at this time to reduce the generation and transmission of redundant data.
Corresponding to the method for adjusting the data sampling frequency in the discrete machining production process in fig. 1, the present application also provides an apparatus for adjusting the data sampling frequency in the discrete machining production process, as shown in fig. 2, the apparatus includes:
the first processing module 22 is configured to predict, through a prediction model, production data of a workpiece to be machined currently by the discrete machining machine to obtain first data, where the prediction model is configured to predict next production data based on a fitting function, the fitting function is a function obtained by fitting a plurality of historical data, and the historical data is data generated in the process of machining the workpiece by the discrete machining machine and collected in a historical time period;
the second processing module 24 is configured to input data generated in the currently acquired discrete machining workpiece process into the neural network model, and output second data; the neural network model is obtained by training an initial neural network model based on a target training set, wherein the target training set comprises data generated in the process of discretely machining a workpiece in a historical time period;
and an adjusting module 26, configured to adjust a sampling frequency of a sensor according to a difference between the first data and the second data, wherein the sensor is configured to acquire data generated in the discrete machining process based on the sampling frequency.
Through the device provided by the embodiment of the application, the first data of the current workpiece to be machined of the discrete machine can be predicted through the prediction model, the corresponding second data is obtained through the neural network model, and then the sampling frequency of the sensor is adjusted according to the difference value of the first data and the second data instead of fixing the sampling frequency of the sensor. That is to say, in the present application, the sampling frequency may be adjusted according to the state change of the discrete machine, for example, if the difference is large, it indicates that the state of the current discrete machine is jittered, and at this time, the possibility of abnormal data is large, so that the sampling frequency may be increased to increase the amount of the sampled data, and if the difference is small, it indicates that the state of the current discrete machine is gentle, and at this time, the possibility of abnormal data is small, so that the amount of the sampled data is reduced, thereby solving the problem that the discrete machine in the prior art adopts a fixed sampling frequency to perform data sampling in the process of processing and producing workpieces, so that the dynamic change demand of the data amount cannot be adapted.
Optionally, the adjusting module 26 in this embodiment of the present application further includes: the first adjusting unit is used for adjusting the sampling frequency of the sensor to be the first sampling frequency based on the absolute value under the condition that the absolute value of the difference value of the first data and the second data is larger than a preset threshold value; the second adjusting unit is used for adjusting the sampling frequency of the sensor to be a second sampling frequency based on the absolute value under the condition that the absolute value of the difference value of the first data and the second data is smaller than a preset threshold value; the sampling frequencies corresponding to different absolute values are different, and the first sampling frequency is greater than the second sampling frequency.
Optionally, the first adjusting unit in this embodiment of the application is further configured to, after adjusting the sampling frequency of the sensor to be the first sampling frequency based on the absolute value, continuously increase the current sampling frequency of the sensor if the absolute value is continuously increased; or, in the case where the absolute value continues to decrease, the current sampling frequency of the sensor is decreased.
Optionally, the second adjusting unit in this embodiment of the application is further configured to, after adjusting the sampling frequency of the sensor to be the second sampling frequency based on the absolute value, continuously decrease the current sampling frequency of the sensor if the absolute value is continuously decreased; or, under the condition that the absolute value is continuously increased, the current sampling frequency of the sensor is increased
Optionally, the apparatus in this embodiment of the present application may further include: the first holding module is used for holding the sampling frequency of the sensor to be the third sampling frequency under the condition that the sampling frequency of the sensor is increased to be the third sampling frequency; the second holding module is used for holding the sampling frequency of the sensor to be the fourth sampling frequency under the condition that the sampling frequency of the sensor is reduced to be the fourth sampling frequency; wherein the third sampling frequency is greater than the fourth sampling frequency.
Optionally, the first processing module 22 in this embodiment of the present application further includes: the first processing unit is used for predicting the production data of the current workpiece to be processed of the discrete machine based on the linear Autoregressive (AR) model to obtain first data;
wherein the fitting function formula in the linear autoregressive AR model is as follows:
wherein, X p [n]Is the first data, X r [n]Is historical data,a i [n]Are coefficients of each order of the AR model.
In the embodiment of the present application, the increased sampling frequency may be determined by the following formula:
further, the reduced sampling frequency may be determined by the following equation:
wherein f is i+1 For increased or decreased sampling frequency, f i For the current sampling frequency, sigma is a preset adjustable parameter, e is a natural constant, e i+1 I is the order of the AR model, is the difference between the first data and the second data.
The apparatus in the embodiment of the present application may further include: the acquisition module is used for acquiring third data generated in the process of discrete machining of the workpiece in a historical time period; the third processing module is used for preprocessing the third data to obtain fourth data, wherein the preprocessing is used for processing abnormal data in the third data, and performing time alignment and noise elimination processing on the processed data on a time domain; the fourth processing module is used for performing feature engineering processing on the fourth data to obtain a target training set; and the training module is used for training the initial neural network model based on the target training set to obtain the neural network model.
As shown in fig. 3, an electronic device according to an embodiment of the present application includes a processor 111, a communication interface 112, a memory 113, and a communication bus 114, where the processor 111, the communication interface 112, and the memory 113 complete mutual communication via the communication bus 114,
a memory 113 for storing a computer program;
in an embodiment of the present application, when the processor 111 is configured to execute the program stored in the memory 113, the functions of the method for adjusting the data sampling frequency in the discrete machining production process provided in any one of the foregoing method embodiments are also similar, and are not described herein again.
Embodiments of the present application further provide a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the method for adjusting data sampling frequency in a discrete machining production process, as provided in any of the method embodiments described above, is implemented.
It is noted that, in this document, relational terms such as "first" and "second," and the like, may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrases "comprising a," "8230," "8230," or "comprising" does not exclude the presence of additional like elements in a process, method, article, or apparatus that comprises the element.
The foregoing are merely exemplary embodiments of the present invention, which enable those skilled in the art to understand or practice the present invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the invention. Thus, the present invention is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims (11)
1. A method of adjusting data sampling frequency during discrete machining production, comprising:
predicting production data of a current workpiece to be machined of a discrete machine through a prediction model to obtain first data, wherein the prediction model is used for predicting next production data based on a fitting function, the fitting function is a function obtained by fitting a plurality of historical data, and the historical data is data which are collected in a historical time period and are generated in the process of machining the workpiece by the discrete machine;
inputting data generated in the process of discrete machining a workpiece, which is acquired currently, into a neural network model, and outputting second data; the neural network model is obtained by training an initial neural network model based on a target training set, wherein the target training set comprises data generated in the process of machining workpieces by the discrete machine in a historical time period;
adjusting the sampling frequency of a sensor according to the difference value of the first data and the second data, wherein the sensor is used for collecting data generated in the discrete machining workpiece process based on the sampling frequency.
2. The method of claim 1, wherein adjusting the sampling frequency of the sensor based on the difference between the first data and the second data comprises:
under the condition that the absolute value of the difference value of the first data and the second data is larger than a preset threshold value, adjusting the sampling frequency of the sensor to be a first sampling frequency based on the absolute value;
under the condition that the absolute value of the difference value of the first data and the second data is smaller than the preset threshold value, adjusting the sampling frequency of the sensor to be a second sampling frequency based on the absolute value;
the sampling frequencies corresponding to different absolute values are different, and the first sampling frequency is greater than the second sampling frequency.
3. The method of claim 2, wherein after adjusting the sampling frequency of the sensor to a first sampling frequency based on the absolute value, the method further comprises:
continuously increasing the current sampling frequency of the sensor under the condition that the absolute value is continuously increased; or,
and in the case that the absolute value continuously decreases, reducing the current sampling frequency of the sensor.
4. The method of claim 2, wherein after adjusting the sampling frequency of the sensor to a second sampling frequency based on the absolute value, the method further comprises:
continuously reducing the current sampling frequency of the sensor under the condition that the absolute value is continuously reduced; or the like, or a combination thereof,
and increasing the current sampling frequency of the sensor under the condition that the absolute value is continuously increased.
5. The method of claim 2, further comprising:
in the case where the sampling frequency of the sensor is increased to be a third sampling frequency, maintaining the sampling frequency of the sensor at the third sampling frequency;
in the case where the sampling frequency of the sensor is reduced to a fourth sampling frequency, maintaining the sampling frequency of the sensor at the fourth sampling frequency;
wherein the third sampling frequency is greater than the fourth sampling frequency.
6. The method of claim 4, wherein the predicting the production data of the workpiece to be machined currently by the discrete machine through the predictive model to obtain the first data comprises:
predicting the production data of the current workpiece to be machined of the discrete machine based on a linear Autoregressive (AR) model to obtain first data;
wherein the fitting function in the AR model has the following formula:
wherein X p [n]Is the first data, X r [n]Is history data, a i [n]Are coefficients of the various orders of the AR model.
7. The method of claim 6,
the increased sampling frequency is determined by the following equation:
the reduced sampling frequency is determined by the following equation:
wherein f is i+1 For increased or decreased sampling frequency, f i For the current sampling frequency, sigma is a preset adjustable parameter, e is a natural constant, e i+1 I is the order of the AR model, is the difference between the first data and the second data.
8. The method of claim 1, further comprising:
acquiring third data generated in the process of machining the workpieces by the discrete machines in historical time periods;
preprocessing the third data to obtain fourth data, wherein the preprocessing is used for processing abnormal data in the third data, and performing time alignment and noise elimination on the processed data in a time domain;
performing feature engineering processing on the fourth data to obtain the target training set;
and training an initial neural network model based on the target training set to obtain the neural network model.
9. An apparatus for adjusting data sampling frequency during discrete machining production, comprising:
the system comprises a first processing module, a second processing module and a third processing module, wherein the first processing module is used for predicting production data of a workpiece to be machined currently of a discrete machine through a prediction model to obtain first data, the prediction model is used for predicting next production data based on a fitting function, the fitting function is a function obtained by fitting a plurality of historical data, and the historical data is data collected in a historical time period and generated in the process of machining the workpiece by the discrete machine;
the second processing module is used for inputting the data generated in the process of discrete machining the workpiece, which is acquired currently, into the neural network model and outputting second data; the neural network model is obtained by training an initial neural network model based on a target training set, wherein the target training set comprises data generated in the process of machining workpieces by the discrete machine in a historical time period;
and the adjusting module is used for adjusting the sampling frequency of the sensor according to the difference value of the first data and the second data, wherein the sensor is used for collecting the data generated in the discrete machining workpiece process based on the sampling frequency.
10. The electronic equipment is characterized by comprising a processor, a communication interface, a memory and a communication bus, wherein the processor and the communication interface are used for realizing the communication between the processor and the memory through the communication bus;
a memory for storing a computer program;
a processor for implementing the method steps of any one of claims 1-8 when executing a program stored in a memory.
11. A computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, carries out the method steps of any of claims 1-8.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202211705982.5A CN115685949A (en) | 2022-12-29 | 2022-12-29 | Method and device for adjusting data sampling frequency in discrete machining production process |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202211705982.5A CN115685949A (en) | 2022-12-29 | 2022-12-29 | Method and device for adjusting data sampling frequency in discrete machining production process |
Publications (1)
Publication Number | Publication Date |
---|---|
CN115685949A true CN115685949A (en) | 2023-02-03 |
Family
ID=85056146
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202211705982.5A Pending CN115685949A (en) | 2022-12-29 | 2022-12-29 | Method and device for adjusting data sampling frequency in discrete machining production process |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN115685949A (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN116797053A (en) * | 2023-08-25 | 2023-09-22 | 深圳普菲特信息科技股份有限公司 | Chemical production data analysis method, system and medium based on neural network |
CN117874435A (en) * | 2024-03-11 | 2024-04-12 | 中国电子科技集团公司第十五研究所 | Distributed edge data acquisition method and device, electronic equipment and storage medium |
Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106446419A (en) * | 2016-09-27 | 2017-02-22 | 广东电网有限责任公司电力科学研究院 | Modeling method and system of coal-fired boiler in thermal power plant |
CN108875841A (en) * | 2018-06-29 | 2018-11-23 | 国家电网有限公司 | A kind of pumped storage unit vibration trend forecasting method |
CN110545305A (en) * | 2018-05-28 | 2019-12-06 | 塔塔咨询服务有限公司 | Method and system for adaptive parameter sampling |
CN111146865A (en) * | 2019-12-25 | 2020-05-12 | 上海电力大学 | Intelligent monitoring system for operation and maintenance state of power equipment |
CN111930079A (en) * | 2020-06-30 | 2020-11-13 | 西门子工厂自动化工程有限公司 | Data acquisition method, device and system, electronic equipment and storage medium |
CN112926770A (en) * | 2021-02-22 | 2021-06-08 | 胡书恺 | Unified data metering and collecting system based on digital twins |
CN113377033A (en) * | 2019-01-15 | 2021-09-10 | 北京百度网讯科技有限公司 | Data acquisition method, device, equipment and computer readable storage medium |
CN113655768A (en) * | 2021-10-21 | 2021-11-16 | 深圳市信润富联数字科技有限公司 | Assembly yield control method, equipment and computer readable storage medium |
-
2022
- 2022-12-29 CN CN202211705982.5A patent/CN115685949A/en active Pending
Patent Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106446419A (en) * | 2016-09-27 | 2017-02-22 | 广东电网有限责任公司电力科学研究院 | Modeling method and system of coal-fired boiler in thermal power plant |
CN110545305A (en) * | 2018-05-28 | 2019-12-06 | 塔塔咨询服务有限公司 | Method and system for adaptive parameter sampling |
CN108875841A (en) * | 2018-06-29 | 2018-11-23 | 国家电网有限公司 | A kind of pumped storage unit vibration trend forecasting method |
CN113377033A (en) * | 2019-01-15 | 2021-09-10 | 北京百度网讯科技有限公司 | Data acquisition method, device, equipment and computer readable storage medium |
CN111146865A (en) * | 2019-12-25 | 2020-05-12 | 上海电力大学 | Intelligent monitoring system for operation and maintenance state of power equipment |
CN111930079A (en) * | 2020-06-30 | 2020-11-13 | 西门子工厂自动化工程有限公司 | Data acquisition method, device and system, electronic equipment and storage medium |
CN112926770A (en) * | 2021-02-22 | 2021-06-08 | 胡书恺 | Unified data metering and collecting system based on digital twins |
CN113655768A (en) * | 2021-10-21 | 2021-11-16 | 深圳市信润富联数字科技有限公司 | Assembly yield control method, equipment and computer readable storage medium |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN116797053A (en) * | 2023-08-25 | 2023-09-22 | 深圳普菲特信息科技股份有限公司 | Chemical production data analysis method, system and medium based on neural network |
CN116797053B (en) * | 2023-08-25 | 2023-11-10 | 深圳普菲特信息科技股份有限公司 | Chemical production data analysis method, system and medium based on neural network |
CN117874435A (en) * | 2024-03-11 | 2024-04-12 | 中国电子科技集团公司第十五研究所 | Distributed edge data acquisition method and device, electronic equipment and storage medium |
CN117874435B (en) * | 2024-03-11 | 2024-06-25 | 中国电子科技集团公司第十五研究所 | Distributed edge data acquisition method and device, electronic equipment and storage medium |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN115685949A (en) | Method and device for adjusting data sampling frequency in discrete machining production process | |
Henriquez et al. | Review of automatic fault diagnosis systems using audio and vibration signals | |
CN106649755B (en) | Threshold value self-adaptive setting abnormity detection method for multi-dimensional real-time power transformation equipment data | |
JP2014238833A (en) | Systems and methods for process alarm reduction | |
Yao et al. | Real-time chatter detection and automatic suppression for intelligent spindles based on wavelet packet energy entropy and local outlier factor algorithm | |
CN108491965B (en) | State prediction method and device for stamping equipment, electronic equipment and storage medium | |
JP2021047183A (en) | Method for detecting abnormality of robot device | |
Yuan et al. | Energy efficiency state identification of milling processing based on EEMD-PCA-ICA | |
CN112207631A (en) | Method for generating tool detection model, method, system, device and medium for detecting tool detection model | |
CN106600446B (en) | Production field event real-time processing system and method based on dynamic priority | |
CN107942953B (en) | Method for inhibiting machining vibration | |
Yang et al. | Application of bispectrum diagonal slice feature analysis to monitoring CNC tool wear states | |
CN117369418A (en) | Fault diagnosis method, system, storage medium and equipment for feeding system of numerical control machine tool | |
CN112420066A (en) | Noise reduction method, noise reduction device, computer equipment and computer readable storage medium | |
US11463849B2 (en) | Data processing device, data analyzing device, data processing system and method for processing data | |
Rahman et al. | Recognition of unnatural variation patterns in metal-stamping process using artificial neural network and statistical features | |
CN111563543B (en) | Method and device for cleaning wind speed-power data of wind turbine generator | |
CN115041544A (en) | Method and device for detecting abnormality of stamping part and storage medium | |
Ganga et al. | Adaptive prediction model for effective electrical machine maintenance | |
CN112426155A (en) | On-site work optimization method and system based on employee work emotion | |
Netsanet et al. | Short term load forecasting using wavelet augmented non-linear autoregressive neural networks: A single customer level perspective | |
CN111258866A (en) | Computer performance prediction method, device, equipment and readable storage medium | |
JP2020187616A (en) | Plant monitoring model creation device, plant monitoring model creation method, and plant monitoring model creation program | |
US20240210911A1 (en) | Mold state monitoring system and method thereof | |
Huang et al. | Process monitoring with ICA‐based signal extraction technique and CART approach |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20230203 |