Intelligent evaluation method and system for environment and reliability test based on big data
By analyzing the correlation between historical product performance and environmental stress, a performance degradation curve is constructed and inflection point characteristics are identified, which solves the problem of inaccurate evaluation results in existing technologies and achieves high-precision reliability test evaluation.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- 深圳市中天泽检测技术有限公司
- Filing Date
- 2026-03-17
- Publication Date
- 2026-06-16
AI Technical Summary
Existing environmental and reliability testing methods cannot adapt to the individual characteristics of different products, resulting in low accuracy of the evaluation results.
By analyzing the correlation between the historical performance of the target product and environmental stress, a performance degradation curve is constructed and the performance inflection point characteristics are identified. Combined with current experimental environment data, the cumulative damage is assessed, and an experimental analysis report is generated.
It improves the accuracy of intelligent assessment of environmental and reliability tests, captures the key point where product performance changes from stable to rapid degradation, and provides an assessment of the actual damage state of the product under the current test environment.
Smart Images
Figure CN122221201A_ABST
Abstract
Description
Technical Field
[0001] This invention relates to a method and system for intelligent evaluation of environmental and reliability testing based on big data, belonging to the field of big data analysis technology. Background Technology
[0002] Intelligent assessment of environmental and reliability testing refers to a technology that uses data analysis to quantitatively analyze and predict the reliability of products under simulated environmental stress. This technology is mainly used in fields with extremely high reliability requirements, such as aerospace, automotive electronics, and precision instruments.
[0003] Current commonly used evaluation methods are primarily based on fixed test profiles and standardized testing procedures. During testing, products are placed under preset environmental stress conditions, and technicians record changes in performance parameters according to established procedures. After the test, reliability assessment is completed by comparing historical data thresholds or performing routine statistical analysis. However, because uniform test conditions are used, they cannot accommodate the individual characteristics of different products, resulting in insufficient accuracy of the evaluation results. Summary of the Invention
[0004] This invention provides a method and system for intelligent evaluation of environmental and reliability testing based on big data, the main purpose of which is to improve the accuracy of intelligent evaluation of environmental and reliability testing.
[0005] To achieve the above objectives, the present invention provides an intelligent evaluation method for environmental and reliability testing based on big data, comprising:
[0006] The correlation characteristics between the product performance of the target product and environmental stress are analyzed, wherein the correlation characteristics are obtained based on the test analysis of the target product under historical environmental conditions; Based on the aforementioned correlation features, a performance degradation curve for the target product is constructed, and the performance inflection point features of the target product are identified using the performance degradation curve. After collecting product data of the target product under the current experimental environment, and combining the performance inflection point characteristics, the cumulative damage of the target product under the current experimental environment is analyzed to generate an experimental analysis report of the target product under the current experimental environment.
[0007] Optionally, based on the performance inflection point characteristics, the cumulative damage of the target product under the current experimental environment is analyzed, including: Extract multi-dimensional environmental stress parameters of the target product from the current experimental environment data; Identify the parameter variation trends of the multi-dimensional environmental stress parameters to divide the current experimental duration corresponding to the target product into multiple stress units, thereby obtaining a stress evaluation unit; Based on the performance inflection point characteristics, the damage increment of the target product corresponding to each unit in the stress assessment unit is calculated to obtain the multi-unit damage increment; Based on the multi-unit damage increment, the cumulative damage of the target product under the current experimental environment data is evaluated.
[0008] Optionally, based on the performance inflection point characteristics, the damage increment of the target product corresponding to each unit in the stress assessment unit is calculated to obtain the multi-unit damage increment, including: Extract the environmental stress characteristic value corresponding to each unit from the stress assessment unit; Calculate the damage component of each element under a single stress. Based on the performance inflection point characteristics, the basic damage components are compositely corrected to obtain the comprehensive damage increment of each unit. The comprehensive damage increment is sorted by time series to obtain the multi-unit damage increment.
[0009] Optionally, based on the correlation features, a performance degradation curve for the target product is constructed, including: Based on the aforementioned correlation features, key data points of the target product during performance degradation are identified; Using the key data points, construct the initial performance degradation curve of the target product; Identify the performance inflection point in the initial performance degradation curve; Based on the performance inflection point, a performance degradation curve for the target product is constructed.
[0010] Optionally, identifying the performance inflection point in the initial performance degradation curve includes: Calculate the first and second derivatives of the initial performance degradation curve; The performance inflection point in the initial performance degradation curve is identified using the first and second derivatives.
[0011] Optionally, the performance inflection point in the initial performance degradation curve is identified using the first derivative and the second derivative, including: The performance degradation rate of the target product is analyzed using the first derivative. The second derivative is used to analyze the performance degradation acceleration of the target product; Based on the performance degradation rate and the performance degradation acceleration, the performance inflection point in the initial performance degradation curve is determined.
[0012] Optionally, analyze the correlation characteristics between the target product's performance and environmental stress, including: Analyze the core performance indicators of the target product and the corresponding environmental stress types; Based on the core performance indicators and the types of environmental stress, the correlation characteristics between the product performance and environmental stress of the target product are determined.
[0013] Optionally, the performance degradation curve can be used to identify the performance inflection point characteristics of the target product, including: Query the inflection point parameters of the performance inflection point in the performance degradation curve; Based on the inflection point parameters, the performance inflection point characteristics of the target product are identified.
[0014] Optionally, a test analysis report of the target product under the current experimental environment is generated, including: Query the experimental evaluation data of the target product under the current experimental environment; Using the experimental evaluation data, construct an experimental analysis report of the target product under the current experimental environment.
[0015] To address the above problems, this invention also provides an intelligent evaluation system for environmental and reliability testing based on big data, the system comprising: The correlation feature analysis module is used to analyze the correlation features between the product performance of the target product and environmental stress, wherein the correlation features are obtained based on the test analysis of the target product under historical environmental conditions; The inflection point feature recognition module is used to construct the performance degradation curve of the target product based on the associated features, and to identify the performance inflection point features of the target product using the performance degradation curve. The reliability assessment module is used to collect product data of the target product under the current experimental environment, and then, in combination with the performance inflection point characteristics, analyze the cumulative damage of the target product under the current experimental environment to generate a test analysis report of the target product under the current experimental environment.
[0016] Compared to the problems described in the background technology, this invention first analyzes the correlation characteristics between the historical performance of the target product and environmental stress. This step uses historical test data as the core and leverages data correlation analysis technology to uncover the inherent laws governing the changes in performance indicators with environmental stress. Then, based on the correlation characteristics, a performance degradation curve is constructed and performance inflection point characteristics are identified. This transforms the abstract correlation characteristics into an intuitive performance degradation curve, clearly presenting the complete trajectory of the product from normal operation to gradual degradation. The accurate identification of performance inflection point characteristics captures the critical node where product performance transitions from stable to rapid degradation. Next, this invention collects current experimental environment data to ensure the authenticity and real-time nature of the stress data and uses inflection point characteristics to assess the cumulative damage degree, intuitively reflecting the actual damage state of the product under the current experimental environment, thus completing the transformation from "historical analysis" to "current assessment." Therefore, this invention can improve the accuracy of intelligent assessment of environmental and reliability testing. Attached Figure Description
[0017] Figure 1 A flowchart illustrating an intelligent evaluation method for environmental and reliability testing based on big data, provided in an embodiment of the present invention; Figure 2 A schematic diagram of modules for implementing the intelligent evaluation method for environmental and reliability testing based on big data, provided in an embodiment of the present invention; Figure 3 A schematic diagram of a computer device for an intelligent evaluation method for environmental and reliability testing based on big data, provided in an embodiment of the present invention.
[0018] The objectives, features, and advantages of this invention will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation
[0019] It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
[0020] This application provides an intelligent evaluation method for environmental and reliability testing based on big data. The executing entity of this intelligent evaluation method includes, but is not limited to, at least one of the following electronic devices that can be configured to execute the method provided in this application: a server, a terminal, etc. In other words, the intelligent evaluation method for environmental and reliability testing based on big data can be executed by software or hardware installed on a terminal device or a server device. The server includes, but is not limited to, a single server, a server cluster, a cloud server, or a cloud server cluster.
[0021] Reference Figure 1 The diagram shown is a flowchart illustrating an intelligent evaluation method for environmental and reliability testing based on big data, provided in an embodiment of the present invention. In this embodiment, the intelligent evaluation method for environmental and reliability testing based on big data includes: S1. Analyze the correlation characteristics between the product performance of the target product and environmental stress, wherein the correlation characteristics are obtained based on the test analysis of the target product under historical environmental conditions.
[0022] The embodiments of the present invention can identify the inherent laws between product performance changes and external environmental stress by analyzing the correlation characteristics between the product performance of the target product and environmental stress. For example, in the temperature cycling test of the circuit board, by analyzing the correspondence between different temperature ranges and their resistance value changes, the specific impact mode of temperature fluctuation on circuit performance can be clarified.
[0023] The target product refers to the product to be tested or analyzed in environmental reliability experiments, such as circuit boards, server motherboard chips, etc. The correlation features refer to the corresponding change patterns between various environmental stresses of the target product in reliability experiments, including power consumption, response speed and output accuracy under different environmental stresses alone or in combination. It should be noted that in this embodiment, the correlation features are obtained based on the test analysis of the target product under historical environments.
[0024] As an embodiment of the present invention, the correlation characteristics between the product performance of the target product and environmental stress are analyzed, including: Analyze the core performance indicators of the target product and the corresponding environmental stress types; Based on the core performance indicators and the types of environmental stress, the correlation characteristics between the product performance and environmental stress of the target product are determined.
[0025] The core performance indicators refer to parameters that can directly or obviously reflect the functional degradation of the target product, such as operational stability parameters, functional output error values, and structural deformation. The environmental stress types refer to various physical or chemical environmental factors that can damage the structure or function of the target product in product life testing or actual use, such as high and low temperature cycle stress, alternating humidity stress, and continuous vibration stress.
[0026] Optionally, in this embodiment of the application, the performance indicators whose weights are greater than a preset threshold in the historical analysis record data of the target product are selected as core performance indicators. Optionally, the weights of the performance indicators can be calculated by weighted average method, and the preset threshold can be set to 0.6. Further, the environmental stress type in this application can be determined by principal component analysis. Specifically, the cumulative variance contribution rate of each stress in the target product can be calculated by principal component analysis, and the environmental stress type with a cumulative variance contribution rate greater than 85% is retained as the final environmental stress type corresponding to the environmental stress type.
[0027] Furthermore, as an embodiment of the present invention, based on the core performance indicators and the type of environmental stress, the correlation characteristics between the product performance and environmental stress of the target product are determined, including: Calculate the fluctuation range of the core performance indicators and the change in stress intensity of different types of environmental stress. Based on the fluctuation range of the aforementioned indicators and the change in stress intensity, the correlation characteristics between the historical performance of the target product and environmental stress are determined.
[0028] The fluctuation range of the indicator refers to the specific fluctuation value of the parameter that reflects the functional degradation of the target product. For example, if the operational stability changes from 95% to 90%, the fluctuation is 5%. The change in stress intensity refers to the change in stress in the production environment of the target product, such as the duration of continuous vibration, the amplitude of vibration, and changes in high and low temperatures in the environment.
[0029] Optionally, when calculating the fluctuation range of the indicators, the core performance indicators can be windowed using the windowing method. Then, the difference between the maximum and minimum values of the core performance indicators within each window can be calculated to obtain the fluctuation range of the indicators. The calculation principle of the stress intensity change is the same as that of the index fluctuation range, so it will not be elaborated further. When analyzing the correlation characteristics, the Pearson correlation coefficient can be used to calculate the correlation strength between the performance fluctuation range and the stress intensity change. By setting a correlation threshold, such as considering a strong correlation if the absolute value of the correlation coefficient is greater than 0.7, it is possible to determine which stress is the key driving factor leading to the decline of a specific performance indicator, thereby ultimately extracting the correlation characteristics with clear physical meaning.
[0030] S2. Based on the correlation features, construct the performance degradation curve of the target product, and use the performance degradation curve to identify the performance inflection point features of the target product.
[0031] This invention, through constructing a performance degradation curve of the target product based on the aforementioned correlation features, can transform the correlation features between the historical performance of the target product and stress into an intuitive curve form, thereby allowing users to clearly understand the degradation pattern of product performance under environmental stress.
[0032] The performance degradation curve refers to the trajectory curve of how the performance parameters of a product change with the increase of test time or stress cycle number.
[0033] As an embodiment of the present invention, constructing the performance degradation curve of the target product based on the associated features includes: Based on the aforementioned correlation features, key data points of the target product during performance degradation are identified; Using the key data points, construct the initial performance degradation curve of the target product; Identify the performance inflection point in the initial performance degradation curve; Based on the performance inflection point, a performance degradation curve for the target product is constructed.
[0034] The key data points refer to representative data points that significantly reflect the correlation between performance and environmental stress during the performance degradation process of the target product. The initial performance degradation curve is a preliminary curve generated by fitting the selected key data points along a time axis using a curve fitting algorithm, used to initially reflect the decay law of the target product's core performance indicators over time. The performance inflection point refers to the critical time point in the initial performance degradation curve where the rate of performance degradation changes significantly (e.g., from slow degradation to rapid deterioration), corresponding to the abrupt change in the curve slope.
[0035] In detail, the data can be segmented using a sliding window algorithm, and the extreme points and abrupt changes in the rate of change of performance parameters within each data segment can be selected as key data points. These points can accurately reflect the key stage characteristics of performance degradation. After obtaining the key data points, the initial performance degradation curve is constructed using cubic spline interpolation.
[0036] Optionally, identifying the performance inflection point in the initial performance degradation curve includes: Calculate the first and second derivatives of the initial performance degradation curve; The performance inflection point in the initial performance degradation curve is identified using the first and second derivatives.
[0037] Furthermore, as another embodiment of the present invention, identifying the performance inflection point in the initial performance degradation curve using the first derivative and the second derivative includes: The performance degradation rate of the target product is analyzed using the first derivative. The second derivative is used to analyze the performance degradation acceleration of the target product; Based on the performance degradation rate and the performance degradation acceleration, the performance inflection point in the initial performance degradation curve is determined.
[0038] In detail, when analyzing the rate of performance degradation, you can first look up the calculated value of the first derivative. The smaller the value, the faster the corresponding rate of performance degradation. When analyzing the acceleration of performance degradation, you can first look up the calculated value of the second derivative. The larger the value, the faster the acceleration of performance degradation. When identifying the performance inflection point, you can first filter out the time points when the second derivative changes from positive to negative or from negative to positive, and then check whether the first derivative at that time point shows a significant jump. If both conditions are met, then the time point is determined to be the performance inflection point.
[0039] Furthermore, by utilizing the performance degradation curve, this embodiment of the invention can identify the performance inflection point characteristics of the target product, thus determining the critical turning point from quantitative to qualitative change in product performance and providing a basis for assessing the critical state of reliability. Taking plated through-holes on a circuit board as an example, when the number of temperature cycles reaches approximately 800, the interconnect resistance value will suddenly increase rapidly. This performance inflection point corresponds to the failure state where microcracks propagate to the critical size. Accurately identifying this feature can provide early warning of structural fatigue failures.
[0040] The performance inflection point characteristic refers to the key turning point on the performance degradation curve that represents the transition of a product from a slow degradation stage to an accelerated failure stage.
[0041] As an embodiment of the present invention, the performance inflection point characteristics of the target product are identified using the performance degradation curve, including: Query the inflection point parameters of the performance inflection point in the performance degradation curve; Based on the inflection point parameters, the performance inflection point characteristics of the target product are identified.
[0042] In detail, specific parameters corresponding to each inflection point can be extracted from the curve, including the time coordinate of the inflection point, the core performance index value at that time point, and the intensity data of environmental stress during the same period. After obtaining the inflection point parameters, the type of inflection point needs to be determined based on the characteristics of these parameters. For example, if the degradation rate before the inflection point is much smaller than the degradation rate after the inflection point, it indicates that the product performance has shifted from a slow degradation stage to an accelerated degradation stage. This type of inflection point can be classified as an accelerated inflection point. Conversely, if the inflection point marks the beginning of the initial degradation of performance from a relatively stable state, it can be defined as an initial inflection point. Then, based on the performance inflection point type, the performance inflection point characteristics of the target product can be identified. Specifically, for different types of inflection points, their corresponding time coordinates, performance index values, degradation rate changes, and associated environmental stress characteristics can be integrated to form a feature description. For example, for an accelerated degradation type inflection point, the time node of its occurrence, the attenuation ratio of the performance index compared to the initial value, the multiple of the degradation rate increase, and the main type of environmental stress that triggered the inflection point can be clearly identified, thereby fully presenting the indicative characteristics of the inflection point in the performance degradation process.
[0043] S3. After collecting product data of the target product under the current experimental environment, and combining the performance inflection point characteristics, analyze the cumulative damage of the target product under the current experimental environment to generate an experimental analysis report of the target product under the current experimental environment.
[0044] This invention can acquire real-time environmental stress data of the target product during the test by collecting the current experimental environment data of the target product, providing real input for subsequent reliability assessment.
[0045] In detail, the current experimental environment data can be obtained in real time by a data acquisition system through temperature, vibration, and humidity sensors arranged in the test area, as well as detection elements such as strain gauges and thermocouples installed on the product body, recording environmental stress parameters and product response data during the test process.
[0046] Furthermore, by combining the performance inflection point characteristics, the present invention analyzes the cumulative damage of the target product under the current experimental environment. This allows the stress load borne by the product under the current experimental environment to be quantitatively converted into a cumulative damage value that represents its performance degradation or health deterioration, thus intuitively reflecting the actual damage state of the product under the current experimental stress.
[0047] As an embodiment of the present invention, the cumulative damage of the target product under the current experimental environment is analyzed in conjunction with the performance inflection point characteristics, including: Extract multi-dimensional environmental stress parameters of the target product from the current experimental environment data; Identify the parameter variation trends of the multi-dimensional environmental stress parameters to divide the current experimental duration corresponding to the target product into multiple stress units, thereby obtaining a stress evaluation unit; Based on the performance inflection point characteristics, the damage increment of the target product corresponding to each unit in the stress assessment unit is calculated to obtain the multi-unit damage increment; Based on the multi-unit damage increment, the cumulative damage of the target product under the current experimental environment data is evaluated.
[0048] The multi-dimensional environmental stress parameters include real-time temperature values, vibration parameters, and humidity percentages.
[0049] In detail, multi-source sensors integrated into the experimental environment (such as thermocouples, accelerometers, and humidity sensors) can be used to collect raw data streams in real time, and key environmental stress parameters directly related to the product failure mechanism can be extracted from them. During the division of stress assessment units, a Bayesian change point detection algorithm can be used to analyze the trend characteristics of the filtered parameter curves. When the rate of change of temperature, vibration, or humidity parameters exceeds the threshold of 0.5% / min, it is identified as a stress state transition point. This divides the test duration into multiple time segments with relatively stable stress characteristics, forming stress assessment units. The damage increment sequence of each stress unit is substituted into a linear cumulative damage model (such as Miner's rule), and the total cumulative damage is calculated by summing them in chronological order using the following formula:
[0050] Where E represents the cumulative damage degree, and n represents the number of stress assessment elements. This represents the element damage increment of the i-th stress element.
[0051] Optionally, based on the performance inflection point characteristics, the damage increment of the target product corresponding to each unit in the stress assessment unit is calculated to obtain the multi-unit damage increment, including: Extract the environmental stress characteristic value corresponding to each unit from the stress assessment unit; Based on the characteristic value of environmental stress, the basic damage component of each element under a single stress is calculated. Based on the performance inflection point characteristics, the basic damage components are compositely corrected to obtain the comprehensive damage increment of each unit. The comprehensive damage increment is sorted by time series to obtain the multi-unit damage increment.
[0052] The environmental stress characteristic values include temperature extremes, root mean square vibration values, and humidity saturation.
[0053] In detail, the raw environmental stress data for each unit can be collected in real time by sensors or retrieved from historical databases. Statistical feature extraction techniques are used to extract core feature parameters such as peak value, mean value, and duration of action. These parameters are then directly integrated into the environmental stress feature value of the unit. Combined with the identified performance inflection point features (such as the abrupt change in the performance degradation rate before and after the inflection point), the corresponding correction coefficients are determined (a fixed coefficient is used before the inflection point based on the normal degradation trend, and the coefficient is adjusted after the inflection point based on the change in degradation acceleration). A weighted correction algorithm is used to adjust the basic damage component, i.e., the comprehensive damage increment = basic damage component × inflection point correction coefficient, finally obtaining the comprehensive damage increment of each unit. The collection timestamp corresponding to the comprehensive damage increment of each unit is extracted, and the comprehensive damage increments of all units are arranged in chronological order using a time series sorting algorithm to ensure that the sorting result completely matches the time process of the target product's performance degradation, forming ordered multi-unit damage increment data.
[0054] Furthermore, as another embodiment of the present invention, the calculation formula for the basic damage component is as follows:
[0055] in, Indicates the basic damage component. Indicates the start time of the experiment. S(t) represents the end time of the experiment, and S(t) represents the environmental stress level as a function of time. This indicates the predicted damage state of the product under the current environmental stress level, indicating potential failure.
[0056] It should be explained that the basic damage component refers to the degree of basic damage accumulated by the product under environmental stress within a single environmental stress unit, with a value range between 0 and 1. The experiment start time refers to the starting time of the stress unit to be calculated, such as the start time of a certain round of high and low temperature cycle test. The experiment end time refers to the end time of the stress unit to be calculated, such as the end time of a certain round of high and low temperature cycle test. The environmental stress level refers to the actual environmental stress value that the product is subjected to at time t. The predicted damage state refers to the total time of the cumulative stress cycles required for the product to fail under the environmental stress level at time t.
[0057] The core of this formula is to calculate the degree of damage to the product under stress conditions within a certain test period. Specifically, the entire reliability test process is divided into multiple time units according to stress type. Then, within each unit time, the environmental stress at each moment is collected in real time, the total number of cycles required for product failure under that stress is predicted, and finally, by integration, the instantaneous damage at each moment within the unit time is summed to obtain the total damage within that unit.
[0058] Furthermore, by generating a test analysis report of the target product under the current experimental environment, the embodiments of the present invention can intuitively present the product test reliability results, providing a direct reference for whether the product meets the usage standards.
[0059] As an embodiment of the present invention, generating a test analysis report of the target product under the current experimental environment includes: Query the experimental evaluation data of the target product under the current experimental environment; Using the experimental evaluation data, construct an experimental analysis report of the target product under the current experimental environment.
[0060] The experimental evaluation data refers to a series of data generated during the environmental reliability testing of the target product.
[0061] In detail, the experimental evaluation data can be obtained by querying the database that records the experimental data during the experiment; the experimental data is organized using Excel, and the specific parameters in the experiment and the corresponding performance of the product are organized into corresponding tables. Then, based on the experimental results and historical experience, a reliability assessment is conducted, and after scoring or providing summary opinions, an experimental analysis report is generated.
[0062] like Figure 2 The diagram shown is a functional block diagram of the intelligent evaluation system for environmental and reliability testing based on big data according to the present invention.
[0063] The intelligent evaluation system 200 for environmental and reliability testing based on big data described in this invention can be installed in an electronic device. Depending on the functions implemented, the intelligent evaluation system can control the correlation feature analysis module 201, the inflection point feature recognition module 202, and the reliability evaluation module 203. The module described in this invention can also be called a unit, which refers to a series of computer program segments that can be executed by the processor of an electronic device and can perform a fixed function, stored in the memory of the electronic device.
[0064] In this embodiment of the invention, the functions of each module / unit are as follows: The correlation feature analysis module 201 is used to analyze the correlation features between the product performance of the target product and environmental stress, wherein the correlation features are obtained based on the test analysis of the target product under historical environmental conditions; The inflection point feature recognition module 202 is used to construct the performance degradation curve of the target product based on the associated features, and to identify the performance inflection point features of the target product using the performance degradation curve. The reliability assessment module 203 is used to collect product data of the target product under the current experimental environment, and then, in combination with the performance inflection point characteristics, analyze the cumulative damage of the target product under the current experimental environment to generate a test analysis report of the target product under the current experimental environment.
[0065] In detail, the modules in the big data-based intelligent evaluation system 200 for environmental and reliability testing described in this embodiment of the invention employ the same methods as described above. Figure 1 The method uses the same technical means as the intelligent evaluation method for environmental and reliability testing based on big data described in the article, and can produce the same technical effect, so it will not be elaborated here.
[0066] In one embodiment, a computer device is provided, which may be a server or a client, and its internal structure diagram may be as follows: Figure 3 As shown, the computer device includes a processor, memory, network interface, and database connected via a system bus. The processor provides computing and control capabilities. The memory includes non-volatile and / or volatile storage media and internal memory. The non-volatile storage media stores the operating system, computer programs, and database. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The network interface is used for communication with external clients via a network connection. When the computer program is executed by the processor, it implements functions or steps on the server or client side of a big data-based intelligent evaluation method for environmental and reliability testing.
[0067] In one embodiment, a computer device is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to perform the following steps: The correlation characteristics between the product performance of the target product and environmental stress are analyzed, wherein the correlation characteristics are obtained based on the test analysis of the target product under historical environmental conditions; Based on the aforementioned correlation features, a performance degradation curve for the target product is constructed, and the performance inflection point features of the target product are identified using the performance degradation curve. After collecting product data of the target product under the current experimental environment, and combining the performance inflection point characteristics, the cumulative damage of the target product under the current experimental environment is analyzed to generate an experimental analysis report of the target product under the current experimental environment.
[0068] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon, the computer program performing the following steps when executed by a processor: The correlation characteristics between the product performance of the target product and environmental stress are analyzed, wherein the correlation characteristics are obtained based on the test analysis of the target product under historical environmental conditions; Based on the aforementioned correlation features, a performance degradation curve for the target product is constructed, and the performance inflection point features of the target product are identified using the performance degradation curve. After collecting product data of the target product under the current experimental environment, and combining the performance inflection point characteristics, the cumulative damage of the target product under the current experimental environment is analyzed to generate an experimental analysis report of the target product under the current experimental environment.
[0069] It should be noted that the functions or steps that can be implemented by the computer-readable storage medium or computer device described above can be referred to the relevant descriptions on the server side and client side in the foregoing method embodiments. To avoid repetition, they will not be described one by one here.
[0070] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium. When executed, the computer program can include the processes of the embodiments of the above methods. Any references to memory, storage, databases, or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), dual data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), RAMbus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.
[0071] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the above-described division of functional units and modules is used as an example. In practical applications, the above functions can be assigned to different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above.
[0072] It will be apparent to those skilled in the art that the present invention is not limited to the details of the exemplary embodiments described above, and that the present invention can be implemented in other specific forms without departing from the spirit or essential characteristics of the present invention.
[0073] Finally, it should be noted that in the above embodiments, each embodiment can be combined with each other or independent. Deleting any one of them will not affect the technical implementation of other embodiments. The above embodiments are only used to illustrate the technical solutions of the present invention and not to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention.
Claims
1. A smart evaluation method for environmental and reliability testing based on big data, characterized in that, The method includes: The correlation characteristics between the product performance of the target product and environmental stress are analyzed, wherein the correlation characteristics are obtained based on the test analysis of the target product under historical environmental conditions; Based on the aforementioned correlation features, a performance degradation curve for the target product is constructed, and the performance inflection point features of the target product are identified using the performance degradation curve. After collecting product data of the target product under the current experimental environment, and combining the performance inflection point characteristics, the cumulative damage of the target product under the current experimental environment is analyzed to generate an experimental analysis report of the target product under the current experimental environment.
2. The intelligent evaluation method for environmental and reliability testing based on big data as described in claim 1, characterized in that, Based on the aforementioned performance inflection point characteristics, the cumulative damage of the target product under the current experimental environment is analyzed, including: Extract multi-dimensional environmental stress parameters of the target product from the current experimental environment data; Identify the parameter variation trends of the multi-dimensional environmental stress parameters to divide the current experimental duration corresponding to the target product into multiple stress units, thereby obtaining a stress evaluation unit; Based on the performance inflection point characteristics, the damage increment of the target product corresponding to each unit in the stress assessment unit is calculated to obtain the multi-unit damage increment; Based on the multi-unit damage increment, the cumulative damage of the target product under the current experimental environment data is evaluated.
3. The intelligent evaluation method for environmental and reliability testing based on big data as described in claim 2, characterized in that, Based on the performance inflection point characteristics, the damage increment of the target product corresponding to each unit in the stress assessment unit is calculated to obtain the multi-unit damage increment, including: Extract the environmental stress characteristic value corresponding to each unit from the stress assessment unit; Calculate the damage component of each element under a single stress. Based on the performance inflection point characteristics, the basic damage components are compositely corrected to obtain the comprehensive damage increment of each unit. The comprehensive damage increment is sorted by time series to obtain the multi-unit damage increment.
4. The intelligent evaluation method for environmental and reliability testing based on big data as described in claim 1, characterized in that, Based on the aforementioned correlation features, the performance degradation curve of the target product is constructed, including: Based on the aforementioned correlation features, key data points of the target product during performance degradation are identified; Using the key data points, construct the initial performance degradation curve of the target product; Identify the performance inflection point in the initial performance degradation curve; Based on the performance inflection point, a performance degradation curve for the target product is constructed.
5. The intelligent evaluation method for environmental and reliability testing based on big data as described in claim 4, characterized in that, Identifying the performance inflection point in the initial performance degradation curve includes: Calculate the first and second derivatives of the initial performance degradation curve; The performance inflection point in the initial performance degradation curve is identified using the first and second derivatives.
6. The intelligent evaluation method for environmental and reliability testing based on big data as described in claim 5, characterized in that, Using the first and second derivatives, the performance inflection point in the initial performance degradation curve is identified, including: The performance degradation rate of the target product is analyzed using the first derivative. The second derivative is used to analyze the performance degradation acceleration of the target product; Based on the performance degradation rate and the performance degradation acceleration, the performance inflection point in the initial performance degradation curve is determined.
7. The intelligent evaluation method for environmental and reliability testing based on big data as described in claim 1, characterized in that, Analyze the correlation characteristics between the target product's performance and environmental stress, including: Analyze the core performance indicators of the target product and the corresponding environmental stress types; Based on the core performance indicators and the types of environmental stress, the correlation characteristics between the product performance and environmental stress of the target product are determined.
8. The intelligent evaluation method for environmental and reliability testing based on big data as described in claim 1, characterized in that, Using the performance degradation curve, the performance inflection point characteristics of the target product are identified, including: Query the inflection point parameters of the performance inflection point in the performance degradation curve; Based on the inflection point parameters, the performance inflection point characteristics of the target product are identified.
9. The intelligent evaluation method for environmental and reliability testing based on big data as described in claim 1, characterized in that, Generate a test analysis report of the target product under the current experimental environment, including: Query the experimental evaluation data of the target product under the current experimental environment; Using the experimental evaluation data, construct an experimental analysis report of the target product under the current experimental environment.
10. An intelligent evaluation system for environmental and reliability testing based on big data, characterized in that: The system includes: The correlation feature analysis module is used to analyze the correlation features between the product performance of the target product and environmental stress, wherein the correlation features are obtained based on the test analysis of the target product under historical environmental conditions; The inflection point feature recognition module is used to construct the performance degradation curve of the target product based on the associated features, and to identify the performance inflection point features of the target product using the performance degradation curve. The reliability assessment module is used to collect product data of the target product under the current experimental environment, and then, in combination with the performance inflection point characteristics, analyze the cumulative damage of the target product under the current experimental environment to generate a test analysis report of the target product under the current experimental environment.