Intelligent test control method and system for aging test

Abstract

The application provides an intelligent test control method and system for aging test, and relates to the technical field of aging test. The method comprises the following steps: obtaining historical test control data of an analysis object, performing data clustering on similar test objects, and forming similar historical test control clustering data; performing temperature change prediction analysis on the similar test objects according to the similar historical test control clustering data, and forming similar test temperature control prediction characteristic data; obtaining real-time test control data, combining the similar test temperature control prediction characteristic data to perform temperature control analysis, and forming real-time temperature control prediction data. The method realizes real-time reaction regulation and control of temperature control through reasonable data analysis and processing, improves the quality and efficiency of temperature control, and effectively guarantees the quality and reliability of the test without improving the performance requirements of the test equipment.

Description

Technical Field

[0001] This invention relates to the field of aging testing technology, and more specifically, to an intelligent testing control method and system for aging testing. Background Technology

[0002] Aging tests assess the thermal lifespan and reliability of a test subject under long-term environmental factors such as heat, oxygen, and stress. It is not simply about "using" old products, but rather about accelerating aging to predict their lifespan under normal operating temperatures. The most crucial aspect of aging tests is the control of time and temperature to accurately assess the lifespan of the test subject. Therefore, precise real-time temperature control within the aging furnace is necessary to ensure the rationality and accuracy of the test.

[0003] Currently, most real-time temperature control methods are reactive, meaning that action is taken immediately after a temperature exceedance is detected. While exceeding the limit may exceed standard requirements, timely temperature control as long as the temperature does not exceed the standard can ensure the normal progress of the experiment. However, this places higher demands on the equipment, especially on temperature monitoring and control.

[0004] Therefore, designing an intelligent test control method and system for aging tests, and achieving real-time response and regulation of temperature control through reasonable data analysis and processing, thereby improving the quality and efficiency of temperature control, and effectively ensuring the quality and reliability of the test without increasing the performance requirements of the test equipment, is an urgent problem to be solved. Summary of the Invention

[0005] The purpose of this invention is to provide an intelligent test control method for aging tests. By acquiring historical temperature control data of the same type of test object, the correlation between all control parameters affecting temperature changes in the aging furnace and temperature parameters under that type of test is obtained. This enables accurate and effective prediction of temperature changes over a predictable period of time. On the one hand, it achieves effective temperature prediction and analysis, which is beneficial for accurately grasping the trend of temperature changes during the test. On the other hand, by using short-term temperature change prediction, parameter control can be adjusted in advance for abnormal temperature changes, effectively ensuring that temperature changes are controlled within the required range in real time. This avoids the delay control defects of post-testing, further improving the test effect and quality, and effectively ensuring the accuracy and rationality of the test results.

[0006] The present invention also aims to provide an intelligent test control system for aging tests. This system combines different functional units to form a system capable of accurate temperature prediction. The data acquisition unit collects the required historical and real-time data; the clustering and scoring unit performs cluster analysis on similar historical data; the feature analysis unit uses the clustered data to perform predictive feature analysis and form a relational model for accurate temperature prediction; and the implementation analysis unit uses the formed relational model to perform temperature prediction analysis on real-time data, providing reliable parameters for timely temperature control adjustments in response to abnormal temperature changes. The close integration and information flow between different functional units is a crucial material basis for achieving accurate temperature prediction.

[0007] In a first aspect, the present invention provides an intelligent test control method for aging tests, comprising: acquiring historical test control data of the analysis object, performing data clustering of similar test objects to form similar historical test control cluster data; performing temperature change prediction analysis for similar test objects based on similar historical test control cluster data to form similar test temperature control prediction feature data; acquiring real-time test control data, and performing temperature control analysis in conjunction with similar test temperature control prediction feature data to form real-time temperature control prediction data.

[0008] In this invention, the method obtains historical temperature control data of the same type of test object to acquire the correlation between all control parameters affecting temperature changes in the aging furnace under that type and the temperature parameter. This enables accurate and effective prediction of temperature changes over a predictable period of time. On the one hand, it achieves effective temperature prediction and analysis, which is beneficial for accurately grasping the trend of temperature changes during the test. On the other hand, by using short-term temperature change prediction, parameter control can be adjusted in advance for abnormal temperature changes, effectively ensuring that temperature changes are controlled within the required range in real time. This avoids the delay control defects of post-event handling, further improving the test effect and quality, and effectively ensuring the accuracy and rationality of the test results.

[0009] One possible implementation is to obtain historical test control data of the analysis object, perform data clustering of similar test objects, and form similar historical test control cluster data. This includes: extracting historical test data of different test objects based on historical test control data; obtaining corresponding object type parameter information for different object historical test data; and performing cluster analysis on different test objects based on the corresponding object type parameter information to form similar historical test control cluster data.

[0010] In this invention, the purpose of cluster analysis is to cluster similar test objects from historical data to ensure more accurate and effective subsequent targeted feature extraction. It should be noted that this clustering is not based on the physicochemical characteristics of the test objects, but rather on their testing conditions within the aging furnace, to ensure that predictions of temperature changes within the furnace are reasonable and effective. Of course, this historical data should be specific to a particular aging furnace; otherwise, the inconsistency in the performance of the equipment and facilities from which the control parameters are derived will cause the clustering and feature analysis to lose accuracy and rationality.

[0011] As one possible implementation, for different object historical test data, corresponding object type parameter information is obtained, including: for different test objects, extracting object type parameter information including but not limited to the following based on the corresponding object historical test data: based on the position of the test object in the analysis object, determining the ratio of the size of the range defined by the plane perpendicular to the first direction of the test object in the analysis coordinate system to the height of the higher limiting plane determined by the defined range, forming the object's X-direction plane limiting position value; based on the position of the test object in the analysis object, determining the ratio of the size of the range defined by the plane perpendicular to the second direction of the test object in the analysis coordinate system to the height of the higher limiting plane determined by the defined range, forming the object's Y-direction plane limiting position value; based on the position of the test object in the analysis object, determining the ratio of the size of the range defined by the plane perpendicular to the third direction of the test object in the analysis coordinate system to the height of the higher limiting plane determined by the defined range, forming the object's Z-direction plane limiting position value; forming a range space based on the range defined by the test object in the three directions, determining the object's limited volume ratio in the range space.

[0012] In this invention, the object type parameter information mainly reflects the test state of the tested object in the aging furnace. After all, the influence of the tested object on the temperature of the aging furnace during operation is mainly reflected through the influence of the tested object on airflow, gas volume, etc. in the space of the aging furnace. The factors affecting these control parameters include, but are not limited to, the size, surface structure shape, and positional relationship of the tested object. This application provides four necessary type parameters. Three of them are the ratio of the distance between the upper and lower limiting planes within the plane range of different directions in the coordinate system relative to the aging furnace to the position value of the upper plane in the direction. This ratio reflects the relative positional relationship of the tested object in the aging furnace analysis object. The positional relationship has a significant impact on the airflow in the aging furnace. The other type parameter is the volume ratio of the tested object. The volume ratio based on the limited position area is more representative. After all, there are cases where the overall object volume is significantly different under the same limited area volume. Directly selecting the volume of the aging furnace to obtain the volume ratio will result in a small ratio due to the large volume of the aging furnace, which has poor analogy and loses the meaning of type classification and comparison. Of course, other parameters can also be used as a reference for clustering, such as structural size-related parameters, size-to-size ratio, and the relative location of the centroid in the confined space. These can be selected according to actual needs to improve the accuracy and rationality of clustering.

[0013] As one possible implementation, cluster analysis is performed on different test objects based on their corresponding object type parameter information to form historical test control cluster data of the same type. This includes: for different test objects, forming an object type parameter matrix based on the corresponding object X-plane limit position value, object Y-plane limit position value, object Z-plane limit position value, and object limited volume ratio value. Where n represents the number of different test objects; the object type parameter matrix for different test objects Determine the identity matrix Object type similarity ,in, , express and The cosine similarity value; the similarity of object types between different test objects. Mapping onto a number axis creates an object similarity mapping axis; performing density variation clustering analysis along the axis generates historical test control clustering data for the same object similarity mapping axis.

[0014] In this invention, after obtaining multiple type parameter information corresponding to each test object, it is necessary to consider how to use these parameters to achieve clustering of the test objects. This method uses a unified identity matrix, and clustering evaluation is performed by comparing the similarity between the matrix established by the multiple type parameters of the test object and the identity matrix. It is understood that the maximum value of the four type parameters extracted for the test object in this application is 1, so it is reasonable to set all elements of the identity matrix to 1. Furthermore, the matrices established for different test objects need to ensure that the order of the type parameters within the matrix is ​​consistent. For clustering analysis using the obtained cosine similarity values, considering that the distribution of cosine similarity values ​​may have a wide range, directly clustering according to the limited magnitude or range of cosine values ​​may lead to the failure to determine cluster centers, resulting in distorted clustering analysis. Therefore, this application considers determining cluster centers first before clustering to ensure the accuracy and rationality of the clustering. Here, the determination of cluster centers is accomplished by mapping cosine values ​​onto a number axis.

[0015] One possible implementation involves performing density variation clustering analysis along the object similarity mapping axis to form similar historical test control clustering data. This includes: setting a window sliding step size and a density analysis radius; starting from the smallest cosine similarity value as the density analysis center point on the object similarity mapping axis, determining the next density analysis center point by the distance of each sliding window step size along the axis, and obtaining the number of cosine similarity values ​​involved within a circle centered on the density analysis center point and with the density analysis radius as the radius, until the window covers the largest cosine similarity value; fitting a location point-quantity curve based on the quantity determined for each density analysis center point; determining the average quantity value based on the location point-quantity curve, and obtaining all peak values ​​above the average quantity value on the location point-quantity curve, and labeling them as cluster similarity center values; for different cluster similarity center values, obtaining the test objects and corresponding historical test data corresponding to all cosine similarity values ​​within the allowable range of unilateral allowable variation centered on the cluster similarity center value and with the cluster tolerance value as the unilateral allowable variation range, forming corresponding similar test object clustering data; and combining different similar test object clustering data to form similar historical test control clustering data.

[0016] In this invention, the cluster centers are determined by mapping cosine similarity values ​​onto a number axis, with the density of similarity values ​​along the axis as a reference. It can be understood that if the test objects can cluster, the cosine similarity values ​​will be concentrated within a certain range. Therefore, a sliding window is established to determine the density variation, thus forming density variation values. The peak value in the density variation function is determined by the average value, thereby obtaining the cluster center point. Using the center point as a reference, and considering a certain tolerance, the cluster range is obtained to form cluster data. The sliding step size, density radius, and cluster tolerance value can be determined according to the actual situation.

[0017] As one possible implementation, based on historical test control clustering data of the same type, temperature change prediction analysis is performed on the same type of test objects to form predictive feature data for temperature control of the same type of test objects. This includes: determining any K predictive analysis time periods for different test objects in different clustering data of the same type of test objects, forming the basic time periods for predictive analysis of different types of objects under the test objects; and extracting the initial values ​​of control parameters for different control parameters at the initial time point of the time period for the basic time periods for predictive analysis of different types of objects in different clustering data of the same type of test objects. Initial temperature value And the final temperature value at the end of the period. Where m represents the number of different test objects in the cluster data of the same type of test objects, and i represents the number of different control parameters; for different test objects in the cluster data of the same type of test objects, according to the parameter information obtained under the corresponding K prediction analysis time periods, the object temperature change prediction analysis is performed to form the type object temperature prediction feature data corresponding to the test object; for the type object temperature prediction feature data corresponding to different test objects in the cluster data of the same type of test objects, the type temperature change prediction analysis is performed to form the type test temperature control prediction feature data; the type test temperature control prediction feature data corresponding to different cluster data of the same type of test objects is collected to form the type test temperature control prediction feature data.

[0018] In this invention, to achieve temperature control prediction feature analysis, it is first necessary to extract basic data for direct analysis. Considering the high requirements of aging furnace temperature control and the limitations of the time span of prediction analysis, the time period of prediction analysis needs to be reasonably limited. The size of the prediction analysis time period can be determined according to the actual situation. For the test object, the test data is continuous in the time dimension. Therefore, in order to keep the data consistent with the data required for prediction analysis, this application performs prediction analysis by discretely extracting parameter control data within the same time span as the prediction analysis. Of course, it is first necessary to perform reasonable analysis of multiple sample data under the same object before performing prediction analysis between different objects to ensure the rationality and accuracy of the analysis.

[0019] As one possible implementation, for different test objects in the clustered data of similar test objects, based on the parameter information obtained under the corresponding K prediction analysis time periods, object temperature change prediction analysis is performed to form object type temperature prediction feature data for the test objects, including: setting the object type temperature prediction feature model: ,in, This is the initial temperature value. This represents the control parameter-related function corresponding to control parameter number i. To predict temperature values, the total number of parameters to be analyzed in the object temperature prediction feature model is determined, and K prediction analysis time periods are grouped according to the total number of parameters to be analyzed, forming a set of analysis groups. For different analysis groups, the object temperature prediction feature model is analyzed according to the parameter information obtained under different prediction analysis time periods in the analysis group, forming the corresponding analysis group object temperature prediction feature relationship. Based on the analysis group object temperature prediction feature relationship determined by different analysis groups, average fitting is performed to form the object temperature prediction feature relationship.

[0020] In this invention, the analysis of the test object takes into full consideration the application of data. This application obtains the temperature prediction characteristic relationship of the object by performing analysis in groups and then performing analysis between groups. It should be noted that the characteristic relationship model can be set according to actual needs. In particular, the functional expression of the control parameters needs to be comprehensively considered. Secondly, the higher the power term, the higher the accuracy, but the greater the analysis difficulty. The analysis of the relationship model can be completed with the same amount of data as the total number of data to be analyzed. Therefore, considering the full utilization of the data, group analysis is necessary. Each group will form a corresponding analytical relationship. This application uses the average value of the same type of terms in the relationship of each group as the final term relationship coefficient value to fully ensure the representativeness of the relationship. In addition, for the control parameters, the parameters that affect the temperature are mainly selected, including but not limited to the average airflow velocity in the furnace, the average oxygen content in the furnace, the average change rate of ventilation, etc. The more parameters, the more accurate the analysis, but the analysis difficulty will also increase. Therefore, the selection should be comprehensively considered according to the actual situation.

[0021] As one possible implementation, type temperature change prediction analysis is performed on the type temperature prediction feature data corresponding to different test objects in the clustered data of similar test objects to form type test temperature control prediction feature data. This includes: extracting all constant terms from the relationship formulas of different test objects in the clustered data of similar test objects to form corresponding object relationship constant matrix; using the object relationship constant matrix corresponding to different test objects to perform relationship filtering in the following way: arbitrarily select an object relationship constant matrix and determine its cosine similarity value with other object relationship constant matrices. If the proportion of the number of cosine similarity values ​​exceeding the similarity judgment threshold to the total number of cosine similarity values ​​is not less than the selection ratio, then the type object temperature prediction feature relationship corresponding to all object relationship constant matrices whose cosine similarity values ​​exceed the similarity judgment threshold is determined as the selected relationship; otherwise, arbitrarily select another object relationship constant matrix to judge the selected relationship until the selected relationship is determined; perform equalization fitting analysis on the determined selected relationship to form the type test temperature control prediction feature relationship.

[0022] In this invention, feature analysis of temperature prediction is performed on the feature relationships of different objects in the data for clustering features of the same type. The main purpose is to reasonably integrate the feature relationships corresponding to different objects to form feature relationships applicable to all objects of the same type. Considering that the test data collected for different objects in historical data may contain certain data errors and biases, in order to avoid the impact of these data errors and biases on the accuracy of the final relationship, it is necessary to first determine whether these relationships can be used for feature analysis. The determination method adopted is to extract different constant terms in the relationship to form a matrix with certain permutations and combinations, and then use the correlation between the data matrices corresponding to different relationship to make reasonable selection. This correlation is represented by the cosine similarity of the matrix. Of course, the magnitude of the cosine similarity value determines the magnitude of the correlation. Therefore, the magnitude of the similarity judgment threshold determines the number of correlations obtained and the accuracy of the feature relationships formed by the feature analysis of the selected correlations for temperature prediction of different objects of the same type. Therefore, the setting of the similarity judgment threshold can be determined according to the actual situation. Of course, the similarity judgment threshold and the selection quantity ratio need to be set in combination to ensure that a sufficient number of relationships that meet the requirements can be obtained. After obtaining the selected relation, the final characteristic relation can be formed by using the average fitting method. This fitting method usually involves extracting the average value of constant terms of the same type and using it as the constant value of the constant term corresponding to the final relation.

[0023] One possible approach is to acquire real-time test control data and combine it with similar test temperature control prediction feature data to perform temperature control analysis, thereby forming real-time temperature control prediction data. This includes: acquiring parameter values ​​for different object types of real-time objects based on the real-time test control data, determining object type similarity based on the identity matrix, and identifying the type test temperature control prediction feature relationship corresponding to the cluster similarity center value closest to the object type similarity as the prediction relationship; extracting real-time parameter values ​​for different control parameters based on the real-time test control data, and determining the predicted temperature value based on the determined type test temperature control prediction feature relationship.

[0024] In this invention, the main purpose of real-time temperature control prediction is to obtain the predicted value of the aging furnace temperature within the prediction period. First, it is necessary to determine the characteristic relationship that is suitable for the real-time test object based on the type parameters of the real-time test object. Then, the highest temperature within the prediction period is determined by using the determined characteristic relationship in combination with the parameter values ​​of different control parameters extracted from the real-time test data to anticipate the occurrence of temperature deviation and make advance temperature control adjustments.

[0025] Secondly, the present invention provides an intelligent test control system for aging tests, comprising: a data acquisition unit for acquiring historical test control data of the analysis object and real-time test control data of the real-time test object; a clustering analysis unit for performing data clustering of similar test objects based on the historical test control data acquired by the data acquisition unit, forming similar historical test control cluster data; a feature analysis unit for performing temperature change prediction analysis for similar test objects based on the similar historical test control cluster data formed by the clustering analysis unit, forming similar test temperature control prediction feature data; and a prediction analysis unit for performing temperature control analysis based on the real-time test control data acquired by the data acquisition unit and the similar test temperature control prediction feature data formed by the feature analysis unit, forming real-time temperature control prediction data.

[0026] In this invention, the system combines different functional units to form a system capable of accurate temperature prediction. The data acquisition unit collects the required historical and real-time data; the clustering and scoring unit performs cluster analysis on similar historical data; the feature analysis unit uses the clustered data to perform predictive feature analysis, forming a relational model for accurate temperature prediction; and the implementation analysis unit uses the formed relational model to perform temperature prediction analysis on real-time data, providing reliable parameters for proactive temperature control adjustments to address abnormal temperature changes. The close integration and information flow between these different functional units is a crucial material foundation for achieving accurate temperature prediction.

[0027] The beneficial effects of the intelligent test control method and system for aging tests provided by this invention are as follows: This method obtains historical temperature control data of the same type of test object to determine the correlation between all control parameters affecting temperature changes in the aging furnace and the temperature parameter. This enables accurate and effective prediction of temperature changes over a predictable period. On the one hand, it achieves effective temperature prediction and analysis, which is beneficial for accurately grasping the trend of temperature changes during the test. On the other hand, by using short-term temperature change prediction, parameter control can be adjusted in advance for abnormal temperature changes, effectively ensuring that temperature changes are controlled within the required range in real time. This avoids the delay in control due to post-event handling, further improving the test effect and quality, and effectively ensuring the accuracy and rationality of the test results.

[0028] This system combines different functional units to form a system capable of accurate temperature prediction. The data acquisition unit collects necessary historical and real-time data; the clustering and scoring unit performs cluster analysis on similar historical data; the feature analysis unit uses the clustered data to perform predictive feature analysis, forming a relational model for accurate temperature prediction; and the implementation analysis unit uses this relational model to perform temperature prediction analysis on real-time data, providing reliable parameters for proactive temperature control adjustments to address abnormal temperature changes. The close integration and information flow between these functional units is a crucial material foundation for achieving accurate temperature prediction. Attached Figure Description

[0029] To more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings used in the embodiments of the present invention will be briefly introduced below. It should be understood that the following drawings only show some embodiments of the present invention and should not be regarded as a limitation of the scope. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0030] Figure 1 A step diagram illustrating an intelligent test control method for aging testing provided in an embodiment of the present invention; Figure 2 This is a schematic diagram of the structure of an intelligent test control system for aging testing provided in an embodiment of the present invention. Detailed Implementation

[0031] The technical solutions of the present invention will now be described with reference to the accompanying drawings in the embodiments of the present invention.

[0032] Aging tests assess the thermal lifespan and reliability of a test subject under long-term environmental factors such as heat, oxygen, and stress. It is not simply about "using" old products, but rather about accelerating aging to predict their lifespan under normal operating temperatures. The most crucial aspect of aging tests is the control of time and temperature to accurately assess the lifespan of the test subject. Therefore, precise real-time temperature control within the aging furnace is necessary to ensure the rationality and accuracy of the test.

[0033] Currently, most real-time temperature control methods are reactive, meaning that action is taken immediately after a temperature exceedance is detected. While exceeding the limit may exceed standard requirements, timely temperature control as long as the temperature does not exceed the standard can ensure the normal progress of the experiment. However, this places higher demands on the equipment, especially on temperature monitoring and control.

[0034] refer to Figures 1-2This invention provides an intelligent test control method for aging tests. This method acquires historical temperature control data of the same type of test object to determine the correlation between all control parameters affecting temperature changes within the aging furnace and the temperature parameter. This allows for accurate and effective prediction of temperature changes over a predictable period. On one hand, it enables effective temperature prediction and analysis, facilitating accurate understanding of temperature trends during testing. On the other hand, by using short-term temperature change prediction, it allows for advance adjustment of parameter controls in case of abnormal temperature changes, effectively ensuring that temperature changes are controlled within the required range in real time. This avoids the delayed control defects of post-testing, further improving the test effect and quality, and effectively guaranteeing the accuracy and rationality of the test results.

[0035] A smart test control method for aging tests specifically includes the following steps: S1: Obtain historical test control data of the analysis object, perform data clustering of similar test objects, and form similar historical test control cluster data.

[0036] The process involves acquiring historical test control data for the analysis objects, clustering similar test objects, and forming historical test control cluster data for the same category. This includes: extracting historical test data for different test objects based on the historical test control data; obtaining corresponding object type parameter information for different object historical test data; and performing cluster analysis on different test objects based on the corresponding object type parameter information to form historical test control cluster data for the same category.

[0037] The purpose of cluster analysis is to cluster similar test objects from historical data to ensure more accurate and effective subsequent targeted feature extraction. It's important to note that this clustering is not based on the physicochemical characteristics of the test objects, but rather on their testing conditions within the aging furnace. This ensures that predictions of temperature changes within the aging furnace are reasonable and effective. Of course, this historical data should be specific to a particular aging furnace; otherwise, inconsistencies in the performance of the equipment and facilities from which the control parameters are derived will render the clustering and feature analysis inaccurate and flawed.

[0038] For different historical test data of objects, obtain corresponding object type parameter information, including: For different test objects, extract object type parameter information including but not limited to the following based on the corresponding historical test data of the object: Based on the position of the test object in the analysis object, determine the ratio of the size of the range of the test object in the first direction of the analysis coordinate system defined by a plane perpendicular to the first direction to the height of the higher limiting plane determined by the defined range, forming the object's X-direction plane limiting position value; Based on the position of the test object in the analysis object, determine the ratio of the size of the range of the test object in the second direction of the analysis coordinate system defined by a plane perpendicular to the second direction to the height of the higher limiting plane determined by the defined range, forming the object's Y-direction plane limiting position value; Based on the position of the test object in the analysis object, determine the ratio of the size of the range of the test object in the third direction of the analysis coordinate system defined by a plane perpendicular to the third direction to the height of the higher limiting plane determined by the defined range, forming the object's Z-direction plane limiting position value; Based on the ranges defined by the test object in the three directions, form a range space, and determine the object's limited volume ratio in the range space.

[0039] The object type parameter information mainly reflects the test state of the tested object in the aging furnace. After all, the influence of the tested object on the temperature of the aging furnace during operation is mainly reflected through the influence of the tested object on airflow and gas volume in the aging furnace space. The factors affecting these control parameters include, but are not limited to, the size, surface structure shape, and positional relationship of the tested object. This application provides four necessary type parameters. Three of them are the ratio of the distance between the upper and lower limiting planes within the plane range bounded by the plane perpendicular to the aging furnace coordinate system in different directions to the position value of the upper plane in the direction. This ratio reflects the relative positional relationship of the tested object in the aging furnace analysis object. The positional relationship has a significant impact on the airflow in the aging furnace. The other type parameter is the volume ratio of the tested object. The volume ratio based on the limited position area is more representative. After all, there are cases where the overall object volume varies significantly under the same limited area volume. Directly selecting the volume of the aging furnace to obtain the volume ratio will result in a small ratio due to the large volume of the aging furnace, which has poor analogy and loses the meaning of type classification and comparison. Of course, other parameters can also be used as a reference for clustering, such as structural size-related parameters, size-to-size ratio, and the relative location of the centroid in the confined space. These can be selected according to actual needs to improve the accuracy and rationality of clustering.

[0040] For different test objects, cluster analysis is performed based on the corresponding object type parameter information to form historical test control cluster data of the same type. This includes: for different test objects, an object type parameter matrix is ​​formed based on the corresponding object X-plane limit position value, object Y-plane limit position value, object Z-plane limit position value, and object limited volume ratio value. Where n represents the number of different test objects; the object type parameter matrix for different test objects Determine the identity matrix Object type similarity ,in, , express and The cosine similarity value; the similarity of object types between different test objects. Mapping onto a number axis creates an object similarity mapping axis; performing density variation clustering analysis along the axis generates historical test control clustering data for the same object similarity mapping axis.

[0041] After obtaining multiple type parameter information for each test object, the next step is to consider how to use these parameters to cluster the test objects. This method uses a unified identity matrix, evaluating clustering by comparing the similarity between the matrix constructed from the multiple type parameters of the test object and the identity matrix. It's understandable that the maximum value of the four type parameters extracted for the test object in this application is 1, so setting all elements of the identity matrix to 1 is reasonable. Furthermore, the matrices constructed for different test objects need to ensure that the order of the type parameters within the matrix is ​​consistent. For clustering analysis using the obtained cosine similarity values, considering that the distribution of cosine similarity values ​​may have a wide range, directly clustering according to the limited magnitude or range of cosine values ​​may lead to the failure to determine cluster centers, resulting in distorted clustering analysis. Therefore, this application considers determining cluster centers first before clustering to ensure the accuracy and rationality of the clustering. Here, the determination of cluster centers is accomplished by mapping cosine values ​​onto a number axis.

[0042] Density variation clustering analysis is performed along the similarity mapping axis of the objects to form control clustering data for similar historical tests. This includes: setting the window sliding step size and density analysis radius; starting from the smallest cosine similarity value as the density analysis center point on the similarity mapping axis, determining the next density analysis center point by sliding the window step size along the axis each time, and obtaining the number of cosine similarity values ​​involved within the range centered on the density analysis center point and with the density analysis radius as the radius, until the window covers the largest cosine similarity value; fitting a location point-quantity curve based on the quantity determined for each density analysis center point; determining the average quantity value based on the location point-quantity curve, and obtaining all peak values ​​above the average quantity value on the location point-quantity curve, and labeling them as cluster similarity center values; for different cluster similarity center values, obtaining the test objects and corresponding historical test data corresponding to all cosine similarity values ​​within the allowable range of unilateral allowable variation centered on the cluster similarity center value and with the cluster tolerance value as the unilateral allowable variation range, forming corresponding clustering data for similar test objects; and combining different clustering data for similar test objects to form control clustering data for similar historical tests.

[0043] Determining cluster centers by mapping cosine similarity values ​​onto a number axis uses the density of similarity values ​​along the axis as a reference. It can be understood that if test objects can cluster, the cosine similarity values ​​will concentrate within a certain range. Therefore, a sliding window is established to determine the density variation, thus forming density variation values. The peak value in the density variation function is determined by the average value, thereby obtaining the cluster center point. Using the center point as a reference, and considering a certain tolerance, the range of clusters is obtained to form cluster data. The sliding step size, density radius, and cluster tolerance value can be determined according to the actual situation.

[0044] S2: Based on the clustering data of similar historical test controls, perform temperature change prediction analysis for similar test objects to form temperature control prediction feature data for similar tests.

[0045] Based on historical test control clustering data of the same type, temperature change prediction analysis is performed for similar test objects to form predictive feature data for temperature control of similar tests. This includes: determining any K predictive analysis time periods for different test objects in different clusters of similar test objects to form the basic time periods for predictive analysis of different types of objects under the test objects; and extracting the initial values ​​of control parameters for different control parameters at the initial time point of the time period for the basic time periods for predictive analysis of different types of objects in different clusters of similar test objects. Initial temperature value And the final temperature value at the end of the period. Where m represents the number of different test objects in the cluster data of the same type of test objects, and i represents the number of different control parameters; for different test objects in the cluster data of the same type of test objects, according to the parameter information obtained under the corresponding K prediction analysis time periods, the object temperature change prediction analysis is performed to form the type object temperature prediction feature data corresponding to the test object; for the type object temperature prediction feature data corresponding to different test objects in the cluster data of the same type of test objects, the type temperature change prediction analysis is performed to form the type test temperature control prediction feature data; the type test temperature control prediction feature data corresponding to different cluster data of the same type of test objects is collected to form the type test temperature control prediction feature data.

[0046] To achieve temperature control prediction feature analysis, the first step is to extract basic data for direct analysis. Considering the high requirements of aging furnace temperature control and the limitations of the prediction analysis time span, the prediction analysis time period needs to be reasonably limited. The size of the prediction analysis time period can be determined according to the actual situation. For the test object, the test data is continuous in the time dimension. Therefore, in order to maintain consistency with the data required for prediction analysis, this application uses discrete extraction of parameter control data within the same time span as the prediction analysis to perform prediction analysis. Of course, it is necessary to first perform reasonable analysis of multiple sample data under the same object before performing prediction analysis between different objects to ensure the rationality and accuracy of the analysis.

[0047] For different test objects in the clustered data of similar test objects, based on the parameter information obtained under the corresponding K prediction analysis time periods, predictive analysis of object temperature changes is performed to form object type temperature prediction feature data for the test objects, including: setting object type temperature prediction feature models: ,in, This is the initial temperature value. This represents the control parameter-related function corresponding to control parameter number i. To predict temperature values, the total number of parameters to be analyzed in the object temperature prediction feature model is determined, and K prediction analysis time periods are grouped according to the total number of parameters to be analyzed, forming a set of analysis groups. For different analysis groups, the object temperature prediction feature model is analyzed according to the parameter information obtained under different prediction analysis time periods in the analysis group, forming the corresponding analysis group object temperature prediction feature relationship. Based on the analysis group object temperature prediction feature relationship determined by different analysis groups, average fitting is performed to form the object temperature prediction feature relationship.

[0048] To fully utilize the data analyzed under the test object, this application employs a method of grouping and then performing analytical processing between groups to obtain the temperature prediction characteristic relationship of the object. It should be noted that the characteristic relationship model can be set according to actual needs, especially the functional expressions concerning control parameters, which require comprehensive consideration. Furthermore, higher power terms result in higher accuracy but also greater analytical difficulty. The analysis of the relationship model only requires the same amount of data as the total number of data points to be analyzed. Therefore, considering the sufficiency of data utilization, grouping and analyzing is necessary. Each group will form a corresponding analytical relationship. This application uses the average value of similar terms in each group's relationship expression as the final term relationship coefficient value to fully ensure the representativeness of the relationship expression. In addition, for control parameters, the main selection focuses on parameters affecting temperature, including but not limited to the average gas flow velocity in the furnace, the average oxygen content in the furnace, and the average rate of change of ventilation. More parameters lead to more accurate analysis but also increase the analytical difficulty; therefore, selection should be based on a comprehensive consideration of the actual situation.

[0049] For the temperature prediction feature data of different test objects in the clustered data of the same type of test objects, type temperature change prediction analysis is performed to form type test temperature control prediction feature data. This includes: extracting all constant terms from the relationship formulas of different test objects in the clustered data of the same type of test objects to form corresponding object relationship constant matrix; using the object relationship constant matrix of different test objects, the relationship formula is filtered in the following way: arbitrarily select an object relationship constant matrix and determine its cosine similarity value with other object relationship constant matrices. If the proportion of the number of cosine similarity values ​​exceeding the similarity value judgment threshold to the total number of cosine similarity values ​​is not less than the selection ratio, then the type object temperature prediction feature relationship formulas corresponding to all object relationship constant matrices whose cosine similarity values ​​exceed the similarity value judgment threshold are determined as selected relationships. Otherwise, arbitrarily select another object relationship constant matrix to judge the selected relationship formula until a selected relationship formula is determined; perform equalization fitting analysis on the determined selected relationships to form type test temperature control prediction feature relationship formulas.

[0050] For clustered features of the same type, feature analysis of the characteristic relationships of different objects in the data for temperature prediction aims to reasonably integrate the characteristic relationships corresponding to different objects to form a feature relationship applicable to all objects of the same type. Considering that the test data collected for different objects in historical data may contain certain data errors and biases, it is necessary to first determine whether these relationships can be used for feature analysis in order to avoid the impact of these data errors and biases on the accuracy of the final relationship. The method adopted is to extract different constant terms from the relationship to form a matrix with certain permutations and combinations, and then use the correlation between the data matrices corresponding to different relationships to make reasonable selections. This correlation is represented by the cosine similarity of the matrices. Of course, the magnitude of the cosine similarity value determines the magnitude of the correlation. Therefore, the magnitude of the similarity judgment threshold determines the number of correlations obtained and the accuracy of the feature relationship formed by the feature analysis of the selected correlations for temperature prediction of different objects of the same type. Therefore, the setting of the similarity judgment threshold can be determined according to the actual situation. Of course, the similarity judgment threshold and the ratio of the number of selections need to be set in combination to ensure that a sufficient number of relationships that meet the requirements can be obtained. After obtaining the selected relation, the final characteristic relation can be formed by using the average fitting method. This fitting method usually involves extracting the average value of constant terms of the same type and using it as the constant value of the constant term corresponding to the final relation.

[0051] S3: Acquire real-time test control data, combine it with temperature control prediction feature data of similar tests to perform temperature control analysis, and form real-time temperature control prediction data.

[0052] Real-time test control data is acquired and combined with temperature control prediction feature data of similar tests to perform temperature control analysis, forming real-time temperature control prediction data. This includes: obtaining parameter values ​​of different object types of real-time objects based on the real-time test control data, determining object type similarity based on the identity matrix, and determining the type test temperature control prediction feature relationship corresponding to the cluster similarity center value closest to the object type similarity as the prediction relationship; extracting real-time parameter values ​​of different control parameters based on the real-time test control data, and determining the predicted temperature value based on the determined type test temperature control prediction feature relationship.

[0053] The main purpose of real-time temperature control prediction is to obtain the predicted value of the aging furnace temperature within the prediction period. First, it is necessary to determine the characteristic relationship suitable for the real-time test object based on the type parameters of the real-time test object. Then, by using the determined characteristic relationship and the parameter values ​​of different control parameters extracted from the real-time test data, the highest temperature within the prediction period can be determined in advance to deal with the occurrence of temperature deviation and make temperature control adjustments in advance.

[0054] This method is suitable for real-time monitoring and control of temperature within an aging furnace, such as in an aging test process for wires. After the aging furnace is heated to 35℃ and held at that temperature for 20 minutes, the first product is powered on. The voltage acquisition module measures the voltage data every 4 seconds and sends it to the PLC for storage. After the fifth voltage measurement, the power supply to the first product is disconnected, and the second product is powered on. The automatic test repeats the above steps until the voltage data of the 12th product is measured. The system uses 35℃ as a baseline, increments by 10℃ each time, holds the temperature for 20 minutes, and measures the voltage data of 12 products. After the aging furnace is heated to 95℃, it is then incremented by 5℃ each time and held at that temperature for 20 minutes, until the aging furnace reaches 145℃, at which point heating is immediately stopped, and the automatic test ends. The method of this application can be used to control the heating and temperature control of the aging furnace to achieve accurate and effective data measurement.

[0055] This invention also provides an intelligent test control system for aging tests. The system includes: a data acquisition unit for acquiring historical test control data of the analysis object and real-time test control data of the real-time test object; a clustering analysis unit for clustering similar test objects based on the historical test control data acquired by the data acquisition unit, forming similar historical test control cluster data; a feature analysis unit for performing temperature change prediction analysis on similar test objects based on the similar historical test control cluster data formed by the clustering analysis unit, forming similar test temperature control prediction feature data; and a prediction analysis unit for performing temperature control analysis based on the real-time test control data acquired by the data acquisition unit and the similar test temperature control prediction feature data formed by the feature analysis unit, forming real-time temperature control prediction data.

[0056] This system combines different functional units to form a system capable of accurate temperature prediction. The data acquisition unit collects necessary historical and real-time data; the clustering and scoring unit performs cluster analysis on similar historical data; the feature analysis unit uses the clustered data to perform predictive feature analysis, forming a relational model for accurate temperature prediction; and the implementation analysis unit uses this relational model to perform temperature prediction analysis on real-time data, providing reliable parameters for proactive temperature control adjustments to address abnormal temperature changes. The close integration and information flow between these functional units is a crucial material foundation for achieving accurate temperature prediction.

[0057] In summary, the beneficial effects of the intelligent test control method and system for aging tests provided by the embodiments of the present invention are as follows: This method obtains historical temperature control data of the same type of test object to determine the correlation between all control parameters affecting temperature changes in the aging furnace and the temperature parameter. This enables accurate and effective prediction of temperature changes over a predictable period. On the one hand, it achieves effective temperature prediction and analysis, which is beneficial for accurately grasping the trend of temperature changes during the test. On the other hand, by using short-term temperature change prediction, parameter control can be adjusted in advance for abnormal temperature changes, effectively ensuring that temperature changes are controlled within the required range in real time. This avoids the delay in control due to post-event handling, further improving the test effect and quality, and effectively ensuring the accuracy and rationality of the test results.

[0058] This system combines different functional units to form a system capable of accurate temperature prediction. The data acquisition unit collects necessary historical and real-time data; the clustering and scoring unit performs cluster analysis on similar historical data; the feature analysis unit uses the clustered data to perform predictive feature analysis, forming a relational model for accurate temperature prediction; and the implementation analysis unit uses this relational model to perform temperature prediction analysis on real-time data, providing reliable parameters for proactive temperature control adjustments to address abnormal temperature changes. The close integration and information flow between these functional units is a crucial material foundation for achieving accurate temperature prediction.

[0059] In the embodiments of this application, "instruction" can include direct and indirect instructions, as well as explicit and implicit instructions. The information indicated by a certain piece of information is called the information to be instructed. In the specific implementation process, there are many ways to instruct the information to be instructed, such as, but not limited to, directly instructing the information to be instructed, such as the information to be instructed itself or its index. It can also indirectly instruct the information to be instructed by instructing other information, where there is a relationship between the other information and the information to be instructed. It can also instruct only a part of the information to be instructed, while the other parts are known or pre-agreed upon. For example, the instruction of specific information can be achieved by using a pre-agreed (e.g., protocol-defined) arrangement of various pieces of information, thereby reducing instruction overhead to some extent. At the same time, common parts of various pieces of information can be identified and uniformly indicated to reduce the instruction overhead caused by individually indicating the same information.

[0060] Furthermore, the specific indication method can also be any existing indication method, such as, but not limited to, the above-mentioned indication methods and their various combinations. Specific details of various indication methods can be found in existing technologies, and will not be repeated here. As described above, for example, when multiple pieces of information of the same type need to be indicated, the indication methods for different pieces of information may differ. In the specific implementation process, the required indication method can be selected according to specific needs. This application embodiment does not limit the selected indication method; therefore, the indication methods involved in this application embodiment should be understood to cover various methods that enable the party to be indicated to obtain the information to be indicated.

[0061] It should be understood that the information to be indicated can be sent as a whole or divided into multiple sub-information messages sent separately, and the sending period and / or timing of these sub-information messages can be the same or different. The specific sending method is not limited in this application embodiment. The sending period and / or timing of these sub-information messages can be predefined, for example, according to a protocol, or configured by the sending device by sending configuration information to the receiving device.

[0062] "Predefined" or "pre-configured" can be achieved by pre-saving corresponding codes, tables, or other means that can be used to indicate relevant information in the device. This application does not limit the specific implementation method. "Saving" can refer to saving in one or more memories. These memories can be separate installations or integrated into the encoder, decoder, processor, or communication device. Alternatively, some memories can be separately installed, while others are integrated into the decoder, processor, or communication device. The type of memory can be any form of storage medium, and this application does not limit this.

[0063] The “protocol” mentioned in the embodiments of this application may refer to a protocol family in the field of communication, a standard protocol with a similar protocol family frame structure, or a related protocol applied to future communication systems. The embodiments of this application do not specifically limit this.

[0064] In the embodiments of this application, descriptions such as "when," "under the circumstances," "if," and "if" all refer to the device making corresponding processing under certain objective circumstances, and are not limited to a specific time. They do not require the device to make a judgment action during implementation, nor do they imply any other limitations.

[0065] In the description of the embodiments of this application, unless otherwise stated, " / " indicates that the objects before and after are in an "or" relationship. For example, A / B can represent A or B. "And / or" in the embodiments of this application is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A alone, A and B simultaneously, and B alone, where A and B can be singular or plural. Furthermore, in the description of the embodiments of this application, unless otherwise stated, "multiple" refers to two or more. "At least one of the following" or similar expressions refer to any combination of these items, including any combination of single or plural items. For example, at least one of a, b, or c can represent: a, b, c, ab, ac, bc, or abc, where a, b, and c can be single or multiple. Additionally, to facilitate a clear description of the technical solutions of the embodiments of this application, the terms "first" and "second" are used in the embodiments of this application to distinguish identical or similar items with essentially the same function and effect. Those skilled in the art will understand that the terms "first," "second," etc., do not limit the quantity or order of execution, and that "first," "second," etc., are not necessarily different. Furthermore, in the embodiments of this application, words such as "exemplary" or "for example" are used to indicate that something is being used as an example, illustration, or description. Any embodiment or design scheme described as "exemplary" or "for example" in the embodiments of this application should not be construed as being more preferred or advantageous than other embodiments or design schemes. Specifically, the use of words such as "exemplary" or "for example" is intended to present the relevant concepts in a concrete manner for ease of understanding.

[0066] It should be understood that the processor in the embodiments of this application can be a central processing unit (CPU), or it can be other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor can be a microprocessor or any conventional processor, etc.

[0067] It should also be understood that the memory in the embodiments of this application can be volatile memory or non-volatile memory, or may include both volatile and non-volatile memory. The non-volatile memory can be read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), or flash memory. The volatile memory can be random access memory (RAM), which is used as an external cache. By way of example, but not limitation, many forms of random access memory (RAM) are available, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate synchronous DRAM (DDR SDRAM), enhanced synchronous DRAM (ESDRAM), synchronous linked DRAM (SLDRAM), and direct rambus RAM (DR RAM).

[0068] The above embodiments can be implemented, in whole or in part, by software, hardware (such as circuits), firmware, or any other combination thereof. When implemented using software, the above embodiments can be implemented, in whole or in part, as a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, all or part of the processes or functions described in the embodiments of this application are generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that includes one or more sets of available media. The available medium can be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium. A semiconductor medium can be a solid-state drive.

[0069] It should be understood that the term "and / or" in this article is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, or B existing alone. A and B can be singular or plural. Additionally, the character " / " in this article generally indicates an "or" relationship between the preceding and following related objects, but it can also represent an "and / or" relationship. Please refer to the context for a more accurate understanding.

[0070] In this application, "at least one" means one or more, and "more than one" means two or more. "At least one of the following" or similar expressions refer to any combination of these items, including any combination of a single item or a plurality of items. For example, at least one of a, b, or c can mean: a, b, c, ab, ac, bc, or abc, where a, b, and c can be a single item or multiple items.

[0071] It should be understood that in the various embodiments of this application, the order of the above-mentioned processes does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application.

[0072] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0073] Those skilled in the art will understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0074] In the several embodiments provided in this application, it should be understood that the disclosed systems, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between apparatuses or units may be electrical, mechanical, or other forms.

[0075] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0076] In addition, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0077] If the aforementioned functions are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0078] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. An intelligent test control method for aging tests, characterized in that, include: Obtain historical test control data of the analysis object, perform data clustering of similar test objects, and form similar historical test control cluster data; Based on the historical test control clustering data of the same type, temperature change prediction analysis is performed for the same type of test objects to form temperature control prediction feature data of the same type of test. Real-time test control data is acquired, and temperature control analysis is performed by combining the temperature control prediction feature data of similar tests to form real-time temperature control prediction data.

2. The intelligent test control method for aging testing according to claim 1, characterized in that, The process of acquiring historical test control data of the analysis object, performing data clustering of similar test objects, and forming similar historical test control cluster data includes: Based on the historical test control data, extract the historical test data of different test objects; For different historical test data of the objects, obtain the corresponding object type parameter information; For different test objects, cluster analysis is performed based on the corresponding object type parameter information to form the same type of historical test control cluster data.

3. The intelligent test control method for aging testing according to claim 2, characterized in that, The process of obtaining corresponding object type parameter information from different historical test data of the objects includes: For different test objects, the following object type parameter information is extracted based on the corresponding historical test data of the object: Based on the position of the test object in the analysis object, the ratio of the size of the range defined by the plane perpendicular to the first direction of the test object in the first direction of the analysis coordinate system to the height of the higher limiting plane determined by the defined range is determined, forming the object's X-direction plane limiting position value; Based on the position of the test object in the analysis object, the ratio of the size of the range defined by the plane perpendicular to the second direction of the test object in the second direction of the analysis coordinate system to the height value of the higher limiting plane determined by the limited range is determined, forming the object's Y-direction plane limiting position value; Based on the position of the test object in the analysis object, the ratio of the size of the range defined by the plane perpendicular to the third direction in the analysis coordinate system to the height of the higher limiting plane determined by the defined range is determined, forming the Z-direction plane limiting position value of the object; Based on the range defined by the test object in three directions, a range space is formed, and the proportion of the test object's volume within the range space is determined.

4. The intelligent test control method for aging testing according to claim 3, characterized in that, The step of performing cluster analysis on different test objects based on the corresponding object type parameter information to form the same type of historical test control cluster data includes: For different test objects, an object type parameter matrix is ​​formed based on the corresponding object X-plane limiting position value, object Y-plane limiting position value, object Z-plane limiting position value, and object volume ratio value. Where n represents the number of the different test objects; The object type parameter matrix for different test objects Determine the identity matrix Object type similarity ,in, , express and The cosine similarity value; The similarity of object types among different test objects Mapped onto a number line, this forms an object similarity mapping axis; Density variation clustering analysis is performed along the similarity mapping axis of the objects to form historical test control clustering data of the same type.

5. The intelligent test control method for aging testing according to claim 4, characterized in that, The density variation clustering analysis along the similarity mapping axis of the objects to form the historical test control clustering data of the same type includes: Set the window sliding step size and density analysis radius; Starting from the smallest cosine similarity value as the density analysis center point on the object similarity mapping axis, the next density analysis center point is determined by sliding the window by the sliding step size along the axis each time. The number of cosine similarity values ​​involved in the range with the density analysis center point as the center and the density analysis radius as the radius is obtained until the window covers the largest cosine similarity value. A location-quantity curve is formed by fitting the quantity determined for each density analysis center point; Based on the location point-quantity curve, the average quantity value is determined, and all peak values ​​above the average quantity value on the location point-quantity curve are obtained and labeled as cluster similarity center values. For different cluster similarity center values, obtain the test objects and their corresponding historical test data within the allowable range of the unilateral allowable variation range centered on the cluster similarity center value and the cluster tolerance value, and form the corresponding cluster data of the same type of test objects. Different clusters of the same type of test objects are collected to form the same type of historical test control cluster data.

6. The intelligent test control method for aging testing according to claim 5, characterized in that, The step of performing temperature change prediction analysis on the same type of test objects based on the same historical test control clustering data to form temperature control prediction feature data for the same type of test objects includes: For different test objects in the cluster data of different test objects of the same type, determine any K predictive analysis time periods to form the basic time periods for predictive analysis of different types of objects under the test objects; For different types of objects in the clustered data of the same type of test objects, predictive analysis is performed on the basic time period, and the initial values ​​of control parameters for different control parameters at the initial time point of the time period are extracted. Initial temperature value And the final temperature value at the end of the period. Where m represents the number of different test objects in the cluster data of the same type of test objects, and i represents the number of different control parameters; For different test objects in the clustered data of the same type of test objects, according to the parameter information obtained under the corresponding K prediction analysis time periods, the object temperature change prediction analysis is performed to form the type object temperature prediction feature data corresponding to the test object. Perform type temperature change prediction analysis on the temperature prediction feature data of different test objects corresponding to the same type of test object cluster data to form type test temperature control prediction feature data; The temperature control prediction feature data of the same type of test is formed by aggregating the cluster data of different clusters of the same type of test objects.

7. The intelligent test control method for aging tests according to claim 6, characterized in that, The method involves performing temperature change prediction analysis on different test objects within the clustered data of the same type of test objects, based on parameter information obtained during the corresponding K prediction analysis time periods, to form type-specific object temperature prediction feature data for the test objects, including: Define the temperature prediction feature model for the specified object type: ,in, This is the initial temperature value. This represents the control parameter-related function corresponding to control parameter number i. To predict temperature values; The total number of parameters to be analyzed in the temperature prediction feature model of the object of the aforementioned type is determined, and the K prediction analysis time periods are grouped according to the total number of parameters to be analyzed to form a set of analysis groups; For different analysis groups, the temperature prediction feature model of the object type is analyzed based on the parameter information obtained under different prediction analysis time periods in the analysis group, and the corresponding analysis group type object temperature prediction feature relationship is formed. Based on the temperature prediction feature relationship of the object type determined by different analytical groups, an average fitting is performed to form the temperature prediction feature relationship of the object type.

8. The intelligent test control method for aging testing according to claim 7, characterized in that, The step of performing type-based temperature change prediction analysis on the temperature prediction feature data of different test objects corresponding to the same type of test objects in the clustered data of the same type of test objects, to form type-based test temperature control prediction feature data, includes: For the temperature prediction feature relationship of different test objects in the cluster data of the same type of test objects, extract all the constant terms in the relationship of different objects to form the corresponding object relationship constant matrix; The relational filtering is performed using the constant matrix of the relational expressions corresponding to different test objects in the following manner: Arbitrarily select one of the object relation constant matrices and determine its cosine similarity value with other object relation constant matrices. If the proportion of the number of cosine similar values ​​exceeding the similarity judgment threshold to the total number of cosine similar values ​​is not less than the selection ratio, then the object temperature prediction feature relation corresponding to all object relation constant matrices whose cosine similarity values ​​exceed the similarity judgment threshold is determined as the selection relation. Otherwise, continue to arbitrarily select one of the object relation constant matrices to judge the selection relation until the selection relation is determined. For the determined selection relationship, a homogenization fitting analysis is performed to form the predictive characteristic relationship of the temperature control of the test type.

9. The intelligent test control method for aging testing according to claim 8, characterized in that, The process of acquiring real-time test control data and combining it with similar test temperature control prediction feature data to perform temperature control analysis and form real-time temperature control prediction data includes: Based on the real-time test control data, the parameter values ​​of different object types of the real-time object are obtained, and the object type similarity is determined according to the identity matrix. The type test temperature control prediction feature relationship corresponding to the cluster similarity center value that is closest to the object type similarity is determined as the prediction relationship. Based on the real-time test control data, extract the real-time parameter values ​​of different control parameters, and determine the predicted temperature value according to the determined predictive characteristic relationship of the type of test temperature control.

10. An intelligent test control system for aging tests, employing the intelligent test control method for aging tests as described in any one of claims 1-9, characterized in that, include: The data acquisition unit is used to acquire historical test control data of the analysis object and real-time test control data of the real-time test object. The clustering analysis unit is used to cluster the data of similar test objects based on the historical test control data obtained by the data acquisition unit, and form similar historical test control cluster data. The feature analysis unit is used to perform temperature change prediction analysis on the same type of test objects based on the same type of historical test control clustering data formed by the clustering analysis unit, and to form the same type of test temperature control prediction feature data. The predictive analysis unit is used to perform temperature control analysis based on the real-time test control data acquired by the data acquisition unit and the similar test temperature control prediction feature data formed by the feature analysis unit, and to form real-time temperature control prediction data.

Images