Aging test method, equipment and medium

Abstract

The invention relates to an aging test method and device and a medium, and relates to the technical field of aging tests.The method comprises the steps that based on a distributed data acquisition system architecture, performance parameters of a to-be-tested product are synchronously acquired at a plurality of test points, data acquired at all the test points are synchronously integrated through timestamp alignment, and integrated data are obtained; based on a preset data analysis model, performing time sequence analysis on the continuously collected performance parameters, fitting a performance degradation curve by using a regression analysis method, determining a degradation function, and predicting the performance failure time of the to-be-tested product according to the degradation function; and determining a plurality of accelerated aging test schemes based on the performance failure time and a combination of a plurality of environmental factors, and executing all the accelerated aging test schemes through a simulator to obtain a plurality of life prediction results. The effect of improving the accuracy of performance evaluation and life prediction of the electronic product is achieved.

Description

Technical Field

[0001] The present invention relates to the technical field of aging test, and in particular to an aging test method, equipment and medium. Background Art

[0002] In the aging test of electronic products, how to effectively integrate normal use data and accelerated aging data, and consider various uncertainties under actual use conditions to improve the accuracy of remaining service life prediction, is the most difficult problem in the entire technical solution. Summary of the invention

[0003] In a first aspect, the present invention provides an aging test method, which mainly includes: Based on the distributed data acquisition system architecture, the performance parameters of the product to be tested are synchronously collected at multiple test points, and the data collected at all the test points are synchronously integrated through timestamp alignment to obtain integrated data; Based on a preset data analysis model, a time series analysis is performed on the continuously collected performance parameters, a performance degradation curve is fitted using a regression analysis method, a degradation function is determined, and the performance failure time of the product to be tested is predicted according to the degradation function; Based on the performance failure time and a combination of multiple environmental factors, multiple accelerated aging test schemes are determined, and all the accelerated aging test schemes are executed through a simulator to obtain multiple life prediction results.

[0004] In a second aspect, an electronic device is provided, comprising a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory communicate with each other via the communication bus; Memory, used to store computer programs; The processor is used to implement the steps of the aging test method described in any embodiment of the first aspect when executing the program stored in the memory.

[0005] In a third aspect, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps of the aging test method as described in any embodiment of the first aspect are implemented.

[0006] The technical solution provided by the embodiment of the present invention may have the following beneficial effects: By collecting the performance parameter characteristics of the product through aging tests and then executing all the accelerated aging test schemes through the simulator, the life of electronic products in various scenarios can be predicted, the accuracy of electronic product performance evaluation and life prediction can be improved, and an important basis for product quality control and maintenance decisions can be provided. BRIEF DESCRIPTION OF THE DRAWINGS

[0007] Figure 1A flowchart of an aging test method of the present invention; Figure 2 A schematic diagram of the structure of a computer device provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0008] The technical solution of the present invention will be clearly and completely described below in conjunction with the embodiments. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0009] like Figure 1-2 In this embodiment, an aging test method may specifically include: S101, based on the distributed data acquisition system architecture, synchronously collect performance parameters of the product to be tested at multiple test points, and synchronously integrate the data collected by all the test points through timestamp alignment to obtain integrated data.

[0010] According to the preset test point distribution, a distributed data acquisition system architecture is adopted to deploy data acquisition equipment and data transmission modules at each test point. The data acquisition equipment obtains the performance parameters of the product in real time, and uploads the collected data and the corresponding timestamp information to the central data processing platform through the data transmission module. The central data processing platform receives data from different test points, and uses the time series analysis algorithm to align the data with the timestamp according to the timestamp information of the data. The aligned data is classified and integrated according to the preset performance indicator system to obtain a comprehensive data set reflecting the overall performance of the product. Statistical learning algorithms (such as linear regression, support vector machine, nearest neighbor, logistic regression, decision tree, k-means, random forest, naive Bayes, dimensionality reduction, gradient enhancement) are used to model and analyze the comprehensive data set, and a product performance status evaluation model is established to quantify the overall performance level of the product. The overall performance evaluation results of the product are compared with the preset performance threshold. If it is lower than the threshold, it is judged as abnormal performance and triggers the early warning mechanism; if it is higher than the threshold, it is judged as normal performance. According to the judgment results of the product performance status, a performance analysis report is automatically generated, and the analysis results are fed back to the relevant departments to provide data support for product optimization and improvement.

[0011] In the specific implementation, a distributed data acquisition system architecture is adopted according to the geographical distribution of product test points. Data acquisition equipment and 4G wireless data transmission modules are deployed at 100 test points across the country. The data acquisition equipment obtains various performance parameters of the product in real time at a frequency of 1 second, such as temperature, humidity, voltage, current, etc., and uploads the collected data and the corresponding millisecond timestamp information to the central data processing platform in the cloud through the 4G network. The central data processing platform uses the Kafka message queue to receive data from different test points. According to the timestamp information of the data, the dynamic time warping (DTW) algorithm is used to align the data timestamps to eliminate the data timestamp deviation caused by network transmission delay. The aligned data is classified and integrated according to the preset performance indicator system, and a multi-dimensional data fusion algorithm is used to obtain a comprehensive data set reflecting the overall performance of the product. The support vector machine (SVM) algorithm is used to model and analyze the comprehensive data set, establish a product performance status evaluation model, and quantify the overall performance level of the product, with a score range of 0 to 100 points. The overall performance evaluation score of the product is compared with the preset performance threshold (such as 80 points). If it is lower than the threshold, it is judged as abnormal performance, triggering the early warning mechanism, and automatically sending SMS and email notifications to relevant personnel; if it is higher than the threshold, it is judged as normal performance. Based on the judgment results of the product performance status, a performance analysis report is automatically generated. The report contains the overall performance score of the product, the scores of various indicators, the cause analysis of abnormal indicators, etc. The analysis results are pushed to relevant departments such as product development and quality management through the API interface to provide data support and decision-making basis for product optimization and improvement.

[0012] In one embodiment, the above step S101 includes: According to the performance parameter characteristics of the product to be tested, a data acquisition model is established. Through the matching design of the test probe and the product connection point, stable and reliable signal acquisition is achieved to obtain the original performance parameter data stream. The data preprocessing technology is used to filter, denoise and normalize the original performance parameter data stream to obtain a standardized performance parameter data set. The key characteristic parameters are extracted from the standardized performance parameter data set through the feature extraction algorithm to construct the performance parameter feature vector. According to the performance parameter feature vector, the cluster analysis method is used to classify the performance parameters of electronic products to obtain product categories with different performance levels. For each performance level product category, the mean, variance, extreme value and other statistical quantities of each performance parameter are calculated through the statistical analysis method to determine the performance parameter benchmark value of the product in this category. In an extremely harsh environment, the host computer software communicates with the electronic product in real time to obtain the real-time performance parameter data stream, and compares it with the performance parameter benchmark value to determine whether the product performance has changed significantly. If the product performance has changed significantly, the law and trend of the performance parameter change are analyzed through the data mining algorithm to determine the degree and mechanism of the impact of the extreme environment on the product performance. According to the law of performance parameter changes and influencing mechanism, the simulation modeling method is used to build the performance degradation model of electronic products under extreme environments to predict the reliability and stability of products. Through the optimization algorithm, combined with the performance degradation model and measured data, the design parameters of electronic products are optimized to improve the reliability and stability of products under extreme environments, and the optimized product design scheme is generated. According to the performance parameter characteristics of the product to be tested, the performance parameter characteristic model is established, and the key performance parameters are extracted as the target parameters for data collection. According to the target parameters, a test probe that matches the product connection point is designed, and the contact stability and signal transmission reliability of the probe and the connection point are improved by optimizing the probe material and structure. The original performance parameter data stream collected by the test probe is obtained, and the data is preprocessed, including denoising and calibration, to improve the data quality. According to the performance parameter characteristic model, the preprocessed data is feature extracted to obtain the key characteristic parameters reflecting the product performance. The support vector machine algorithm is used to establish a mapping model between performance parameters and product quality, and the function of predicting the product quality level by performance parameters is realized. If the prediction result does not meet the preset quality threshold, it is judged as a quality defective product. The performance parameter characteristics of the defective product are analyzed through data mining to optimize the product design and production process. Continuously collect product performance parameter data, dynamically update performance parameter characteristic models and quality prediction models, realize online monitoring and early warning of product quality, and improve quality management level.

[0013] In the specific implementation, a data acquisition model is established according to the performance parameter characteristics of the product to be tested. For example, for a mobile phone, a data acquisition matrix can be established by testing its CPU frequency, memory capacity, battery capacity and other parameters. A high-precision oscilloscope is used to connect to 20 test points on the mobile phone motherboard to collect voltage signals of various performance parameters in real time at a sampling frequency of 100MHz to obtain the original parameter data stream. Then, a Butterworth low-pass filter is used to denoise the data, and the data is mapped to the [0,1] interval by the minimum-maximum normalization method to obtain a standardized performance parameter data set. The principal component analysis PCA algorithm is used to extract the five characteristic parameters with the highest contribution rate from the data set to form a performance parameter feature vector. Based on the K-means clustering algorithm, k=3 is set to cluster the feature vectors and divide the mobile phones into three performance levels: high, medium and low. For each level of mobile phone, the mean and standard deviation of each performance parameter are calculated as the performance benchmark value of that level. In a low temperature environment of -40℃, the performance data of the mobile phone is collected in real time through the USB interface and compared with the benchmark value. If the mean value of a certain parameter is found to be offset by more than 5%, the performance is judged to have changed significantly. The Apriori association rule mining algorithm is used to analyze the parameter change trend, and it is found that low temperature causes the battery capacity to drop by 20% and the CPU frequency fluctuation to increase by 30%. Based on this, a simulation model of mobile phone performance degradation in low temperature environment is established, and it is predicted that its mean time to failure (MTTF) will be reduced by 25%. Finally, the particle swarm optimization algorithm is used to optimize the heat dissipation structure and power management strategy of the mobile phone, so that its performance degradation at low temperature is controlled within 10%, and the optimized mobile phone structure design diagram and parameter configuration plan are output to provide guidance for product improvement.

[0014] In one embodiment, the above-mentioned step S101 also includes: real-time monitoring of the performance parameters of the integrated data according to a preset parameter threshold value, and when the performance parameter exceeds the parameter threshold value, triggering an alarm mechanism to generate abnormal status warning information including abnormal parameters, degree of exceeding the threshold value and occurrence time.

[0015] According to the product performance index requirements, the pre-set performance parameter thresholds are obtained; based on the preset data acquisition system, the performance parameter data during the operation of the product is obtained in real time; the obtained real-time performance parameter data is input into the pre-built data analysis model, which is trained using the support vector machine algorithm; the input performance parameter data is analyzed and anomaly detected in real time through the data analysis model to determine whether each performance parameter exceeds the preset threshold; if the judgment result is that the performance parameter exceeds the threshold, the alarm mechanism is triggered, the current time is obtained, and the name of the abnormal parameter and the degree of exceeding the threshold are determined; according to the name of the abnormal parameter, the degree of exceeding the threshold and the time when the abnormality occurs, abnormal status warning information is generated; the generated abnormal status warning information is sent to the preset alarm terminal, and the warning information is displayed through a visual interface to prompt relevant personnel to deal with the performance abnormality problem in a timely manner.

[0016] In the specific implementation, according to the product performance index requirements, the pre-set performance parameter thresholds are obtained, for example, the CPU usage threshold is set to 80%, and the memory usage threshold is set to 75%. The data collection system, such as the Prometheus monitoring system, collects performance parameter data during the product operation process every 5 seconds. The acquired real-time performance parameter data is input into the pre-built data analysis model, which is trained using the support vector machine SVM algorithm, using the Gaussian kernel function, the penalty factor C is set to 10, and the number of training set samples is 1000. The input performance parameter data is analyzed in real time and anomaly detected by the data analysis model to determine whether each performance parameter exceeds the preset threshold. For example, the current CPU usage is 85%, which exceeds the preset 80% threshold. If the judgment result is that the performance parameter exceeds the threshold, the alarm mechanism is triggered, and the current time is obtained as 2023-05-2014:30:25, and the abnormal parameter name is determined to be CPU usage, and the degree of exceeding the threshold is 5%. According to the abnormal parameter name, the degree of exceeding the threshold and the time when the abnormality occurred, abnormal status warning information is generated, such as "2023-05-2014:30:25, the CPU usage rate exceeds the threshold of 5%, and the current value is 85%". The generated abnormal status warning information is sent to the preset alarm terminal, such as the mobile phone APP of the operation and maintenance personnel. The warning information is displayed in the form of pop-up windows and sound prompts through the visual interface, prompting relevant personnel to deal with performance abnormalities in a timely manner, such as analyzing the reasons for the high CPU usage rate, adjusting the task scheduling strategy, and increasing CPU resource allocation.

[0017] S102, based on a preset data analysis model, performing time series analysis on the continuously collected performance parameters, fitting the performance degradation curve using a regression analysis method, determining a degradation function, and predicting the performance failure time of the product to be tested according to the degradation function.

[0018] Acquire multi-dimensional performance parameter data of the product and construct a time series data set; preprocess the data of the time series data set to remove outliers and noise data to obtain a processed time series data set; fit the performance degradation curve based on a preset multivariate regression analysis algorithm and the processed time series data set to obtain a performance degradation function; extract characteristic parameters from the performance degradation function, and determine the performance degradation law of the product based on the characteristic parameters; predict the failure time of the product based on the performance degradation law and a preset failure threshold; if the failure time is earlier than expected, trigger an early warning to indicate the need for product maintenance or replacement; continuously monitor product performance data, dynamically update the performance degradation function and failure time prediction, and ensure the accuracy of the prediction results.

[0019] In the specific implementation, when obtaining the multi-dimensional performance parameter data of the product, various sensors such as temperature sensors, pressure sensors, vibration sensors, etc. can be installed on the product to collect real-time data of the product during operation. These data may include the temperature, pressure, vibration frequency, etc. of the product. The data is collected every 5 minutes to form a time series data set. When preprocessing the collected time series data, the moving average filter method can be used to remove noise and outliers in the data, and the sliding window size is set to 10 to smooth the data curve. Then, the multivariate linear regression model is used to fit the product performance degradation curve, the independent variable is the product operation time, and the dependent variable is multiple performance parameters of the product, such as temperature, pressure, etc. The coefficients of the regression model are estimated by the least squares method to obtain the performance degradation function. From the fitted performance degradation function, characteristic parameters such as degradation rate, degradation acceleration, etc. are extracted to analyze the law of product performance degradation. According to the performance degradation law and the preset failure threshold, such as the temperature exceeding 100 degrees Celsius, the time when the product performance reaches failure is predicted. If the predicted failure time is earlier than the design life of the product, an early warning is triggered, indicating that the product needs to be maintained or replaced. During product operation, the product performance data is continuously monitored, and the performance degradation function and failure time prediction results are dynamically updated using the newly collected data to ensure the accuracy of the prediction. For example, when the predicted failure time is advanced by 10%, the performance degradation curve needs to be refitted and the prediction results updated.

[0020] S103, based on the performance failure time and a combination of multiple environmental factors, determining multiple accelerated aging test schemes, executing all the accelerated aging test schemes through a simulator, and obtaining multiple life prediction results.

[0021] Based on the predicted failure time, an accelerated aging test program is designed, and a combined loading method of multiple environmental factors such as temperature, humidity, and vibration is used to perform accelerated aging treatment on the product.

[0022] According to the historical failure data of the product and the environmental factor monitoring data, a failure time prediction model is established based on preset machine learning algorithms such as support vector machines or random forests to predict the failure time of the product. According to the predicted failure time, the acceleration ratio coefficient of the accelerated aging test is determined, and the equivalent time of the accelerated aging test is obtained by converting the acceleration ratio coefficient. The historical monitoring data of environmental factors such as temperature, humidity, and vibration of the product are obtained, and the loading level of each environmental factor in the accelerated aging test is determined according to the data distribution characteristics. The orthogonal experimental design method is adopted to design an accelerated aging test scheme with multiple environmental factor combinations according to the loading level of each environmental factor. Accelerated aging tests are carried out for different combinations of environmental factors, and each environmental parameter is monitored in real time during the test to ensure the controllability of the test process. After reaching the predetermined accelerated aging equivalent time, the product is subjected to performance testing and failure analysis to obtain data on product performance degradation and failure under different environmental factor combinations. By analyzing the accelerated aging test data under different environmental factor combinations, a product failure mechanism model is established to provide a basis for product design optimization and reliability improvement.

[0023] In the specific implementation, the failure time prediction model was first established by using the product historical failure data and environmental factor monitoring data, and the support vector machine algorithm was used. The model hyperparameters were optimized by grid search and cross-validation to improve the prediction accuracy. The model predicted that the failure time of the product was 1000 hours. According to the ratio of the predicted failure time to the actual use time, the acceleration coefficient of the accelerated aging test was determined to be 2.5. By converting the acceleration coefficient, the equivalent time of the accelerated aging test was obtained to be 400 hours. Then the historical monitoring data of the product environment was obtained, and it was found that the temperature data obeyed the normal distribution, with a mean of 25℃ and a standard deviation of 5℃; the humidity data obeyed the log-normal distribution, with a mean of 60% and a standard deviation of 10%; the vibration data obeyed the exponential distribution, with a mean of 2g. According to the data distribution characteristics, the loading levels of temperature in the accelerated aging test were determined to be 45℃, 55℃ and 65℃, the loading levels of humidity were 70%, 80% and 90%, and the loading levels of vibration were 4g, 6g and 8g. The L9 orthogonal table was used to design the accelerated aging test scheme for 9 combinations of environmental factors. For different combinations of environmental factors, a 400-hour accelerated aging test was carried out, and environmental parameters were monitored in real time to ensure that the fluctuation range of parameters such as temperature, humidity and vibration were controlled within ±2°C, ±5% and ±0.5g respectively. After the test, the product was subjected to performance testing and failure analysis, and it was found that the product failure rate was the highest under the combination of high temperature, high humidity and high vibration, reaching 15%; while the product failure rate was the lowest under the combination of low temperature, low humidity and low vibration, only 2%. By comparing and analyzing the accelerated aging test data under different combinations of environmental factors, a failure mechanism model based on the Arrhenius model was established, the key environmental factors affecting product failure were identified, and the degree of influence of each factor on failure was quantified, providing an important basis for subsequent product design optimization.

[0024] In one embodiment, the method further includes the steps of: continuously collecting the performance parameters during the accelerated aging process, comparing and analyzing the accelerated aging data with normal use data, establishing a quantitative relationship between the acceleration factor and the performance degradation rate, and establishing a performance prediction model based on machine learning based on the accelerated aging test data and a preset data mining algorithm, by inputting the performance parameter data collected in real time and using the established quantitative relationship between the acceleration factor and the performance degradation rate for correction, to obtain the remaining service life prediction result of the product under actual use conditions.

[0025] According to the key performance parameters of the product, an accelerated aging test plan is designed, accelerated aging conditions and test cycles are formulated, and performance parameter data are continuously collected. At the same time, the performance parameter data of the product under normal use conditions is obtained, and the accelerated aging data is compared and analyzed with the normal use data to calculate the performance degradation rate. A quantitative relationship model between the acceleration factor and the performance degradation rate is established through data mining algorithms such as regression analysis. Based on the accelerated aging test data, machine learning algorithms such as support vector machines and random forests are used to train the performance prediction model. During the actual use of the product, key performance parameter data is collected in real time as input to the performance prediction model. Using the established quantitative relationship model between the acceleration factor and the performance degradation rate, the performance prediction results are corrected to obtain the performance degradation trend of the product under actual use conditions. According to the performance degradation trend and the preset performance threshold, the remaining service life of the product is calculated to provide a decision-making basis for product maintenance and replacement.

[0026] In the specific implementation, an accelerated aging test plan is designed according to the key performance parameters of the product, such as battery capacity and response time. For example, the product is placed in an environment of 60 degrees Celsius and 90% relative humidity, and performance data is continuously collected. At the same time, the performance data of the product under normal use conditions such as 25 degrees Celsius and 50% relative humidity is obtained, and the performance degradation rate is calculated by comparison and analysis. A quantitative relationship model between the acceleration factor and the performance degradation rate is established through multivariate linear regression, such as Y=8X1+6X2+2X3 (Y is the performance degradation rate, X1, X2, and X3 are temperature, humidity, and vibration acceleration factors, respectively). Based on the accelerated aging data, the performance prediction model is trained with a support vector machine, and the performance data is collected in real time and input into the model to predict the performance. The prediction results are corrected using the acceleration factor model Y=8X1+6X2+2X3 to obtain the performance degradation trend under actual use conditions. If the performance is lower than the preset threshold, such as 80% of the initial performance, the product needs to be maintained or replaced, thereby realizing the remaining service life prediction and providing a basis for operation and maintenance decisions.

[0027] like Figure 2 As shown, Figure 2 5 is a schematic block diagram of a computer device provided in an embodiment of the present application. The computer device 500 may be a terminal or a server, wherein the terminal may be an electronic device with communication functions such as a smart phone, a tablet computer, a laptop computer, a desktop computer, a personal digital assistant, and a wearable device. The server may be an independent server or a server cluster composed of multiple servers.

[0028] The computer device 500 includes a processor 502 , a memory, and a network interface 505 connected via a system bus 501 , wherein the memory may include a non-volatile storage medium 503 and an internal memory 504 .

[0029] The non-volatile storage medium 503 may store an operating system 5031 and a computer program 5032. When the computer program 5032 is executed, the processor 502 may execute an aging test method.

[0030] The processor 502 is used to provide computing and control capabilities to support the operation of the entire computer device 500 .

[0031] The internal memory 504 provides an environment for the operation of the computer program 5032 in the non-volatile storage medium 503. When the computer program 5032 is executed by the processor 502, the processor 502 can execute an aging test method.

[0032] The network interface 505 is used to communicate with other devices over the network. Those skilled in the art will appreciate that the above structure is only a block diagram of a portion of the structure related to the present application solution, and does not constitute a limitation on the computer device 500 to which the present application solution is applied. The specific computer device 500 may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0033] It should be understood that in the embodiment of the present application, the processor 502 may be a central processing unit (CPU), and the processor 502 may also be other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. Among them, the general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0034] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. An aging test method, characterized in that: The method comprises: Based on the distributed data acquisition system architecture, the performance parameters of the product to be tested are synchronously collected at multiple test points, and the data collected at all the test points are synchronously integrated through timestamp alignment to obtain integrated data; Based on a preset data analysis model, a time series analysis is performed on the continuously collected performance parameters, a performance degradation curve is fitted using a regression analysis method, a degradation function is determined, and the performance failure time of the product to be tested is predicted according to the degradation function; Based on the performance failure time and a combination of multiple environmental factors, multiple accelerated aging test schemes are determined, and all the accelerated aging test schemes are executed through a simulator to obtain multiple life prediction results.

2. The method according to claim 1, characterized in that Based on the distributed data acquisition system architecture, the performance parameters of the product to be tested are synchronously collected at multiple test points, and the data collected at all the test points are synchronously integrated through timestamp alignment to obtain integrated data, including: A data acquisition model is established according to the performance parameter characteristics of the product to be tested, and an original performance parameter data stream is acquired at the connection point between the test probe and the product connection point based on the data acquisition model as the performance parameter.

3. The method according to claim 1, characterized in that Based on the distributed data acquisition system architecture, the performance parameters of the product to be tested are synchronously collected at multiple test points, and the data collected at all the test points are synchronously integrated through time stamp alignment to obtain integrated data, and further includes: The performance parameters of the integrated data are monitored in real time according to preset parameter thresholds. When the performance parameters exceed the parameter thresholds, an alarm mechanism is triggered to generate abnormal status warning information including abnormal parameters, degree of exceeding the thresholds and occurrence time.

4. The method according to claim 1, characterized in that: Based on the distributed data acquisition system architecture, the performance parameters of the product to be tested are synchronously collected at multiple test points, and the data collected at all the test points are synchronously integrated through timestamp alignment to obtain integrated data, including: According to the preset test point distribution, a distributed data acquisition system architecture is adopted to deploy data acquisition equipment and data transmission modules at each test point; The performance parameters of the product to be tested are collected in real time by the data collection device, and the collected performance parameters and corresponding timestamp information are uploaded to the central data processing platform through the data transmission module, wherein the central data processing platform uses the timestamp information to perform timestamp alignment on the performance parameters based on a preset time series analysis algorithm, and the aligned data are classified and integrated according to a preset performance indicator system to obtain the integrated data.

5. The method according to claim 2, characterized in that: The step of establishing a data acquisition model according to the performance parameter characteristics of the product to be tested, and acquiring an original performance parameter data stream as the performance parameter at the connection point between the test probe and the product connection point based on the data acquisition model, comprises: According to the product performance index requirements, obtain the pre-set performance parameter thresholds; Based on the preset data acquisition system, the performance parameter data of the product during operation can be obtained in real time; The acquired real-time performance parameter data is input into a pre-built data analysis model, which is trained using a support vector machine algorithm; The data analysis model performs real-time analysis and anomaly detection on the input performance parameter data to determine whether each performance parameter exceeds the preset threshold; If the judgment result is that the performance parameter exceeds the threshold, the alarm mechanism is triggered, the current time is obtained, and the name of the abnormal parameter and the degree of exceeding the threshold are determined; Generate abnormal status warning information based on abnormal parameter name, degree of exceeding threshold and abnormal occurrence time; The generated abnormal status warning information is sent to the preset alarm terminal, and the warning information is displayed through a visual interface.

6. The method according to claim 1, characterized in that The method includes performing time series analysis on the continuously collected performance parameters based on a preset data analysis model, fitting the performance degradation curve using a regression analysis method, determining a degradation function, and predicting the performance failure time of the product to be tested according to the degradation function, including: Obtain multi-dimensional performance parameter data of products and construct time series data sets; Preprocess the data of the time series data set to remove outliers and noise data to obtain the processed time series data set; Based on the preset multiple regression analysis algorithm and the processed time series data set, the performance degradation curve is fitted to obtain the performance degradation function; Extracting characteristic parameters from the performance degradation function, and determining the performance degradation law of the product according to the characteristic parameters; Predicting the failure time of the product according to the performance degradation law and the preset failure threshold; If the failure time is earlier than expected, an early warning is triggered, indicating that product maintenance or replacement is required; Continuously monitor product performance data, dynamically update performance degradation functions and failure time predictions, and ensure the accuracy of prediction results.

7. The method according to claim 1, characterized in that Based on the performance failure time and a combination of multiple environmental factors, multiple accelerated aging test schemes are determined, and all the accelerated aging test schemes are executed by the simulator to obtain multiple life prediction results, including: According to the historical failure data of the product and the environmental factor monitoring data, a failure time prediction model is established based on the preset learning algorithm to predict the failure time of the product; According to the predicted failure time, the acceleration proportional coefficient of the accelerated aging test is determined, and the equivalent time of the accelerated aging test is obtained by converting the acceleration proportional coefficient; Obtain historical monitoring data of environmental factors such as temperature, humidity and vibration of the product, and determine the loading level of each environmental factor in the accelerated aging test based on the data distribution characteristics; Adopting the orthogonal test design method, according to the loading level of each environmental factor, design an accelerated aging test scheme with multiple environmental factors combined loading; Carry out accelerated aging tests for different combinations of environmental factors, and monitor various environmental parameters in real time during the test; After reaching the predetermined accelerated aging equivalent time, the product is subjected to performance testing and failure analysis to obtain data on product performance degradation and failure under different combinations of environmental factors; By analyzing the accelerated aging test data under different environmental factor combinations, a product failure mechanism model is established.

8. The method according to claim 1, characterized in that The method further comprises: During the accelerated aging process, the performance parameters are continuously collected, the accelerated aging data is compared and analyzed with the normal use data, and a quantitative relationship between the acceleration factor and the performance degradation rate is established. Based on the accelerated aging test data and a preset data mining algorithm, a performance prediction model based on a preset machine learning is established. By inputting the performance parameter data collected in real time and using the established quantitative relationship between the acceleration factor and the performance degradation rate for correction, a prediction result of the remaining service life of the product under actual use conditions is obtained.

9. A computer device, characterized in that: It includes a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory communicate with each other through the communication bus; Memory, used to store computer programs; A processor, for implementing the steps of the method described in any one of claims 1 to 8 when executing a program stored in a memory.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 8 are implemented.

Images