CN117057432B - Method and system applied to workpiece temperature impact test - Google Patents
Method and system applied to workpiece temperature impact test Download PDFInfo
- Publication number
- CN117057432B CN117057432B CN202311117456.1A CN202311117456A CN117057432B CN 117057432 B CN117057432 B CN 117057432B CN 202311117456 A CN202311117456 A CN 202311117456A CN 117057432 B CN117057432 B CN 117057432B
- Authority
- CN
- China
- Prior art keywords
- historical
- temperature
- detection
- detection frequency
- 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.)
- Active
Links
- 238000009863 impact test Methods 0.000 title claims abstract description 78
- 238000000034 method Methods 0.000 title claims abstract description 56
- 238000001514 detection method Methods 0.000 claims abstract description 217
- 230000008859 change Effects 0.000 claims abstract description 110
- 238000003062 neural network model Methods 0.000 claims abstract description 18
- 210000002569 neuron Anatomy 0.000 claims description 70
- 238000012545 processing Methods 0.000 claims description 23
- 238000004590 computer program Methods 0.000 claims description 10
- 230000002159 abnormal effect Effects 0.000 claims description 8
- 230000005856 abnormality Effects 0.000 claims description 8
- 238000000605 extraction Methods 0.000 claims description 3
- 238000011156 evaluation Methods 0.000 abstract description 11
- 238000012360 testing method Methods 0.000 description 15
- 239000011159 matrix material Substances 0.000 description 12
- 239000013598 vector Substances 0.000 description 11
- 230000000694 effects Effects 0.000 description 7
- 230000008569 process Effects 0.000 description 6
- 238000010586 diagram Methods 0.000 description 4
- 238000005070 sampling Methods 0.000 description 4
- 230000009286 beneficial effect Effects 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 238000010438 heat treatment Methods 0.000 description 2
- 230000001360 synchronised effect Effects 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 238000001816 cooling Methods 0.000 description 1
- 238000013075 data extraction Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000001537 neural effect Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 238000011897 real-time detection Methods 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012800 visualization Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N7/00—Computing arrangements based on specific mathematical models
- G06N7/02—Computing arrangements based on specific mathematical models using fuzzy logic
- G06N7/026—Development tools for entering the parameters of a fuzzy system
-
- 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
- Engineering & Computer Science (AREA)
- Software Systems (AREA)
- Physics & Mathematics (AREA)
- Automation & Control Theory (AREA)
- Fuzzy Systems (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Computational Mathematics (AREA)
- Mathematical Analysis (AREA)
- General Health & Medical Sciences (AREA)
- Algebra (AREA)
- Artificial Intelligence (AREA)
- Biomedical Technology (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Life Sciences & Earth Sciences (AREA)
- Molecular Biology (AREA)
- Mathematical Optimization (AREA)
- Pure & Applied Mathematics (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Health & Medical Sciences (AREA)
- Testing Of Devices, Machine Parts, Or Other Structures Thereof (AREA)
Abstract
The application belongs to the technical field of temperature impact tests, and discloses a method and a system applied to a workpiece temperature impact test, wherein the method comprises the following steps: identifying the model of the input workpiece; based on the model of the input workpiece, acquiring historical temperature impact test data, and extracting historical characteristic parameters of the historical temperature impact test data; the historical characteristic parameters are weighted and then input into a preset neural network model, and a temperature change trend is predicted and obtained; setting a dynamic threshold of the detection frequency based on the temperature change trend and a preset parameter standard library; inputting a detection frequency dynamic threshold and historical characteristic parameters into a preset fuzzy control model, and setting an actual detection frequency; compared with the prior art, the method provided by the application has the advantages that the detection frequency can be adaptively set according to the model of the workpiece, and the accuracy of the evaluation result of the temperature impact test is improved.
Description
Technical Field
The application belongs to the technical field of temperature impact tests, and particularly relates to a method and a system applied to a workpiece temperature impact test.
Background
The temperature impact test method is widely applied to evaluate the endurance and reliability of various workpieces in high and low temperature environments; the method can simulate the instant temperature difference of the workpiece under the condition of rapid temperature change, evaluate the physical, mechanical, electrical and other performance performances of the workpiece in the temperature change process, and is helpful for guiding the improvement and optimization of the workpiece and improving the performance and reliability of the workpiece.
The existing temperature impact test is limited by preset parameters of operators, the detection frequency of each workpiece temperature impact test is constant, and when the temperature of temperature impact test equipment rapidly suddenly changes, the temperature change and potential problems (such as material breakage, conductivity reduction and the like) existing in the workpiece are difficult to accurately capture, so that the test evaluation result is inaccurate.
Disclosure of Invention
The application provides a method and a system applied to a workpiece temperature impact test, which are used for improving the accuracy of a temperature impact test evaluation result.
The first technical scheme adopted by the application is as follows:
A method for use in a workpiece temperature impact test, comprising:
Identifying the model of the input workpiece;
Based on the model of the input workpiece, acquiring historical temperature impact test data, and extracting historical characteristic parameters of the historical temperature impact test data;
the historical characteristic parameters are weighted and then input into a preset neural network model, and a temperature change trend is predicted and obtained;
Setting a detection frequency dynamic threshold based on the temperature change trend and a preset parameter standard library;
And inputting the detection frequency dynamic threshold and the historical characteristic parameters into a preset fuzzy control model, and setting actual detection frequency.
According to the technical scheme, the workpiece model is firstly identified, historical temperature impact test data are obtained according to the workpiece model, historical characteristic parameters are extracted from the workpiece model, the historical characteristic parameters are input into a preset neural network model after being weighted, the temperature change trend is predicted to be obtained, the detection frequency dynamic threshold is set according to the temperature change trend and a preset parameter standard library, and finally the detection frequency dynamic threshold and the historical parameters are input into a preset fuzzy control model to adaptively set the actual detection frequency; compared with the prior art, the method provided by the application has the advantages that the temperature change trend can be predicted according to the model of the workpiece, the dynamic threshold of the detection frequency is set as the limit range of the actual detection frequency according to the temperature change trend and the parameter standard library, and the detection frequency is adaptively set according to the property of the historical characteristic parameter through the fuzzy control model, so that the possibility that the temperature change and the potential problem of the workpiece are difficult to accurately capture when the temperature of the temperature impact test equipment rapidly suddenly changes due to the constant detection frequency is reduced, and the accuracy of the evaluation result of the temperature impact test is further improved.
The application is further provided with: the historical characteristic parameters comprise historical workpiece records, historical storage occupancy rates, historical detection time and historical temperature change parameters; the preset neural network model comprises a first neuron, a second neuron, a third neuron, a fourth neuron and a BP network; the step of inputting the weighted historical characteristic parameters into a preset neural network model, and the step of predicting the temperature change trend comprises the following steps:
the historical workpiece records are input into the first neuron after being weighted;
The historical storage occupancy rate is weighted and then input into the second neuron;
Weighting the history detection time and inputting the weighted history detection time into the third neuron;
weighting the historical temperature change parameters and inputting the weighted historical temperature change parameters into the fourth neuron;
based on the BP network, acquiring and processing the data in the first neuron, the second neuron, the third neuron and the fourth neuron, and predicting to obtain a temperature change trend.
Through the technical scheme, the first neuron is used for receiving the matrix vector of the historical workpiece record after the weighting treatment and converting the historical workpiece record (in the form of characters and the like) into the quantifiable associated data representation; the second neuron is used for receiving the matrix vector of which the historical storage occupancy rate is subjected to weighting processing; the third neuron is used for receiving the matrix vector of which the historical detection time is subjected to weighting processing; the fourth neuron is used for receiving the matrix vector of the historical temperature change parameter after weighting; the BP network normalizes the matrix vectors of each neuron, and finally predicts the temperature change trend of the corresponding workpiece model; compared with the prior art, when the testers input different types of workpieces, the method disclosed by the application can be adapted to the temperature change trend of the corresponding workpiece, so as to assist the testers in predicting the effect of the temperature impact test.
The application is further provided with: the detection frequency dynamic threshold value comprises a constant temperature detection dynamic threshold value and a variable temperature detection dynamic threshold value, and the setting of the detection frequency dynamic threshold value based on the temperature change trend and a preset parameter standard library comprises the following steps:
based on the temperature change trend, a constant temperature trend and a variable temperature trend are obtained;
Setting a standard detection frequency interval based on a preset parameter standard library;
Setting the constant temperature detection dynamic threshold based on the constant temperature trend and the standard detection frequency interval;
and setting the dynamic threshold of temperature change detection based on the temperature change trend and the standard detection frequency interval.
By the technical scheme, when the workpiece is tested in a constant temperature state, the probability of potential problems of the workpiece is much smaller than that of the workpiece in a variable temperature state, and the detection requirement can be met by adopting lower detection frequency; the parameter standard library can be set according to national standard GB2423, and also can be set according to internal technical files, and the parameter standard library is used for limiting the upper limit and the lower limit of detection frequency setting; compared with the prior art, the constant temperature detection dynamic threshold is set through the constant temperature trend and the standard detection frequency interval so as to adapt to the change characteristic of the workpiece under the constant temperature test; and setting a variable temperature detection dynamic threshold value through a variable temperature trend and a standard detection frequency interval so as to adapt to the change characteristic of the workpiece under a variable temperature test.
The application is further provided with: the history characteristic parameters further comprise history detection setting frequency; the actual detection frequency comprises constant temperature detection frequency; inputting the detection frequency dynamic threshold and the historical characteristic parameter into a preset fuzzy control model, and setting the actual detection frequency, wherein the method comprises the following steps:
taking the constant temperature detection dynamic threshold value as a first variable range, and inputting a preset fuzzy control model;
And setting the constant temperature detection frequency based on the first variable range by taking the historical temperature change parameter, the historical detection setting frequency and the historical storage occupancy rate as fuzzy sets.
According to the technical scheme, the constant temperature detection dynamic threshold is used as a first variable range of the fuzzy control model, the historical temperature change parameter, the historical detection setting frequency and the historical storage occupancy rate are used as fuzzy sets, the membership relation of the historical detection setting frequency and the historical storage occupancy rate is used as the fuzzy set, the module control model adaptively sets the constant temperature detection frequency according to the historical detection setting frequency, the historical storage occupancy rate and the first variable range, so that the detection frequency is reduced as much as possible on the premise of meeting detection requirements, the data processing capacity of temperature impact test equipment is reduced, the flash memory occupied by data is reduced, and more abundant equipment resources are reserved for the temperature change test process.
The application is further provided with: the actual detection frequency comprises a variable temperature detection frequency; inputting the detection frequency dynamic threshold and the historical characteristic parameter into a preset fuzzy control model, and setting the actual detection frequency, wherein the method comprises the following steps:
Taking the temperature change detection dynamic threshold value as a second variable range, and inputting a preset fuzzy control model;
And setting the temperature change detection frequency based on the fuzzy set and the second variable range.
According to the technical scheme, the variable temperature detection dynamic threshold is used as the second variable range, and the variable temperature detection frequency is set based on the fuzzy set and the second variable range, so that the detection frequency is increased as much as possible on the premise that equipment resources and standard detection frequency intervals are allowed, and the accuracy of the temperature impact test evaluation result is improved.
The application is further provided with: after the dynamic threshold value of the detection frequency and the historical characteristic parameter are input into a preset fuzzy control model, setting the actual detection frequency, the method further comprises the following steps:
based on the actual detection frequency, acquiring abnormal detection information of the workpiece;
And if the abnormality detection information exceeds a preset alarm threshold value, an abnormality early warning is sent out.
Through the technical scheme, after the actual detection frequency is set, the abnormal detection information of the workpiece is obtained so as to realize real-time detection of potential problems of the workpiece, and when the abnormal detection information exceeds the preset alarm threshold value, an abnormal early warning is sent out so as to prompt the test personnel that the workpiece is seriously damaged in the process of the sample, so that the test personnel can be assisted in evaluating the quality of the workpiece.
The second object of the application is realized by the following technical scheme:
A system for workpiece temperature impact test, the system being applied to a method for workpiece temperature impact test, the system comprising:
The identification module is used for identifying the model of the input workpiece;
the characteristic parameter extraction module is used for acquiring historical temperature impact test data based on the model of the input workpiece and extracting historical characteristic parameters of the historical temperature impact test data;
the prediction module is used for inputting the weighted historical characteristic parameters into a preset neural network model and predicting to obtain a temperature change trend;
The dynamic threshold setting module is used for setting a dynamic threshold of the detection frequency based on the temperature change trend and a preset parameter standard library;
The actual frequency setting module is used for inputting the dynamic threshold value of the detection frequency and the historical characteristic parameter into a preset fuzzy control model and setting the actual detection frequency.
The application is further provided with: the prediction module includes:
the first processing submodule is used for inputting the historical workpiece record into the first neuron after weighting treatment;
The second processing submodule is used for inputting the weighted historical storage occupancy rate into the second neuron;
a third processing sub-module, configured to input the weighted history detection time to the third neuron;
a fourth processing sub-module, configured to input the weighted historical temperature change parameter into the fourth neuron;
And the prediction sub-module is used for acquiring and processing the data in the first neuron, the second neuron, the third neuron and the fourth neuron based on the BP network, and predicting to obtain a temperature change trend.
The third object of the application is realized by the following technical scheme:
a computer device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, the processor executing the computer program to perform a method as described above for use in a workpiece temperature impact test.
The fourth object of the application is realized by the following technical scheme:
a computer readable storage medium storing a computer program which when executed by a processor implements a method as described above for use in a workpiece temperature impact test.
In summary, the present application includes at least one of the following beneficial technical effects:
1. Compared with the prior art, the method provided by the application has the advantages that the temperature change trend can be predicted according to the model of the workpiece, the dynamic threshold of the detection frequency is set as the limit range of the actual detection frequency according to the temperature change trend and the parameter standard library, and the detection frequency is adaptively set according to the property of the historical characteristic parameter through the fuzzy control model, so that the possibility that the temperature change and the potential problem of the workpiece are difficult to accurately capture when the temperature of the temperature impact test equipment rapidly suddenly changes due to the constant detection frequency is reduced, and the accuracy of the test evaluation result is further improved.
2. Compared with the prior art, when the testers input different types of workpieces, the method disclosed by the application can be adapted to the temperature change trend of the corresponding workpiece, so as to assist the testers in predicting the effect of the temperature impact test.
3. Compared with the prior art, the variable temperature detection dynamic threshold is used as the second variable range, and the variable temperature detection frequency is set based on the fuzzy set and the second variable range, so that the detection frequency is increased as much as possible on the premise that equipment resources and standard detection frequency intervals are allowed, and the accuracy of test evaluation results is improved.
Drawings
FIG. 1 is a flow chart of a method for workpiece temperature impact testing according to a first embodiment of the application;
FIG. 2 is a flowchart of step S30 in a method for workpiece temperature impact test according to a first embodiment of the application;
FIG. 3 is a diagram showing the effect of step S30 in the method for workpiece temperature impact test according to the first embodiment of the application;
FIG. 4 is a flowchart of step S40 in a method for workpiece temperature impact test according to a first embodiment of the application;
FIG. 5 is a diagram showing the effect of step S40 in a method for performing a temperature impact test on a workpiece according to an embodiment of the application;
FIG. 6 is a flowchart of step S50 in a method for workpiece temperature impact test according to a first embodiment of the application;
FIG. 7 is a schematic block diagram of a system for workpiece temperature impact testing in accordance with a second embodiment of the application;
Fig. 8 is a schematic diagram of a computer device in a third embodiment of the application.
Detailed Description
The technical solutions of the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present application, and it is apparent that the described embodiments are some embodiments of the present application, but not all embodiments, and all other embodiments obtained by those skilled in the art without making creative efforts based on the embodiments of the present application are included in the protection scope of the present application.
The embodiment of the application provides a method and a system applied to a workpiece temperature impact test, which are used for improving the accuracy of a temperature impact test evaluation result.
Example 1
As shown in fig. 1, a method for applying to a workpiece temperature impact test according to an embodiment of the present application includes:
S10: and identifying the model of the input workpiece.
In this embodiment, the workpiece to be put into is mainly a part of a new energy automobile, such as a new energy battery, a window, a chassis, etc.; each workpiece is provided with a label code, and the existing workpiece temperature impact test equipment can automatically identify the model of the input workpiece in a code scanning mode; the tester can also manually input the model of the input workpiece.
Specifically, the workpiece temperature impact test equipment automatically identifies the input new energy automobile parts to obtain the input workpiece model.
S20: based on the model of the input workpiece, historical temperature impact test data are acquired, and historical characteristic parameters of the historical temperature impact test data are extracted.
In this embodiment, the conventional workpiece temperature impact test apparatus is generally built with a storage unit to store history data.
Specifically, according to the corresponding historical temperature impact test data of each workpiece model, characteristic parameters of the historical temperature impact test data are extracted.
S30: the historical characteristic parameters are weighted and then input into a preset neural network model, and a temperature change trend is predicted and obtained;
In this embodiment, the neural network model adopts an existing BP neural network model, which can normalize matrix data in a plurality of neural units; wherein, the trend of temperature change can be presented in the form of data flow and can also be presented in the form of map.
Specifically, the historical characteristic parameters are input into a preset neural network model after weighted treatment, and the temperature change trend is predicted so as to facilitate the experimenter to evaluate the heating and cooling characteristics of the workpiece in advance.
As shown in fig. 2 and fig. 3, the historical characteristic parameters include historical workpiece records, historical storage occupancy rates, historical detection time and historical temperature change parameters, and the preset neural network model includes a first neuron, a second neuron, a third neuron, a fourth neuron and a BP network; step S30 of the method of the present application comprises:
S31: the historical workpiece record is weighted and then input into a first neuron;
s32: the historical storage occupancy rate is weighted and then input into a second neuron;
S33: weighting the historical detection time and inputting the weighted historical detection time into a third neuron;
s34: weighting the historical temperature change parameters and inputting the weighted historical temperature change parameters into a fourth neuron;
S35: based on the BP network, acquiring and processing data in the first neuron, the second neuron, the third neuron and the fourth neuron, and predicting to obtain a temperature change trend.
In the embodiment, the historical workpiece record refers to the model of the workpiece which is subjected to the test in the past by the temperature impact test equipment; the historical storage occupancy rate refers to the occupancy rate of the flash memory of the equipment processor when the corresponding workpiece model is input; the historical detection time refers to the time consumption of corresponding workpiece detection when the corresponding workpiece model is input;
the historical temperature change time refers to the corresponding temperature change record within the time elapsed for workpiece detection.
Preferably, the historical workpiece record, the historical storage occupancy rate, the historical detection time and the historical temperature change parameters are extracted in a linked list mode.
The following is a table of the relation among the historical workpiece record, the historical storage occupancy rate, the historical detection time and the historical temperature change parameters of the single type of workpiece:
It should be noted that, the historical workpiece record, the historical storage occupancy rate, the historical detection time and the historical temperature change parameter all independently form a data set, not single data, and each data set has an associated binding relationship, and each data set forms a matrix vector.
Specifically, the first neuron receives the matrix vector of the history work piece record after the weighting treatment, and converts the history work piece record (in the form of characters and the like) into the quantifiable associated data representation, the second neuron receives the matrix vector of the history storage occupancy rate after the weighting treatment, the third neuron receives the matrix vector after the weighting treatment at the history detection time, and the fourth neuron receives the matrix vector after the weighting treatment at the history temperature change parameter, and the steps S31-S34 are executed in parallel; finally, the BP network normalizes the matrix vectors of each neuron, and predicts the temperature change trend of the corresponding workpiece model;
Compared with the prior art, when the testers input different types of workpieces, the method disclosed by the application can be adapted to predict the temperature change trend of the corresponding workpiece, and the visualization of the temperature change trend is realized, so that the method is beneficial to assisting the testers in carrying out pre-evaluation on the performance of the workpiece.
S40: and setting a dynamic threshold of the detection frequency based on the temperature change trend and a preset parameter standard library.
In this embodiment, the parameter standard library is set according to the national standard GB2423, and the standard includes a range of upper and lower limits of temperature, a range of upper and lower limits of frequency detection, and a range of upper and lower limits of detection time.
Specifically, according to the temperature change trend and a preset parameter standard library, a dynamic threshold of the detection frequency is set so as to meet the standard parameter setting of national standards, and the reliability of the temperature impact test is ensured.
As shown in fig. 4 and fig. 5, the detection frequency dynamic threshold includes a constant temperature detection dynamic threshold and a variable temperature detection dynamic threshold, and step S40 of the method of the present application includes:
s41: based on the temperature change trend, acquiring a constant temperature trend and a variable temperature trend;
S42: setting a standard detection frequency interval based on a preset parameter standard library;
S43: setting a constant temperature detection dynamic threshold based on a constant temperature trend and a standard detection frequency interval;
S44: and setting a dynamic threshold value of temperature change detection based on the temperature change trend and the standard detection frequency interval.
In this embodiment, the constant temperature trend refers to a constant temperature section in the predicted temperature variation trend; the temperature change trend refers to a temperature change section in the predicted temperature change trend; the relation among the standard detection frequency interval, the constant temperature detection dynamic threshold value and the variable temperature detection dynamic threshold value is shown in the following formula:
Equation one:
Formula II:
and (3) a formula III: f min≤f1＜＜f2
Equation four: f 2≤fmax
Wherein, (f min,fmax) is a standard detection frequency interval; f 1 is a constant temperature detection dynamic threshold; f 2 is a temperature change detection dynamic threshold; n 1 is the number of sampling points of the constant temperature section; n 2 is the sampling point number of the variable temperature section.
Specifically, when the workpiece is tested in a constant temperature state, the probability of potential problems of the workpiece is much smaller than that of the workpiece in a variable temperature state, and the detection requirement can be met by adopting lower detection frequency; the parameter standard library is set according to the national standard GB2423, and an upper limit and a lower limit of detection frequency setting are limited; the temperature change detection dynamic threshold value is far greater than the constant temperature detection dynamic threshold value, so that the accuracy of acquiring workpiece information when the workpiece changes temperature is improved;
Compared with the prior art, the method sets the constant temperature detection dynamic threshold through the constant temperature trend and the standard detection frequency interval so as to adapt to the change characteristics of the workpiece under the constant temperature test, reduce the self resource occupation amount of the equipment and improve the data processing effect; according to the method, the variable temperature detection dynamic threshold is set through the variable temperature trend and the standard detection frequency interval so as to adapt to the variable characteristic of the workpiece under the variable temperature test, and the data acquisition quantity is increased as much as possible under the national standard limiting condition and within the equipment allowable range so as to improve the sampling number of the variable temperature characteristic information of the workpiece, thereby improving the accuracy of evaluating the quality of the workpiece.
S50: and inputting the dynamic threshold value of the detection frequency and the historical characteristic parameters into a preset fuzzy control model, and setting the actual detection frequency.
In this embodiment, the history characteristic parameter input to the fuzzy control model is mainly the history detection setting frequency.
Specifically, the method of the application inputs the historical detection setting frequency and the detection frequency dynamic threshold value into the fuzzy control model, and finally sets the actual detection frequency, and the actual detection frequency can be adaptively adjusted according to the temperature change characteristic of the workpiece, thereby reducing the possibility that the temperature change and the potential problem of the workpiece are difficult to accurately capture when the temperature of the temperature impact test equipment rapidly suddenly changes due to the constant detection frequency, and further improving the accuracy of the test evaluation result.
As shown in fig. 6, the historical characteristic parameter further includes a historical detection set frequency, and the actual detection frequency includes a constant temperature detection frequency and a variable temperature detection frequency, and step S50 of the method of the present application includes:
s51: taking a constant temperature detection dynamic threshold value as a first variable range, and inputting a preset fuzzy control model;
s52: and setting constant temperature detection frequency based on the first variable range by taking the historical temperature change parameter, the historical detection setting frequency and the historical storage occupancy rate as fuzzy sets.
In this embodiment, the fuzzy relation formula of the first variable range, the historical temperature change parameter, the historical detection setting frequency and the historical storage occupancy rate in steps S51 to S52 is as follows:
Formula five: mu R(x,y,z)＝min[μA(x),μB(x),μC (x) ]
Formula six: f 1min≤μR(x,y,z)≤f1max
Wherein the first variable range is (f 1min,f1max); setting the historical detection frequency as mu A (x); the historical temperature change parameter is mu B (x); the historical storage occupancy rate is mu C(x),μR (x, y, z) which is constant temperature detection frequency, and [ mu A(x),μB(x),μC (x) ] is an ambiguity set.
Specifically, a constant temperature detection dynamic threshold value is used as a first variable range of a fuzzy control model, a historical temperature change parameter, a historical detection setting frequency and a historical storage occupancy rate are used as fuzzy sets, membership of the historical detection setting frequency, the historical storage occupancy rate and the historical temperature change parameter are associated,
Mu R (x, y, z) calculated takes the minimum value, and mu R (x, y, z) must be within the range of (f 1min,f1max),
On the premise of meeting detection requirements, the detection frequency is reduced as much as possible, so that the data processing capacity and the data occupied flash memory of the temperature impact test equipment are reduced, and more abundant equipment resources are reserved for the temperature change test process.
Wherein, step S50 further comprises:
S53: taking the variable temperature detection dynamic threshold value as a second variable range, and inputting a preset fuzzy control model;
S54, setting the temperature change detection frequency based on the fuzzy set and the second variable range.
In the present embodiment, the relation formula of the second variable range and the fuzzy set in steps S53 to S54 is as follows: formula seven: mu G(x,y,z)＝max[μA(x),μB(x),μC (x) ]
Formula eight: f 2min≤μR(x,y,z)≤f2max
The second variable range is (f 2min,f2max);μG (x, y, z) which is the temperature change detection frequency.
Specifically, the variable temperature detection dynamic threshold is used as a second variable range, the variable temperature detection frequency is set based on the fuzzy set and the second variable range, so that the maximum detection frequency is set on the premise that equipment resources and standard detection frequency intervals are allowed, the data extraction amount in the workpiece variable temperature process is increased, the omission of data sampling is reduced, and the accuracy of the test evaluation result is improved.
Wherein, after step S50, the method of the present application further comprises:
based on the actual detection frequency, acquiring abnormal detection information of the workpiece;
If the abnormality detection information exceeds a preset alarm threshold value, an abnormality early warning is sent out.
Specifically, after setting an actual detection frequency, the temperature impact test equipment starts heating the workpiece based on the actual detection frequency, acquires abnormal detection information of the workpiece, and detects potential problems of the workpiece in real time; when the abnormality detection information exceeds a preset alarm threshold value, an abnormality early warning is sent out to prompt a tester that a workpiece is seriously damaged in the process of a sample; and the abnormal early warning is stored in a corresponding memory, so that the test personnel can call data later to evaluate the quality of the workpiece further.
Example two
As shown in fig. 7, an embodiment of the present application discloses a system for applying to a workpiece temperature impact test, for performing a method for applying to a workpiece temperature impact test as described above, and a system for applying to a workpiece temperature impact test corresponds to a method for applying to a workpiece temperature impact test as described above in the embodiment.
The embodiment of the application provides a system applied to a workpiece temperature impact test, which comprises:
an identification module 10 for identifying the model of the workpiece;
The characteristic parameter extraction module 20 is used for acquiring historical temperature impact test data based on the model of the input workpiece and extracting historical characteristic parameters of the historical temperature impact test data;
The prediction module 30 is configured to input the weighted historical characteristic parameters into a preset neural network model, and predict a temperature variation trend;
a dynamic threshold setting module 40, configured to set a dynamic threshold of the detection frequency based on the temperature variation trend and a preset parameter standard library;
The actual frequency setting module 50 is configured to input the dynamic threshold value of the detected frequency and the historical characteristic parameter into a preset fuzzy control model, and set the actual detected frequency.
Wherein the prediction module 30 comprises:
The first processing submodule is used for inputting the weighted historical workpiece records into a first neuron;
the second processing submodule is used for inputting the weighted historical storage occupancy rate into a second neuron;
the third processing sub-module is used for inputting the weighted history detection time into a third neuron;
the fourth processing submodule is used for inputting the weighted historical temperature change parameters into a fourth neuron;
and the prediction sub-module is used for acquiring and processing the data in the first neuron, the second neuron, the third neuron and the fourth neuron based on the BP network, and predicting to obtain a temperature change trend.
Wherein the dynamic threshold setting module 40 includes:
The first acquisition submodule is used for acquiring a constant temperature trend and a variable temperature trend based on the temperature change trend;
The standard interval setting submodule is used for setting a standard detection frequency interval based on a preset parameter standard library;
the first threshold setting submodule is used for setting a constant-temperature detection dynamic threshold based on a constant-temperature trend and a standard detection frequency interval;
The second threshold setting submodule is used for setting a temperature change detection dynamic threshold based on the temperature change trend and the standard detection frequency interval.
Wherein, the actual frequency setting module 50 includes:
the first input submodule is used for taking a constant-temperature detection dynamic threshold value as a first variable range and inputting a preset fuzzy control model; the constant temperature detection frequency setting sub-module is used for setting constant temperature detection frequency based on a first variable range by taking the historical temperature change parameter, the historical detection setting frequency and the historical storage occupancy rate as fuzzy sets;
The second input submodule is used for taking the variable-temperature detection dynamic threshold value as a second variable range and inputting a preset fuzzy control model; the temperature change detection frequency setting sub-module is used for setting the temperature change detection frequency based on the fuzzy set and the second variable range.
The system for workpiece temperature impact test provided in this embodiment can achieve each step of the foregoing embodiments due to the function of each module and the logic connection between each module, so that the same technical effects as those of the foregoing embodiments can be achieved, and the principle analysis can refer to the related description of the steps of the foregoing method for workpiece temperature impact test, which is not repeated herein.
For specific limitations on a system applied to the workpiece temperature impact test, reference may be made to the above limitation on a method applied to the workpiece temperature impact test, and detailed descriptions thereof are omitted herein; each of the above-described modules in a system for workpiece temperature impact testing may be implemented in whole or in part by software, hardware, and combinations thereof; each of the above modules may be embedded in hardware or may be independent of a processor in the computer device, or may be stored in software in a memory in the computer device, so that the processor may invoke and execute the operations corresponding to each of the above modules.
Example III
As shown in fig. 8, in the present embodiment, a computer apparatus includes a memory, a processor, and a computer program stored in the memory and executable on the processor, the processor implementing the following steps when executing the computer program:
Identifying the model of the input workpiece;
Based on the model of the input workpiece, acquiring historical temperature impact test data, and extracting historical characteristic parameters of the historical temperature impact test data;
the historical characteristic parameters are weighted and then input into a preset neural network model, and a temperature change trend is predicted and obtained;
Setting a detection frequency dynamic threshold based on the temperature change trend and a preset parameter standard library;
And inputting the detection frequency dynamic threshold and the historical characteristic parameters into a preset fuzzy control model, and setting actual detection frequency.
In this embodiment, there is provided a computer-readable storage medium storing a computer program which when executed performs the steps of:
Identifying the model of the input workpiece;
Based on the model of the input workpiece, acquiring historical temperature impact test data, and extracting historical characteristic parameters of the historical temperature impact test data;
the historical characteristic parameters are weighted and then input into a preset neural network model, and a temperature change trend is predicted and obtained;
Setting a detection frequency dynamic threshold based on the temperature change trend and a preset parameter standard library;
And inputting the detection frequency dynamic threshold and the historical characteristic parameters into a preset fuzzy control model, and setting actual detection frequency.
Those skilled in the art will appreciate that implementing all or part of the above described embodiment methods may be accomplished by way of a computer program stored on a non-transitory computer readable storage medium, which when executed, may comprise the steps of each of the above described embodiments. Any reference to memory, storage, database, or other medium used in each of the embodiments provided herein may include non-volatile and/or volatile memory. The nonvolatile memory can include Read Only Memory (ROM), programmable ROM (PROM), electrically Programmable ROM (EPROM), electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a number of forms such as Static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double Data Rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (SYNCHLINK), DRAM (SLDRAM), memory bus (rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), among others.
It will be apparent to those skilled in the art that, for convenience and brevity of description, only the above-described division of each functional unit and module is illustrated, and in practical application, the above-described functional allocation may be performed by different functional units and modules, that is, the internal result of the apparatus is divided into different functional units or modules, so as to perform all or part of the above-described functions.
The above embodiments are only for illustrating the technical solution of the present application, and not for limiting the same; although the application has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art will understand that; the technical scheme described in each embodiment can be modified or part of the characteristics can be replaced equivalently; such modifications and substitutions do not depart from the spirit and scope of the technical solutions of each embodiment of the present application, and are intended to be included in the scope of the present application.
Claims (7)
1. A method for use in a workpiece temperature impact test, comprising:
Identifying the model of the input workpiece;
Based on the model of the input workpiece, acquiring historical temperature impact test data, and extracting historical characteristic parameters of the historical temperature impact test data;
the historical characteristic parameters are weighted and then input into a preset neural network model, and a temperature change trend is predicted and obtained;
Setting a detection frequency dynamic threshold based on the temperature change trend and a preset parameter standard library;
Inputting the detection frequency dynamic threshold and the historical characteristic parameters into a preset fuzzy control model, and setting actual detection frequency;
The historical characteristic parameters comprise historical workpiece records, historical storage occupancy rates, historical detection time and historical temperature change parameters; the preset neural network model comprises a first neuron, a second neuron, a third neuron, a fourth neuron and a BP network; the step of inputting the weighted historical characteristic parameters into a preset neural network model, and the step of predicting the temperature change trend comprises the following steps:
the historical workpiece records are input into the first neuron after being weighted;
The historical storage occupancy rate is weighted and then input into the second neuron;
Weighting the history detection time and inputting the weighted history detection time into the third neuron;
weighting the historical temperature change parameters and inputting the weighted historical temperature change parameters into the fourth neuron;
Based on the BP network, acquiring and processing the data in the first neuron, the second neuron, the third neuron and the fourth neuron, and predicting to obtain a temperature change trend;
The detection frequency dynamic threshold value comprises a constant temperature detection dynamic threshold value and a variable temperature detection dynamic threshold value, and the setting of the detection frequency dynamic threshold value based on the temperature change trend and a preset parameter standard library comprises the following steps:
based on the temperature change trend, a constant temperature trend and a variable temperature trend are obtained;
Setting a standard detection frequency interval based on a preset parameter standard library;
Setting the constant temperature detection dynamic threshold based on the constant temperature trend and the standard detection frequency interval;
and setting the dynamic threshold of temperature change detection based on the temperature change trend and the standard detection frequency interval.
2. The method of claim 1, wherein the historical characteristic parameters further comprise historical detection set frequencies; the actual detection frequency comprises constant temperature detection frequency; inputting the detection frequency dynamic threshold and the historical characteristic parameter into a preset fuzzy control model, and setting the actual detection frequency, wherein the method comprises the following steps:
taking the constant temperature detection dynamic threshold value as a first variable range, and inputting a preset fuzzy control model;
And setting the constant temperature detection frequency based on the first variable range by taking the historical temperature change parameter, the historical detection setting frequency and the historical storage occupancy rate as fuzzy sets.
3. The method of claim 2, wherein the actual detection frequency comprises a temperature change detection frequency; inputting the detection frequency dynamic threshold and the historical characteristic parameter into a preset fuzzy control model, and setting the actual detection frequency, wherein the method comprises the following steps:
Taking the temperature change detection dynamic threshold value as a second variable range, and inputting a preset fuzzy control model;
And setting the temperature change detection frequency based on the fuzzy set and the second variable range.
4. The method according to claim 1, wherein after the step of inputting the detection frequency dynamic threshold and the history feature parameter into a preset fuzzy control model to set an actual detection frequency, the method further comprises:
based on the actual detection frequency, acquiring abnormal detection information of the workpiece;
And if the abnormality detection information exceeds a preset alarm threshold value, an abnormality early warning is sent out.
5. A system for use in a workpiece temperature impact test, the system comprising:
The identification module is used for identifying the model of the input workpiece;
the characteristic parameter extraction module is used for acquiring historical temperature impact test data based on the model of the input workpiece and extracting historical characteristic parameters of the historical temperature impact test data;
the prediction module is used for inputting the weighted historical characteristic parameters into a preset neural network model and predicting to obtain a temperature change trend;
The dynamic threshold setting module is used for setting a dynamic threshold of the detection frequency based on the temperature change trend and a preset parameter standard library;
the actual frequency setting module is used for inputting the detection frequency dynamic threshold and the history characteristic parameter into a preset fuzzy control model and setting actual detection frequency;
wherein the prediction module comprises:
The first processing submodule is used for inputting the weighted historical workpiece records into a first neuron;
the second processing submodule is used for inputting the weighted historical storage occupancy rate into a second neuron;
the third processing sub-module is used for inputting the weighted history detection time into a third neuron;
the fourth processing submodule is used for inputting the weighted historical temperature change parameters into a fourth neuron;
The prediction sub-module is used for acquiring and processing the data in the first neuron, the second neuron, the third neuron and the fourth neuron based on the BP network, and predicting to obtain a temperature change trend;
Wherein, the dynamic threshold setting module includes:
The first acquisition submodule is used for acquiring a constant temperature trend and a variable temperature trend based on the temperature change trend;
The standard interval setting submodule is used for setting a standard detection frequency interval based on a preset parameter standard library;
the first threshold setting submodule is used for setting a constant-temperature detection dynamic threshold based on a constant-temperature trend and a standard detection frequency interval;
The second threshold setting submodule is used for setting a temperature change detection dynamic threshold based on the temperature change trend and the standard detection frequency interval.
6. A computer device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, the processor implementing a method for applying a workpiece temperature impact test as claimed in any one of claims 1 to 4 when the computer program is executed.
7. A computer-readable storage medium, characterized in that the computer-readable storage medium stores a computer program which, when executed by a processor, implements a method for applying a workpiece temperature impact test according to any one of claims 1 to 4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311117456.1A CN117057432B (en) | 2023-08-31 | 2023-08-31 | Method and system applied to workpiece temperature impact test |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311117456.1A CN117057432B (en) | 2023-08-31 | 2023-08-31 | Method and system applied to workpiece temperature impact test |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117057432A CN117057432A (en) | 2023-11-14 |
| CN117057432B true CN117057432B (en) | 2024-04-19 |
Family
ID=88657167
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311117456.1A Active CN117057432B (en) | 2023-08-31 | 2023-08-31 | Method and system applied to workpiece temperature impact test |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117057432B (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2006329701A (en) * | 2005-05-24 | 2006-12-07 | Espec Corp | Thermal shock testing device, and testing method for thermal shock test |
| CN109187035A (en) * | 2018-08-03 | 2019-01-11 | 中国地质大学（武汉） | A kind of diesel engine cold shock testing device and method |
| CN113804389A (en) * | 2021-09-29 | 2021-12-17 | 广州计测检测技术股份有限公司 | Impact test detection method |
| CN115115653A (en) * | 2022-06-13 | 2022-09-27 | 广东众志检测仪器有限公司 | Refined temperature calibration method for cold and hot impact test box |
| CN115855016A (en) * | 2023-02-27 | 2023-03-28 | 南开大学 | Low-temperature impact error compensation method for optical fiber gyroscope |
| CN219121684U (en) * | 2022-09-26 | 2023-06-02 | 昆明理工大学 | Thermal shock fatigue test bed with fault recognition and alarm functions for heated part |
-
2023
- 2023-08-31 CN CN202311117456.1A patent/CN117057432B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2006329701A (en) * | 2005-05-24 | 2006-12-07 | Espec Corp | Thermal shock testing device, and testing method for thermal shock test |
| CN109187035A (en) * | 2018-08-03 | 2019-01-11 | 中国地质大学（武汉） | A kind of diesel engine cold shock testing device and method |
| CN113804389A (en) * | 2021-09-29 | 2021-12-17 | 广州计测检测技术股份有限公司 | Impact test detection method |
| CN115115653A (en) * | 2022-06-13 | 2022-09-27 | 广东众志检测仪器有限公司 | Refined temperature calibration method for cold and hot impact test box |
| CN219121684U (en) * | 2022-09-26 | 2023-06-02 | 昆明理工大学 | Thermal shock fatigue test bed with fault recognition and alarm functions for heated part |
| CN115855016A (en) * | 2023-02-27 | 2023-03-28 | 南开大学 | Low-temperature impact error compensation method for optical fiber gyroscope |
Non-Patent Citations (3)
| Title |
|---|
| A Near-Surface Layer Heat Treatment of Die Casting Dies by Means of Electron-Beam Technology;Torsten Schuchardt 等;《Electron Beam Treatment Technology in Metals》;第11卷(第8期);1-15 * |
| 基于BP神经网络的汽轮机转子钢热脆化性能的预测;张胜寒;范永哲;陈颖敏;;《中国电机工程学报》(第23期);113-116 * |
| 随弹射座椅离机工作的电子设备环境试验探讨;尹树悦 等;《电子产品可靠性与环境试验》;第36卷(第1期);113-116 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117057432A (en) | 2023-11-14 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111667011B (en) | Damage detection model training and vehicle damage detection method, device, equipment and medium | |
| CN111667010A (en) | Sample evaluation method, device and equipment based on artificial intelligence and storage medium | |
| CN110008082B (en) | Abnormal task intelligent monitoring method, device, equipment and storage medium | |
| CN112115005B (en) | Test data acquisition method and device, computer equipment and storage medium | |
| CN112149909A (en) | Ship oil consumption prediction method and device, computer equipment and storage medium | |
| CN111124898B (en) | Question-answering system testing method and device, computer equipment and storage medium | |
| CN113110961B (en) | Equipment abnormality detection method and device, computer equipment and readable storage medium | |
| CN117057432B (en) | Method and system applied to workpiece temperature impact test | |
| CN112988606B (en) | Test case generation method, device, equipment and storage medium | |
| CN116994641A (en) | Semiconductor aging test method and system thereof | |
| CN115865630B (en) | Network equipment fault diagnosis method and system based on deep learning | |
| CN111161747A (en) | Prediction method and device based on Tensorflow awakening model and computer equipment | |
| CN116738261A (en) | Numerical characteristic discretization attribution analysis method and device based on clustering and binning | |
| CN115965625A (en) | Instrument detection device based on visual identification and detection method thereof | |
| CN110865939B (en) | Application program quality monitoring method, device, computer equipment and storage medium | |
| CN109241864A (en) | Emotion prediction technique, device, computer equipment and storage medium | |
| CN113222370B (en) | Power system risk early warning method, device, equipment and storage medium | |
| CN114282834A (en) | Evaluation result traceability analysis method, device, equipment and storage medium | |
| CN114372536A (en) | Unknown network flow data identification method and device, computer equipment and storage medium | |
| CN114879043A (en) | Lithium ion battery lithium analysis diagnosis method, device, equipment and medium | |
| CN112541177A (en) | Data security-based anomaly detection method and system | |
| CN113670987A (en) | Method, device, equipment and storage medium for identifying insulation aging state of oil paper | |
| CN115729785A (en) | Equipment state detection method and device, electronic equipment and storage medium | |
| CN115841255B (en) | On-site early warning method and system for building engineering based on-line analysis | |
| CN117310813A (en) | Rock mass instability prediction method and device based on microseismic monitoring |
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 |