CN116502155A - Safety supervision system for numerical control electric screw press - Google Patents
Safety supervision system for numerical control electric screw press Download PDFInfo
- Publication number
- CN116502155A CN116502155A CN202310775936.0A CN202310775936A CN116502155A CN 116502155 A CN116502155 A CN 116502155A CN 202310775936 A CN202310775936 A CN 202310775936A CN 116502155 A CN116502155 A CN 116502155A
- Authority
- CN
- China
- Prior art keywords
- data
- screw press
- electric screw
- numerical control
- control electric
- 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.)
- Granted
Links
- 238000007637 random forest analysis Methods 0.000 claims abstract description 44
- 238000000034 method Methods 0.000 claims abstract description 36
- 238000007405 data analysis Methods 0.000 claims abstract description 19
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 18
- 238000013500 data storage Methods 0.000 claims abstract description 16
- 238000012545 processing Methods 0.000 claims abstract description 12
- 238000007726 management method Methods 0.000 claims abstract description 11
- 238000004891 communication Methods 0.000 claims abstract description 4
- 238000011156 evaluation Methods 0.000 claims description 165
- 238000012544 monitoring process Methods 0.000 claims description 44
- 238000007781 pre-processing Methods 0.000 claims description 19
- 230000002596 correlated effect Effects 0.000 claims description 18
- 238000006073 displacement reaction Methods 0.000 claims description 16
- 238000012795 verification Methods 0.000 claims description 11
- 230000002159 abnormal effect Effects 0.000 claims description 10
- 230000008569 process Effects 0.000 claims description 9
- 238000004140 cleaning Methods 0.000 claims description 8
- 238000003066 decision tree Methods 0.000 claims description 8
- 238000012216 screening Methods 0.000 claims description 8
- 238000003860 storage Methods 0.000 claims description 8
- 238000004458 analytical method Methods 0.000 claims description 7
- 238000005516 engineering process Methods 0.000 claims description 6
- 230000006870 function Effects 0.000 claims description 6
- 238000011426 transformation method Methods 0.000 claims description 6
- 238000013145 classification model Methods 0.000 claims description 4
- 230000008030 elimination Effects 0.000 claims description 4
- 238000003379 elimination reaction Methods 0.000 claims description 4
- 238000010801 machine learning Methods 0.000 claims description 4
- 230000007246 mechanism Effects 0.000 claims description 4
- 238000010606 normalization Methods 0.000 claims description 4
- 238000012423 maintenance Methods 0.000 claims description 3
- 238000005242 forging Methods 0.000 description 5
- 238000004364 calculation method Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 2
- 238000007689 inspection Methods 0.000 description 2
- 238000012502 risk assessment Methods 0.000 description 2
- 238000006467 substitution reaction Methods 0.000 description 2
- 230000009466 transformation Effects 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 238000013480 data collection Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 238000010223 real-time analysis Methods 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 238000007873 sieving Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 238000012549 training Methods 0.000 description 1
- 238000009966 trimming Methods 0.000 description 1
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B21—MECHANICAL METAL-WORKING WITHOUT ESSENTIALLY REMOVING MATERIAL; PUNCHING METAL
- B21J—FORGING; HAMMERING; PRESSING METAL; RIVETING; FORGE FURNACES
- B21J9/00—Forging presses
- B21J9/10—Drives for forging presses
- B21J9/20—Control devices specially adapted to forging presses not restricted to one of the preceding subgroups
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/211—Selection of the most significant subset of features
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/217—Validation; Performance evaluation; Active pattern learning techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/243—Classification techniques relating to the number of classes
- G06F18/24323—Tree-organised classifiers
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Biology (AREA)
- Artificial Intelligence (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Life Sciences & Earth Sciences (AREA)
- Evolutionary Computation (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Mechanical Engineering (AREA)
- Testing And Monitoring For Control Systems (AREA)
- General Factory Administration (AREA)
Abstract
The invention relates to the technical field of safety management, and particularly discloses a safety supervision system for a numerical control electric screw press, which comprises a processor, and a data acquisition module, a data storage module, a data analysis module and a data display module which are in communication connection with the processor; by selecting data processing and algorithms, a random forest model with high efficiency, accuracy and generalization capability is constructed, support is provided for safety supervision of the numerical control electric screw press, key features with the greatest influence on the safety of the numerical control electric screw press are screened out from a large number of features, so that the performance and accuracy of the random forest model are improved, and the method is used for solving the problems that the high data dimension and the high data complexity in a safety supervision system of characteristic data reduce the efficiency and accuracy of data analysis.
Description
Technical Field
The invention relates to the technical field of safety management, in particular to a safety supervision system for a numerical control electric screw press.
Background
The screw press is forging machinery for transmitting flywheel energy by using a screw rod and a nut as a transmission mechanism, is widely applied to different forging processes such as die forging, trimming, correction and the like, and particularly the numerical control electric screw press adopted by the connecting rod die forging of the automobile engine generally needs to be subjected to strict safety supervision and quality inspection. With the development of big data technology, it has become a trend to monitor and manage the numerical control electric screw press by using the big data technology. The equipment data volume in the safety monitoring management system of the characteristic data is large, the data dimension is high, the existing monitoring management system cannot extract the characteristic with the largest influence on the running state of the equipment through huge equipment data with higher dimension, and the efficiency and the accuracy of data analysis are reduced due to high data dimension and high data complexity.
The random forest is an integrated learning algorithm based on a decision tree, the importance of the characteristics can be calculated by constructing a random forest model, and the application of the algorithm in a safety supervision system of a numerical control electric screw press for a connecting rod die forging piece of an automobile engine is not clear and specific, and particularly, the method is very important for monitoring and managing effective energy, striking force, sliding block speed, sliding block displacement, driving current, driving voltage and motor temperature rise. In order to solve the above problems, a technical solution is now provided.
Disclosure of Invention
In order to overcome the defects in the prior art, the invention provides a safety supervision system for a numerical control electric screw press, which constructs a random forest model with high efficiency, accuracy and high generalization capability through data processing and algorithm selection, provides support for safety supervision of the numerical control electric screw press, screens out key features with the greatest influence on the safety of the numerical control electric screw press from a large number of features, better performs risk assessment and prediction of the numerical control electric screw press, and improves the efficiency and performance of the safety supervision system of the numerical control electric screw press so as to solve the problems in the background technology.
In order to achieve the above purpose, the present invention provides the following technical solutions:
the utility model provides a safety supervision system for numerical control electric screw press, including the treater and with the data acquisition module of treater communication connection, data storage module, data analysis module and data show module, data analysis module includes data preprocessing module, parameter evaluation module, modeling module and prediction module, parameter evaluation module builds equipment running state evaluation index through numerical control electric screw press temperature that data washd is accomplished, pressure, flow, vibration, electric current and voltage data, safety state evaluation index and energy efficiency evaluation index, be used for evaluating equipment running state, safety state and energy efficiency information respectively, carry out comprehensive evaluation to equipment's state through equipment running state evaluation index, safety state evaluation index and the weighted sum of energy efficiency evaluation index, comprehensive evaluation's formula is:
；
wherein:for comprehensive evaluation index->For the evaluation of the operating state, ∈>For the safety state evaluation index, < >>Is an energy efficiency evaluation index, which is->、/>And +.>The influence weights of the operation state evaluation index, the safety state evaluation index and the energy efficiency evaluation index are set individually according to the type of the numerical control electric screw press and the attribute of the parameter emphasis, so that the requirements of ≡>、/>And +.>All are->Constant between->；
The parameter evaluation index obtains the data of the comprehensive evaluation index through a comprehensive evaluation formula, a sample data set is created by utilizing the data of the comprehensive evaluation index, the mean value and the standard deviation of the sample data set are calculated, the data in the sample data set are standardized by utilizing the mean value and the standard deviation, and the standardization formula is as follows:
；
wherein:for comprehensively evaluating the indexStandard value, ->For the mean value of the sample dataset, +.>Variance for the sample dataset;
substituting the standard value of the comprehensive evaluation index as an independent variable into a functionUsing function valuesAnd carrying out two classifications on the comprehensive evaluation indexes to realize classification evaluation of the comprehensive indexes.
As a further scheme of the invention, in the parameter evaluation module, the operation state evaluation index of the numerical control electric screw press is positively correlated with the monitoring values of effective energy, striking force, sliding block speed and sliding block displacement, and the operation state evaluation index formula of the numerical control electric screw press is as follows:
；
wherein:for the effective energy monitoring value of a numerical control electric screw press,/->Is the striking force monitoring value of the numerical control electric screw press, < ->For the slide speed monitoring value of the numerical control electric screw press, < >>Is the basic value of the speed of the sliding block of the numerical control electric screw press, is the initial striking speed in the descending return stroke of the sliding block, is +.>Is a sliding block displacement monitoring value of the numerical control electric screw press.
As a further scheme of the invention, in the parameter evaluation module, the safety state evaluation index of the numerical control electric screw press is positively correlated with the driving current, positively correlated with the driving voltage and positively correlated with the motor temperature rise, and the formula of the safety state evaluation index is as follows:
；
wherein:for the gas concentration monitoring value, +.>For the initial gas concentration value, < > is empirically set according to the type of gas used in the numerical control electric screw press>For the gas temperature monitoring value of the gas cylinder, +.>Is the pressure monitoring value of the gas cylinder.
As a further scheme of the invention, in the parameter evaluation module, an energy efficiency evaluation index of the numerical control electric screw press is positively correlated with the actual displacement of the sliding block, and is positively correlated with the actual striking energy, and the formula of the energy efficiency evaluation index is as follows:
；
wherein:for the actual slide displacement monitoring value, < >>Is the actual striking energy monitoring value.
As a further aspect of the present invention, in the parameter evaluation module, the classification mechanism of the comprehensive evaluation index is that,
when (when)When the comprehensive evaluation index is classified as a first level;
when (when)And when the comprehensive evaluation indexes are classified into a second level, the evaluation state of the first level is smaller than that of the second level.
As a further aspect of the invention, the processor is for processing data from at least one component of a safety supervision system for a digitally controlled electric screw press;
the data acquisition module is used for acquiring monitoring data of the numerical control electric screw press, sending the acquired monitoring data to the data analysis module for analysis and processing, and sending the acquired monitoring data to the data storage module for storage;
the data storage module is used for storing the acquired data on a plurality of nodes by using a distributed storage technology through the data generated by acquisition, preprocessing, evaluation, modeling and prediction;
the data display module is used for displaying the processed data in the form of a chart and providing a function of managing remote control and maintenance record management of the numerical control electric screw press.
According to the invention, after the data analysis module receives the information sent by the data acquisition module, the data stored in the data storage module is called by the processor to analyze and process the running state of the numerical control electric screw press, different state evaluation indexes and comprehensive evaluation indexes are obtained, the comprehensive indexes are subjected to hierarchical evaluation, evaluation levels are sent to the data storage module and the data display module, meanwhile, different state evaluation indexes are sent to the modeling module and the prediction module, an original data set is built through the evaluation index values of three different states, the original data set is divided into a plurality of different subsets, a decision tree is built for each subset, a random forest model is obtained through integrating all decision trees, the characteristic with the largest influence on the running state of the numerical control electric screw press is extracted, abnormal data are identified, the alarm is given in time, the fault risk and the safety risk of the numerical control electric screw press are judged, the safety state and the fault state of the numerical control electric screw press are comprehensively analyzed and predicted, and the mutual influence and the cross relation among the evaluation indexes of the different states are judged.
As a further scheme of the invention, the process of extracting the operating state influence characteristics of the numerical control electric screw press by the data analysis module through utilizing the random forest machine learning model comprises the following steps,
step S1, data preprocessing: the data preprocessing module respectively acquires different subsets from the acquired running state evaluation index data set, the safety state evaluation index data set and the energy efficiency evaluation index data set, and performs data cleaning, missing value filling and data standardization on the data of the subsets;
step S2, constructing a random forest model: the modeling module uses the preprocessed equipment data to construct a classification model by utilizing a random forest algorithm, adjusts parameters of the random forest model, wherein the parameters of the random forest model comprise the number of trees and the depth of the trees, and judges the running state and abnormal condition of the equipment;
step S3, calculating feature importance: calculating the importance of the features by using a random forest algorithm, and judging the influence degree of each feature on a target variable by using a base index;
step S4, feature selection: selecting features with larger influence on a target variable according to an importance sorting result, and preprocessing the features by using a feature screening method, a feature transformation method and a feature combination method, wherein the feature screening method adopts a correlation coefficient analysis method to select features related to fault prediction, the feature transformation method comprises feature standardization and normalization, the feature combination method is to construct a feature set by a feature intersection method, remove redundancy and noise features, and perform feature selection by using a recursive feature elimination method;
step S5, model verification and adjustment: and verifying the validity of the selected features by using a cross verification method, evaluating and optimizing the constructed random forest model, randomly selecting a plurality of super-parameter combinations in a preset super-parameter space for searching, and obtaining the optimal super-parameter combinations.
Evaluating the model by using the verification set, calculating the accuracy, recall and F1 score in the model, adjusting the super parameters of the model according to the performance indexes on the verification set, simultaneously increasing or reducing the feature quantity, searching the optimal super parameter combination by using a random search method, regularizing the model according to the performance indexes and the parameter adjustment result of the model, preventing the model from being over fitted, and finally retesting the model by using the test set to obtain the final prediction result.
The invention discloses a technical effect and advantages of a safety supervision system for a numerical control electric screw press, which are as follows:
according to the invention, through data processing and algorithm selection, a parameter evaluation module is utilized to acquire effective energy, striking force, slider speed, slider displacement, driving current, driving voltage and motor temperature rise data of the numerical control electric screw press which are completed through data cleaning, an equipment operation state evaluation index, a safety state evaluation index and an energy efficiency evaluation index are constructed, a high-efficiency, accurate and generalized random forest model with strong capability is constructed to judge and predict fault states of data sets of the three state evaluation indexes, support is provided for safety supervision of the numerical control electric screw press, key characteristics with the greatest influence on the safety of the numerical control electric screw press are screened from a large number of characteristics, so that the performance and accuracy of a random forest model are improved, the risk evaluation and prediction of the numerical control electric screw press are better carried out, the calculation cost and the storage cost are reduced, the efficiency and performance of a safety supervision system of the numerical control electric screw press are improved, and the effective monitoring and management of the logarithmic control electric screw press are realized.
Drawings
FIG. 1 is a flow chart of a process of extracting the influence characteristics of the running state of a numerical control electric screw press by a data analysis module according to the invention by using a random forest machine learning model;
fig. 2 is a schematic structural diagram of a safety supervision system for a numerical control electric screw press according to the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Example 1
The invention discloses a safety supervision system for a numerical control electric screw press, which is characterized in that through data processing and algorithm selection, a parameter evaluation module is utilized to acquire effective energy, striking force, sliding block speed, sliding block displacement, driving current, driving voltage of the numerical control electric screw press which is completed through data cleaning, and operational state evaluation indexes, safety state evaluation indexes and energy efficiency evaluation indexes of motor temperature rise data construction equipment, and then a high-efficiency, accurate and generalization random forest model is constructed to perform fault state judgment and prediction on data sets of the three state evaluation indexes, so that support is provided for safety supervision of the numerical control electric screw press, key characteristics with the greatest influence on the safety of the numerical control electric screw press are screened out from a large number of characteristics, so that the performance and accuracy of the random forest model are improved, the risk evaluation and the prediction of the numerical control electric screw press are better performed, the calculation cost and the storage cost are reduced, the efficiency and the performance of the safety supervision system of the numerical control electric screw press are improved, and the effective energy, striking force, the sliding block displacement, the driving current, the driving voltage and the effective supervision and the management of the motor temperature rise are realized.
FIG. 1 shows a process flow diagram of a data analysis module for extracting the operating state influence characteristics of a numerical control electric screw press by using a random forest machine learning model, which comprises the following steps:
step S1, data preprocessing: the data preprocessing module respectively acquires different subsets from the acquired running state evaluation index data set, the safety state evaluation index data set and the energy efficiency evaluation index data set, and performs data cleaning, missing value filling and data standardization on the data of the subsets;
step S2, constructing a random forest model: the modeling module uses the preprocessed equipment data to construct a classification model by utilizing a random forest algorithm, adjusts parameters of the random forest model, wherein the parameters of the random forest model comprise the number of trees and the depth of the trees, and judges the running state and abnormal condition of the equipment;
step S3, calculating feature importance: calculating the importance of the features by using a random forest algorithm, and judging the influence degree of each feature on a target variable by using a base index;
step S4, feature selection: selecting features with larger influence on a target variable according to an importance sorting result, and preprocessing the features by using a feature screening method, a feature transformation method and a feature combination method, wherein the feature screening method adopts a correlation coefficient analysis method to select features related to fault prediction, the feature transformation method comprises feature standardization and normalization, the feature combination method is to construct a feature set by a feature intersection method, remove redundancy and noise features, and perform feature selection by using a recursive feature elimination method;
step S5, model verification and adjustment: and verifying the validity of the selected features by using a cross verification method, evaluating and optimizing the constructed random forest model, randomly selecting a plurality of super-parameter combinations in a preset super-parameter space for searching, and obtaining the optimal super-parameter combinations.
Specifically, the detailed process of each step of the invention is as follows:
step S1:
the invention firstly carries out data preprocessing: the data preprocessing module respectively acquires different subsets from the acquired running state evaluation index data set, the safety state evaluation index data set and the energy efficiency evaluation index data set, and performs data cleaning, missing value filling and data standardization on the data of the subsets.
It should be noted that, the preprocessing of the data can remove the missing value, the repeated value and the abnormal value in the data set, retain the effective data, select the adapted data according to the evaluation index and the evaluation requirement, reject the irrelevant data, normalize the data and carry out the dimensionality removal processing to the data, and facilitate the training and comparison of the model.
Step S2:
the invention reconstructs a random forest model: the modeling module uses the preprocessed equipment data to construct a classification model by utilizing a random forest algorithm, adjusts parameters of the random forest model, wherein the parameters of the random forest model comprise the number of trees and the depth of the trees, and judges the running state and abnormal condition of the equipment.
It should be noted that, as an integrated learning algorithm, the random forest algorithm can obtain a good prediction effect when the obtained data sets with three state evaluation indexes in a large scale are processed, and can be combined with the data of the data acquisition module and the prediction module to predict the safety condition and the fault state of the numerical control electric screw press in real time.
Step S3:
the invention further calculates feature importance: and calculating the importance of the features by using a random forest algorithm, and judging the influence degree of each feature on the target variable by using the base index.
It is pointed out that the base index of each feature is obtained by using a base index algorithm, the importance score of each feature is obtained, and then the ranking of the feature importance is realized, so that the key feature with the greatest influence on the safety of the numerical control electric screw press is accurately determined, and the calculation performance and accuracy of a random forest model are improved by sieving the selected optimal feature, so that the risk assessment and prediction of the numerical control electric screw press are better carried out.
Step S4:
in step S4, mainly the sign selection: according to the importance sorting result, selecting features with larger influence on the target variable, and preprocessing the features by using feature screening, feature transformation and feature combination modes, wherein the feature screening adopts a correlation coefficient analysis method to select features related to fault prediction, the feature transformation comprises feature standardization and normalization, the feature combination is to construct a feature set by a feature intersection method, remove redundancy and noise features, and perform feature selection by using a recursive feature elimination method.
It should be noted that the significance of feature selection in the safety supervision system of the numerical control electric screw press is mainly represented in the following aspects:
(1) High model efficiency: the safety supervision system of the numerical control electric screw press needs to monitor a large amount of equipment data in real time, and can predict and diagnose the abnormal condition of the equipment. By selecting the features, the most representative features can be screened out, the calculated amount of the model is reduced, and the model efficiency and response speed are improved.
(2) The accuracy and generalization capability of the model are improved: the safety supervision system of the numerical control electric screw press needs to predict and diagnose various types of equipment abnormal conditions, so that a model with better generalization capability needs to be constructed. Through feature selection, interference of redundant features is reduced, and accuracy and generalization capability of the model are improved.
(3) The modeling cost is reduced: a large amount of equipment data needs to be collected and processed in a safety supervision system of the numerical control electric screw press, and the characteristic selection reduces the cost of data collection and processing, and simultaneously reduces the time cost of modeling.
In summary, the technical problem of feature selection is solved by applying the random forest algorithm, the accuracy and efficiency of feature selection are improved more effectively, the random error and noise interference can be reduced by integrating the results of a plurality of decision trees, the feature importance ranking can be provided, the most representative features can be screened accurately, and the accuracy and generalization capability of the model are improved.
Step S5
In step S5, the model verification and adjustment are mainly: and verifying the validity of the selected features by using a cross verification method, evaluating and optimizing the constructed random forest model, randomly selecting a plurality of super-parameter combinations in a preset super-parameter space for searching, and obtaining the optimal super-parameter combinations.
The random forest model after verification and optimization adjustment is combined with the acquired data of the data acquisition module, real-time analysis of the monitoring big data of the numerical control electric screw press can be realized, the use condition of the numerical control electric screw press is helped to be known, potential problems are found, the production efficiency and the product quality are improved, the management level of the numerical control electric screw press is improved, the supervision and the inspection of equipment are enhanced, and the standardization and the scientization of the management of the numerical control electric screw press are facilitated.
Example 2
Embodiment 2 of the present invention differs from embodiment 1 in that this embodiment is presented with a safety supervision system for a digitally controlled electric screw press.
Fig. 2 shows a schematic structural diagram of a safety supervision system for a digital control electric screw press, which comprises a processor, a data acquisition module, a data storage module, a data analysis module and a data display module which are in communication connection with the processor, wherein the data analysis module comprises a data preprocessing module, a parameter evaluation module, a modeling module and a prediction module, the parameter evaluation module constructs an equipment operation state evaluation index, a safety state evaluation index and an energy efficiency evaluation index through data of temperature, pressure, flow, vibration, current and voltage of the digital control electric screw press after data cleaning, and the parameter evaluation module is respectively used for evaluating the operation state, the safety state and the energy efficiency information of the equipment, and comprehensively evaluates the state of the equipment through the weighted sum of the equipment operation state evaluation index, the safety state evaluation index and the energy efficiency evaluation index, and the comprehensive evaluation formula is as follows:
；
wherein:for comprehensive evaluation index->For the evaluation of the operating state, ∈>For the safety state evaluation index, < >>Is an energy efficiency evaluation index, which is->、/>And +.>The influence weights of the operation state evaluation index, the safety state evaluation index and the energy efficiency evaluation index are set individually according to the type of the numerical control electric screw press and the attribute of the parameter emphasis, so that the requirements of ≡>、/>And +.>All are->Constant between->；
The parameter evaluation index obtains the data of the comprehensive evaluation index through a comprehensive evaluation formula, a sample data set is created by utilizing the data of the comprehensive evaluation index, the mean value and the standard deviation of the sample data set are calculated, the data in the sample data set are standardized by utilizing the mean value and the standard deviation, and the standardization formula is as follows:
；
wherein:is the standard value of the comprehensive evaluation index, and is->For the mean value of the sample dataset, +.>Variance for the sample dataset;
substituting the standard value of the comprehensive evaluation index as an independent variable into a functionUsing function valuesAnd carrying out two classifications on the comprehensive evaluation indexes to realize classification evaluation of the comprehensive indexes.
In the parameter evaluation module, the operation state evaluation index of the numerical control electric screw press is positively correlated with the monitoring values of effective energy, striking force, sliding block speed and sliding block displacement, and the operation state evaluation index formula of the numerical control electric screw press is as follows:
；
wherein:for the effective energy monitoring value of a numerical control electric screw press,/->Is the striking force monitoring value of the numerical control electric screw press, < ->For the slide speed monitoring value of the numerical control electric screw press, < >>Is numerical controlThe basic value of the sliding block speed of the electric screw press is the initial striking speed in the descending return stroke of the sliding block,/-for the sliding block>Is a sliding block displacement monitoring value of the numerical control electric screw press.
In the parameter evaluation module, the safety state evaluation index of the numerical control electric screw press is positively correlated with the driving current, positively correlated with the driving voltage and positively correlated with the motor temperature rise, and the formula of the safety state evaluation index is as follows:
；
wherein:for the gas concentration monitoring value, +.>For the initial gas concentration value, < > is empirically set according to the type of gas used in the numerical control electric screw press>For the gas temperature monitoring value of the gas cylinder, +.>Is the pressure monitoring value of the gas cylinder.
In the parameter evaluation module, the energy efficiency evaluation index of the numerical control electric screw press is positively correlated with the actual displacement of the sliding block, and is positively correlated with the actual striking energy, and the formula of the energy efficiency evaluation index is as follows:
；
wherein:for the actual slide displacement monitoring value, < >>Is the actual striking energy monitoring value.
In the parameter evaluation module, the classification mechanism of the comprehensive evaluation index is that,
when (when)When the comprehensive evaluation index is classified as a first level;
when (when)And when the comprehensive evaluation indexes are classified into a second level, the evaluation state of the first level is smaller than that of the second level.
The processor is used for processing data from at least one component of a safety supervision system for the numerical control electric screw press;
the data acquisition module is used for acquiring monitoring data of the numerical control electric screw press, sending the acquired monitoring data to the data analysis module for analysis and processing, and sending the acquired monitoring data to the data storage module for storage;
the data storage module is used for storing the acquired data on a plurality of nodes by using a distributed storage technology through the data generated by acquisition, preprocessing, evaluation, modeling and prediction;
the data display module is used for displaying the processed data in the form of a chart and providing a function of managing remote control and maintenance record management of the numerical control electric screw press.
After the data analysis module receives the information sent by the data acquisition module, the data stored in the data storage module is called by the processor to analyze and process the running state of the numerical control electric screw press, different state evaluation indexes and comprehensive evaluation indexes are obtained, the comprehensive indexes are evaluated in a grading manner, evaluation levels are sent to the data storage module and the data display module, meanwhile, different state evaluation indexes are sent to the modeling module and the prediction module, an original data set is built through evaluation index values of three different states, the original data set is divided into a plurality of different subsets, a decision tree is built for each subset, a random forest model is obtained through integrating all the decision trees, the characteristic with the largest influence on the running state of the numerical control electric screw press is extracted, abnormal data is identified, the alarm is given in time, the fault risk and the safety risk of the numerical control electric screw press are judged, the safety state and the fault state of the numerical control electric screw press are comprehensively analyzed and predicted, and the mutual influence and the cross relation among the evaluation indexes of the different states are judged.
The above formulas are all formulas with dimensionality removed and numerical calculation, the formulas are formulas with the latest real situation obtained by software simulation through collecting a large amount of data, and preset parameters and threshold selection in the formulas are set by those skilled in the art according to the actual situation.
The foregoing is merely specific embodiments of the present application, but the scope of the present application is not limited thereto, and any person skilled in the art can easily think about changes or substitutions within the technical scope of the present application, and the changes and substitutions are intended to be covered by the scope of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.
Finally: the foregoing description of the preferred embodiments of the invention is not intended to limit the invention to the precise form disclosed, and any such modifications, equivalents, and alternatives falling within the spirit and principles of the invention are intended to be included within the scope of the invention.
Claims (8)
1. The safety supervision system for the numerical control electric screw press is characterized by comprising a processor, a data acquisition module, a data storage module, a data analysis module and a data display module which are in communication connection with the processor, wherein the data analysis module comprises a data preprocessing module, a parameter evaluation module, a modeling module and a prediction module, the parameter evaluation module constructs an equipment operation state evaluation index, a safety state evaluation index and an energy efficiency evaluation index through data of temperature, pressure, flow, vibration, current and voltage of the numerical control electric screw press after data cleaning, the parameter evaluation module is respectively used for evaluating the operation state, the safety state and the energy efficiency information of the equipment, and the state of the equipment is comprehensively evaluated through the weighted sum of the equipment operation state evaluation index, the safety state evaluation index and the energy efficiency evaluation index, and the comprehensive evaluation formula is as follows:
；
wherein:for comprehensive evaluation index->For the evaluation of the operating state, ∈>For the safety state evaluation index, < >>Is an energy efficiency evaluation index, which is->、/>And +.>The influence weights of the operation state evaluation index, the safety state evaluation index and the energy efficiency evaluation index are set individually according to the type of the numerical control electric screw press and the attribute of the parameter emphasis, so that the requirements of ≡>、/>And +.>All are->Constant between->；
The parameter evaluation index obtains the data of the comprehensive evaluation index through a comprehensive evaluation formula, a sample data set is created by utilizing the data of the comprehensive evaluation index, the mean value and the standard deviation of the sample data set are calculated, the data in the sample data set are standardized by utilizing the mean value and the standard deviation, and the standardization formula is as follows:
；
wherein:is the standard value of the comprehensive evaluation index, and is->For the mean value of the sample dataset, +.>Variance for the sample dataset;
substituting the standard value of the comprehensive evaluation index as an independent variable into a functionUtilize function value->And carrying out two classifications on the comprehensive evaluation indexes to realize classification evaluation of the comprehensive indexes.
2. A safety supervision system for a digitally controlled electric screw press according to claim 1, wherein: in the parameter evaluation module, the operation state evaluation index of the numerical control electric screw press is positively correlated with the monitoring values of effective energy, striking force, sliding block speed and sliding block displacement, and the operation state evaluation index formula of the numerical control electric screw press is as follows:
；
wherein:for the effective energy monitoring value of a numerical control electric screw press,/->Is the striking force monitoring value of the numerical control electric screw press, < ->For the slide speed monitoring value of the numerical control electric screw press, < >>Is the basic value of the speed of the sliding block of the numerical control electric screw press, is the initial striking speed in the descending return stroke of the sliding block, is +.>Is a sliding block displacement monitoring value of the numerical control electric screw press.
3. A safety supervision system for a digitally controlled electric screw press according to claim 1, wherein: in the parameter evaluation module, the safety state evaluation index of the numerical control electric screw press is positively correlated with the driving current, positively correlated with the driving voltage and positively correlated with the motor temperature rise, and the formula of the safety state evaluation index is as follows:
；
wherein:for the gas concentration monitoring value, +.>For the initial gas concentration value, < > is empirically set according to the type of gas used in the numerical control electric screw press>For the gas temperature monitoring value of the gas cylinder, +.>Is the pressure monitoring value of the gas cylinder.
4. A safety supervision system for a digitally controlled electric screw press according to claim 1, wherein: in the parameter evaluation module, the energy efficiency evaluation index of the numerical control electric screw press is positively correlated with the actual displacement of the sliding block, and is positively correlated with the actual striking energy, and the formula of the energy efficiency evaluation index is as follows:
；
wherein:for the actual slide displacement monitoring value, < >>Is the actual striking energy monitoring value.
5. A safety supervision system for a digitally controlled electric screw press according to claim 1, wherein: in the parameter evaluation module, the classification mechanism of the comprehensive evaluation index is that,
when (when)When the comprehensive evaluation index is classified as a first level;
when (when)And when the comprehensive evaluation indexes are classified into a second level, the evaluation state of the first level is smaller than that of the second level.
6. A safety supervision system for a digitally controlled electric screw press according to claim 1, wherein:
the processor is used for processing data from at least one component of a safety supervision system for the numerical control electric screw press;
the data acquisition module is used for acquiring monitoring data of the numerical control electric screw press, sending the acquired monitoring data to the data analysis module for analysis and processing, and sending the acquired monitoring data to the data storage module for storage;
the data storage module is used for storing the acquired data on a plurality of nodes by using a distributed storage technology through the data generated by acquisition, preprocessing, evaluation, modeling and prediction;
the data display module is used for displaying the processed data in the form of a chart and providing a function of managing remote control and maintenance record management of the numerical control electric screw press.
7. A safety supervision system for a digitally controlled electric screw press according to claim 1, wherein: after the data analysis module receives the information sent by the data acquisition module, the data stored in the data storage module is called by the processor to analyze and process the running state of the numerical control electric screw press, different state evaluation indexes and comprehensive evaluation indexes are obtained, the comprehensive indexes are evaluated in a grading manner, evaluation levels are sent to the data storage module and the data display module, meanwhile, different state evaluation indexes are sent to the modeling module and the prediction module, an original data set is built through evaluation index values of three different states, the original data set is divided into a plurality of different subsets, a decision tree is built for each subset, a random forest model is obtained through integrating all the decision trees, the characteristic with the largest influence on the running state of the numerical control electric screw press is extracted, abnormal data is identified, the alarm is given in time, the fault risk and the safety risk of the numerical control electric screw press are judged, the safety state and the fault state of the numerical control electric screw press are comprehensively analyzed and predicted, and the mutual influence and the cross relation among the evaluation indexes of the different states are judged.
8. A safety supervision system for a digitally controlled electric screw press according to claim 7, wherein: the process of extracting the operating state influence characteristics of the numerical control electric screw press by the data analysis module through the random forest machine learning model comprises the following steps,
step S1, data preprocessing: the data preprocessing module respectively acquires different subsets from the acquired running state evaluation index data set, the safety state evaluation index data set and the energy efficiency evaluation index data set, and performs data cleaning, missing value filling and data standardization on the data of the subsets;
step S2, constructing a random forest model: the modeling module uses the preprocessed equipment data to construct a classification model by utilizing a random forest algorithm, adjusts parameters of the random forest model, wherein the parameters of the random forest model comprise the number of trees and the depth of the trees, and judges the running state and abnormal condition of the equipment;
step S3, calculating feature importance: calculating the importance of the features by using a random forest algorithm, and judging the influence degree of each feature on a target variable by using a base index;
step S4, feature selection: selecting features influencing a target variable according to an importance sorting result, and preprocessing the features by using a feature screening method, a feature transformation method and a feature combination method, wherein the feature screening method adopts a correlation coefficient analysis method to select features related to fault prediction, the feature transformation method comprises feature standardization and normalization, the feature combination method is used for constructing a feature set by a feature intersection method, eliminating redundancy and noise features, and performing feature selection by using a recursive feature elimination method;
step S5, model verification and adjustment: and verifying the validity of the selected features by using a cross verification method, evaluating and optimizing the constructed random forest model, randomly selecting a plurality of super-parameter combinations in a preset super-parameter space for searching, and obtaining the super-parameter combinations.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310775936.0A CN116502155B (en) | 2023-06-28 | 2023-06-28 | Safety supervision system for numerical control electric screw press |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310775936.0A CN116502155B (en) | 2023-06-28 | 2023-06-28 | Safety supervision system for numerical control electric screw press |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116502155A true CN116502155A (en) | 2023-07-28 |
| CN116502155B CN116502155B (en) | 2023-09-19 |
Family
ID=87321701
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310775936.0A Active CN116502155B (en) | 2023-06-28 | 2023-06-28 | Safety supervision system for numerical control electric screw press |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116502155B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117341261A (en) * | 2023-12-04 | 2024-01-05 | 淄博诚拓机械有限公司 | Intelligent control method and system for servo direct-drive screw press |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20190005400A1 (en) * | 2016-09-20 | 2019-01-03 | Southwest Petroleum University | A fuzzy evaluation and prediction method for running status of mechanical equipment with occurrence probability of failure modes |
| CN109241601A (en) * | 2018-08-28 | 2019-01-18 | 大连理工大学 | A kind of numerically-controlled machine tool comprehensive performance evaluation method based on modified scatter degree |
| CN110288200A (en) * | 2019-05-29 | 2019-09-27 | 同济大学 | A kind of harmful influence transportation safety risk prevention system system and method |
| WO2020041955A1 (en) * | 2018-08-28 | 2020-03-05 | 大连理工大学 | Method for evaluating comprehensive performance of numerical control machine tool based on improved pull-apart grade method |
| US20200184131A1 (en) * | 2018-06-27 | 2020-06-11 | Dalian University Of Technology | A method for prediction of key performance parameter of an aero-engine transition state acceleration process based on space reconstruction |
| CN111401749A (en) * | 2020-03-17 | 2020-07-10 | 三峡大学 | Dynamic safety assessment method based on random forest and extreme learning regression |
| CN113837578A (en) * | 2021-09-15 | 2021-12-24 | 江苏兴力工程管理有限公司 | Gridding supervision and management evaluation method for power supervision enterprise |
| CN115475904A (en) * | 2022-09-14 | 2022-12-16 | 常州机电职业技术学院 | Forging hydraulic press fault prediction and health management device and working method |
| CN116187725A (en) * | 2023-04-27 | 2023-05-30 | 武汉新威奇科技有限公司 | Forging equipment management system for forging automatic line |
| CN116296305A (en) * | 2022-11-28 | 2023-06-23 | 江苏亚威机床股份有限公司 | Method for diagnosing rear material blocking part of bending machine with online fault self-diagnosis function |
-
2023
- 2023-06-28 CN CN202310775936.0A patent/CN116502155B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20190005400A1 (en) * | 2016-09-20 | 2019-01-03 | Southwest Petroleum University | A fuzzy evaluation and prediction method for running status of mechanical equipment with occurrence probability of failure modes |
| US20200184131A1 (en) * | 2018-06-27 | 2020-06-11 | Dalian University Of Technology | A method for prediction of key performance parameter of an aero-engine transition state acceleration process based on space reconstruction |
| CN109241601A (en) * | 2018-08-28 | 2019-01-18 | 大连理工大学 | A kind of numerically-controlled machine tool comprehensive performance evaluation method based on modified scatter degree |
| WO2020041955A1 (en) * | 2018-08-28 | 2020-03-05 | 大连理工大学 | Method for evaluating comprehensive performance of numerical control machine tool based on improved pull-apart grade method |
| CN110288200A (en) * | 2019-05-29 | 2019-09-27 | 同济大学 | A kind of harmful influence transportation safety risk prevention system system and method |
| CN111401749A (en) * | 2020-03-17 | 2020-07-10 | 三峡大学 | Dynamic safety assessment method based on random forest and extreme learning regression |
| CN113837578A (en) * | 2021-09-15 | 2021-12-24 | 江苏兴力工程管理有限公司 | Gridding supervision and management evaluation method for power supervision enterprise |
| CN115475904A (en) * | 2022-09-14 | 2022-12-16 | 常州机电职业技术学院 | Forging hydraulic press fault prediction and health management device and working method |
| CN116296305A (en) * | 2022-11-28 | 2023-06-23 | 江苏亚威机床股份有限公司 | Method for diagnosing rear material blocking part of bending machine with online fault self-diagnosis function |
| CN116187725A (en) * | 2023-04-27 | 2023-05-30 | 武汉新威奇科技有限公司 | Forging equipment management system for forging automatic line |
Non-Patent Citations (3)
| Title |
|---|
| 余俊等: "考虑不确定性的机枪作战效能综合评估方法", 兵工学报, no. 10 * |
| 张根保等: "数控机床可靠性试验中关键功能部件的提取研究", 中国机械工程, no. 17 * |
| 文妍等: "基于多分类器融合与模糊综合评判的滚动轴承故障诊断", 中国科技论文, no. 04 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117341261A (en) * | 2023-12-04 | 2024-01-05 | 淄博诚拓机械有限公司 | Intelligent control method and system for servo direct-drive screw press |
| CN117341261B (en) * | 2023-12-04 | 2024-02-23 | 淄博诚拓机械有限公司 | Intelligent control method and system for servo direct-drive screw press |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116502155B (en) | 2023-09-19 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112254964A (en) | Rolling bearing fault diagnosis method based on rapid multi-scale convolution neural network | |
| CN113807570B (en) | XGBoost-based reservoir dam risk level assessment method and system | |
| CN111259947A (en) | Power system fault early warning method and system based on multi-mode learning | |
| CN116502155B (en) | Safety supervision system for numerical control electric screw press | |
| CN112039903B (en) | Network security situation assessment method based on deep self-coding neural network model | |
| CN115409131B (en) | Production line abnormity detection method based on SPC process control system | |
| CN113866642A (en) | Lithium ion battery fault diagnosis method based on gradient lifting tree | |
| CN116148679A (en) | Battery health state prediction method and related device | |
| CN113688558A (en) | Automobile driving condition construction method and system based on large database samples | |
| CN116227745B (en) | Big data-based research and analysis method and system for fishing vessels | |
| CN115935286A (en) | Abnormal point detection method, device and terminal for railway bearing state monitoring data | |
| CN115099149A (en) | Result prediction method based on multiple feature comparison and random forest algorithm | |
| CN113255591A (en) | Bearing fault diagnosis method based on random forest and fusion characteristics | |
| CN114416707A (en) | Method and device for automated feature engineering of industrial time series data | |
| CN117131425B (en) | Numerical control machine tool processing state monitoring method and system based on feedback data | |
| CN117782198B (en) | Highway electromechanical equipment operation monitoring method and system based on cloud edge architecture | |
| CN116738214B (en) | Data dimension reduction preprocessing method based on high-order tensor | |
| CN113112067A (en) | Method for establishing TFRI weight calculation model | |
| CN115729761B (en) | Hard disk fault prediction method, system, equipment and medium | |
| CN114580472B (en) | Large-scale equipment fault prediction method with repeated cause and effect and attention in industrial internet | |
| CN116030955A (en) | Medical equipment state monitoring method and related device based on Internet of things | |
| CN114239759B (en) | Fault diagnosis method and device for electric vehicle, electronic equipment and storage medium | |
| CN108763728A (en) | Mechanical failure diagnostic method based on the extraction of parallel connection type deep neural network layered characteristic | |
| CN114266401B (en) | Chassis engine fault prediction method and system | |
| CN118014373B (en) | Risk identification model based on data quality monitoring and construction method thereof |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |