Intelligent evaluation method and system for reliability of component

Abstract

The invention relates to the technical field of reliability engineering, in particular to an intelligent evaluation method and system for component reliability, and the method comprises the steps: collecting and preprocessing key information of a component, inputting the preprocessed key information into a corresponding failure distribution model, and carrying out the parameter fitting; comparing goodness-of-fit indexes of the failure distribution model, and outputting an optimal fitting model and corresponding detailed parameters; constructing and refining a reliability model of the component; and outputting an evaluation result based on the corresponding reliability model. The method has the effect of effectively evaluating the reliability.

Description

Technical Field

[0001] The present application relates to the field of reliability engineering technology, and specifically to an intelligent evaluation method and system for component reliability. Background Art

[0002] In the electronics industry, many products are susceptible to degradation-related failures, such as capacitors, lithium-ion batteries, ferroelectric memories, and photoelectric sensors. Reliability analysis and evaluation of these products is essential to ensuring the proper functioning of these equipment. Currently, most reliability theories focus on failure-related data. These methods analyze product failure data from accelerated testing conditions, select the optimal statistical distribution model (exponential, Weibull, lognormal, etc.) based on a statistical criterion, and then extrapolate to estimate the product's life under normal stress conditions. However, these methods for processing data related to sudden failures are not suitable for reliability modeling and analysis of degradation-related data.

[0003] With continuous improvements in processes and technologies, modern electronic products are experiencing increasingly lower failure rates and longer lifespans. However, due to the limited number of test samples, obtaining field degradation failure data during reliability assessments is often impossible. This presents significant challenges for reliability assessments of long-life electronic products. While accelerated testing can monitor the degradation of key product performance parameters, the limited sample size often prevents these parameters from exhibiting degradation failure characteristics.

[0004] Therefore, improvements are needed. Summary of the Invention

[0005] To solve the above technical problems, the present application provides an intelligent evaluation method and system for component reliability.

[0006] The first object of the invention of this application is achieved through the following technical solutions:

[0007] A method for intelligently evaluating component reliability comprises the following steps:

[0008] Collect key information of components and perform preprocessing, input the preprocessed key information into the corresponding failure distribution model, and perform parameter fitting;

[0009] Comparing the goodness-of-fit indices of the failure distribution models, and outputting the best-fit model and corresponding detailed parameters;

[0010] Build and refine component reliability models;

[0011] Based on the corresponding reliability model, the evaluation results are output.

[0012] In a preferred embodiment, the step of collecting and preprocessing key information of components, inputting the preprocessed key information into a corresponding failure distribution model, and performing parameter fitting includes the following steps:

[0013] The key information includes reliability data, stress conditions, and failure modes;

[0014] The reliability data includes failure time and failure number;

[0015] The stress conditions include temperature, humidity, voltage, current, power, and vibration;

[0016] The failure modes include short circuit and open circuit;

[0017] Input the pre-processed key information into the preset failure distribution model library to match the corresponding failure distribution model;

[0018] The failure distribution model includes exponential distribution, parametric Weibull distribution, normal distribution, lognormal distribution, Gamma distribution, and Logistic distribution;

[0019] Based on the reliability data, matching the corresponding fitting analysis method to perform parameter fitting;

[0020] The fitting analysis methods include maximum likelihood, rank regression, standard rank regression, Fisher matrix, interval confidence method, median order, and Kaplan-Meier ranking method.

[0021] In a preferred embodiment, the step of comparing the goodness-of-fit indexes of the failure distribution models and outputting the best-fit model and corresponding detailed parameters comprises the following steps:

[0022] Based on statistical testing methods, the failure distribution model after parameter fitting is evaluated to see how well it fits the actual data in the preset actual database, and a goodness of fit index is output;

[0023] Compare the goodness-of-fit indicators of different failure distribution models and output the best fitting model;

[0024] Outputting detailed parameters of the best fitting model, the detailed parameters including the life distribution curve, characteristic parameters, and the life distribution curve within the confidence interval;

[0025] The characteristic parameters include reliability curve and failure density curve;

[0026] The confidence interval includes a one-sided interval and a two-sided interval.

[0027] In a preferred embodiment, the step of constructing and refining the reliability model of components includes the steps of:

[0028] For the key information of degradation, a corresponding degradation model is established based on the specific information of the components;

[0029] The specific information includes operating principles, degradation or failure mechanisms of key materials and structures;

[0030] The degradation model includes linear, exponential, and power functions;

[0031] Extrapolating key information to predict pseudo-failure life distribution when failure criteria are reached based on the degradation model;

[0032] Output pseudo-failure life distribution and perform life characteristic analysis.

[0033] In a preferred embodiment, the step of constructing and refining the reliability model of components further includes the steps of:

[0034] For the key information of competitive failure, the key information is classified based on the main failure modes and failure mechanisms of components under stress;

[0035] Based on the fitting analysis method, parameter fitting is performed on the classified key information to output reliability characteristic parameters.

[0036] In a preferred embodiment, the step of constructing and refining the reliability model of components further includes the steps of:

[0037] Collect and analyze accelerated life test data of the components under different stress conditions;

[0038] Match failure physical models based on data characteristics and failure mechanisms;

[0039] The failure physics models include Arrhenius model, Eyring model, inverse power rate model, hygrothermal-non-thermal stress model, and cumulative damage model;

[0040] Based on the least squares method, the parameters of the matched failure physical model are estimated and the failure physical model parameters are extracted;

[0041] The failure physical model parameters include activation energy, voltage acceleration factor, moisture acceleration factor, temperature cycle acceleration factor, power acceleration factor, and vibration fatigue acceleration factor;

[0042] Based on the extracted failure physical model parameters, the corresponding reliability model is established.

[0043] In a preferred embodiment, the step of outputting the evaluation result based on the reliability model comprises the steps of:

[0044] Based on the reliability model, calculating the acceleration factor under different stress conditions;

[0045] Based on the acceleration factor and the reliability model, extrapolating and predicting a reliability characteristic curve under normal stress conditions;

[0046] The conventional stress conditions include an ambient temperature of 20°C-25°C, a relative humidity of 50%, and a nominal voltage;

[0047] Output evaluation results, including failure physical model parameters, acceleration coefficients, and reliability characteristic curves.

[0048] The second object of the invention of this application is achieved through the following technical solutions:

[0049] The first module collects key information of components and preprocesses it, inputs the preprocessed key information into the corresponding failure distribution model, and performs parameter fitting;

[0050] The second module: compares the goodness-of-fit index of the failure distribution model and outputs the best fitting model and corresponding detailed parameters;

[0051] Module 3: Build and refine the reliability model of components;

[0052] Module 4: Output evaluation results based on the corresponding reliability model.

[0053] The third object of the invention of this application is achieved through the following technical solutions:

[0054] A computer device includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the steps of the above-mentioned intelligent component reliability evaluation method are implemented.

[0055] The fourth object of the invention of this application is achieved through the following technical solutions:

[0056] A computer-readable storage medium stores a computer program, which, when executed by a processor, implements the steps of the above-mentioned intelligent component reliability evaluation method.

[0057] In summary, this application includes at least one of the following beneficial technical effects:

[0058] First, key component information is collected and preprocessed to ensure data quality and consistency. This information is then input into the corresponding failure distribution model for parameter fitting, providing a basis for subsequent analysis. By comparing the goodness-of-fit indicators of different models, the best-fit model and its detailed parameters are selected, ensuring the scientific nature and accuracy of the model selection. Based on these parameters, a reliability model for the components is constructed and refined, fully considering various influencing factors. Ultimately, this reliability model is used to output evaluation results, including failure physics model parameters, acceleration factors, and reliability characteristic curves. (This method not only improves the efficiency and accuracy of the evaluation, but also provides strong support for companies to formulate maintenance strategies and optimize product design, and has significant application value and promotion potential.) BRIEF DESCRIPTION OF THE DRAWINGS

[0059] Figure 1 This is a flowchart of an implementation of an embodiment of an intelligent component reliability evaluation method of the present application;

[0060] Figure 2 This is a flowchart for implementing step S10 in an embodiment of an intelligent component reliability evaluation method of the present application;

[0061] Figure 3 This is a flowchart for implementing step S20 in an embodiment of an intelligent component reliability evaluation method of the present application;

[0062] Figure 4 This is a principle block diagram of a computer device of the present application. DETAILED DESCRIPTION

[0063] The following is combined with Figure 1-4 This application is described in further detail.

[0064] In one embodiment, if Figure 1 As shown, the present application discloses an intelligent evaluation method for component reliability, which specifically includes the following steps:

[0065] S10: collecting key information of components and performing preprocessing, inputting the preprocessed key information into the corresponding failure distribution model, and performing parameter fitting;

[0066] S20: comparing the goodness-of-fit indexes of the failure distribution models, and outputting the best fitting model and corresponding detailed parameters;

[0067] S30: Build and refine component reliability models;

[0068] S40: Based on the corresponding reliability model, output the evaluation results.

[0069] In this embodiment, accurate prediction of component reliability is achieved through systematic data processing and model analysis. First, in step S10, key information of components is collected and preprocessed to ensure the quality and consistency of the data. Subsequently, this information is input into the corresponding failure distribution model for parameter fitting, which provides a basis for subsequent analysis. In step S20, by comparing the goodness of fit indicators of different models, the best fitting model and its detailed parameters are selected to ensure the scientificity and accuracy of the model selection. Based on these parameters, step S30 constructs and refines the reliability model of the components, taking into full consideration various influencing factors. Finally, in step S40, this reliability model is used to output the evaluation results, including failure physical model parameters, acceleration coefficients, and reliability characteristic curves. This method not only improves the efficiency and accuracy of the evaluation, but also provides strong support for enterprises to formulate maintenance strategies and optimize product design. It has significant application value and promotion potential.

[0070] Figure 2 , step S10, comprising the steps of:

[0071] S101: The key information includes reliability data, stress conditions, and failure modes;

[0072] S102: The reliability data includes failure time and failure number;

[0073] S103: The stress conditions include temperature, humidity, voltage, current, power, and vibration;

[0074] S104: The failure modes include short circuit and open circuit;

[0075] S105: Input the pre-processed key information into a preset failure distribution model library to match the corresponding failure distribution model;

[0076] S106: The failure distribution model includes exponential distribution, parametric Weibull distribution, normal distribution, lognormal distribution, Gamma distribution, and Logistic distribution;

[0077] S107: Based on the reliability data, matching the corresponding fitting analysis method to perform parameter fitting;

[0078] S108: The fitting analysis methods include maximum likelihood, rank regression, standard rank regression, Fisher matrix, interval confidence interval method, median order, and Kaplan-Meier ranking method.

[0079] In this embodiment, step S10 lays the foundation for the intelligent evaluation of component reliability through precise data collection and model matching. Specifically, the collection of key information (S101-S104) covers reliability data, stress conditions and failure modes, which are the core elements for evaluating component reliability. By preprocessing this information, the validity and applicability of the data are ensured. Then, the preprocessed data is input into the preset failure distribution model library (S105) and matched with the most suitable failure distribution model (S106), such as exponential distribution, Weibull distribution, etc. Finally, based on the reliability data, an appropriate fitting analysis method (S107-S108) is selected, such as maximum likelihood method, rank regression, etc., to perform parameter fitting, thereby providing accurate parameter estimation for subsequent model comparison and reliability evaluation.

[0080] Figure 3 , step S20, comprising the steps of:

[0081] S201: Evaluate the degree of fit between the failure distribution model after parameter fitting and the actual data in the preset actual database based on a statistical test method, and output a goodness of fit index;

[0082] S202: Compare the goodness-of-fit indices of different failure distribution models and output the best fitting model;

[0083] S203: Outputting detailed parameters of the best fitting model, wherein the detailed parameters include a life distribution curve, characteristic parameters, and a life distribution curve within a confidence interval;

[0084] S204: The characteristic parameters include a reliability curve and a failure density curve.

[0085] S205: The confidence interval includes a one-sided interval and a two-sided interval.

[0086] In this embodiment, step S20 performs a goodness of fit evaluation on the failure distribution model by means of a statistical test method, thereby ensuring a high degree of consistency between the model and the actual data. Specifically, in step S201, a statistical test method is used to evaluate the degree of matching between the failure distribution model after parameter fitting and the data in the actual database, and outputs a goodness of fit index, such as a chi-square test, AIC (Akaike information criterion), etc. Then, in step S202, the goodness of fit indexes of different failure distribution models are compared to determine the best fitting model. Finally, step S203 outputs the detailed parameters of the best fitting model, including the life distribution curve, characteristic parameters (such as reliability curve, failure density curve) and the life distribution curve within the confidence interval (S204-S205). These parameters provide a quantitative basis for reliability evaluation.

[0087] Step S30 includes the following steps:

[0088] SA1: For the key information of degradation type, establish the corresponding degradation model based on the specific information of components;

[0089] SA2: The specific information includes the operating principle, degradation or failure mechanism of key materials and structures;

[0090] SA3: The degradation model includes linear, exponential, and power functions;

[0091] SA4: Extrapolate key information and predict the pseudo-failure life distribution when the failure criterion is reached based on the degradation model;

[0092] SA5: Output pseudo-failure life distribution and perform life characteristic analysis.

[0093] In this embodiment, for the key degradation information of components, corresponding degradation models are first established based on their specific information, including the operating principle, degradation or failure mechanism of key materials and structures. These models can be in the form of linear, exponential, or power functions, and are designed to accurately describe the degradation process of the components. Next, the selected degradation model is used to extrapolate the degradation data to predict the pseudo-failure life distribution when the failure criteria are reached. Finally, this distribution is output and life characteristic analysis is performed. This series of steps effectively combines the intrinsic characteristics and external performance of the components, achieving an in-depth understanding and accurate prediction of their reliability characteristics, providing strong support for subsequent maintenance and optimization.

[0094] Step S30 further includes the following steps:

[0095] SB1: For the key information of competing failures, classify the key information based on the main failure modes and failure mechanisms of components under stress;

[0096] SB2: Based on the fitting analysis method, parameter fitting is performed on the classified key information to output reliability characteristic parameters.

[0097] In this embodiment, the component reliability model is deeply constructed and refined through two sub-steps, SB1 and SB2. In step SB1, by understanding the main failure modes and failure mechanisms of components under stress, key information on competing failures is classified. This enables more accurate identification and differentiation of different failure causes, providing more precise input for the construction of the reliability model. Next, in step SB2, fitting analysis methods are used to perform parameter fitting on the classified key information, outputting reliability characteristic parameters, which are an important basis for evaluating component reliability.

[0098] Step S30 further includes the following steps:

[0099] SE1: Collect and analyze accelerated life test data of the components under different stress conditions;

[0100] SE2: Matching failure physical models based on data characteristics and failure mechanisms;

[0101] SE3: The failure physics models include Arrhenius model, Eyring model, inverse power law model, hygrothermal-non-thermal stress model, and cumulative damage model;

[0102] SE4: Based on the least squares method, the parameters of the matched failure physical model are estimated and the failure physical model parameters are extracted;

[0103] SE5: The failure physical model parameters include activation energy, voltage acceleration factor, moisture acceleration factor, temperature cycle acceleration factor, power acceleration factor, and vibration fatigue acceleration factor;

[0104] SE6: Based on the extracted failure physical model parameters, establish the corresponding reliability model.

[0105] In this embodiment, step S30 constructs a detailed and accurate reliability model by deeply analyzing the accelerated life test data of components under different stress conditions and combining it with the failure physical model. Specifically, in step SE1, the accelerated life test data are collected and analyzed. These data help to quickly evaluate the reliability of components under extreme conditions. In step SE2, according to the data characteristics and failure mechanism, the corresponding failure physical model (SE3) is matched, such as the Arrhenius model, the Eyring model, etc. These models can describe the failure behavior of components under different stresses. Then, in step SE4, the least squares method is used to estimate the parameters of the failure physical model and extract the key failure physical model parameters (SE5), such as activation energy, voltage acceleration factor, etc. Finally, step SE6 establishes the corresponding reliability model based on these parameters.

[0106] Step S40 includes the following steps:

[0107] S401: Calculating acceleration factors under different stress conditions based on the reliability model;

[0108] S402: Based on the acceleration factor and the reliability model, extrapolate and predict the reliability characteristic curve under normal stress conditions;

[0109] S403: The conventional stress conditions include an ambient temperature of 20° C. to 25° C., a relative humidity of 50%, and a nominal voltage;

[0110] S404: Output the evaluation results, which include failure physical model parameters, acceleration coefficients, and reliability characteristic curves.

[0111] In this embodiment, step S40 focuses on the practical application and prediction of the established reliability model. First, the acceleration coefficients under different stress conditions are calculated based on the reliability model. These coefficients reflect the changes in the failure rate of components under different environments. Then, using these acceleration coefficients and reliability models, the reliability characteristic curves under conventional stress conditions (such as an ambient temperature of 20°C-25°C, a relative humidity of 50% and a nominal voltage) are extrapolated to predict the reliability of the components under normal use conditions. Finally, the evaluation results including failure physical model parameters, acceleration coefficients and reliability characteristic curves are output, providing users with comprehensive and intuitive reliability information. This step not only improves the practicality and accuracy of reliability evaluation, but also provides strong data support for enterprises to formulate maintenance strategies and optimize product design, significantly enhancing the reliability and service life prediction capabilities of components.

[0112] It should be understood that the size of the serial numbers of the steps in the above embodiments does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application.

[0113] In one embodiment, a component reliability intelligent evaluation system is provided, which corresponds to the component reliability intelligent evaluation method in the above embodiment. The component reliability intelligent evaluation system includes:

[0114] The first module collects key information of components and preprocesses it, inputs the preprocessed key information into the corresponding failure distribution model, and performs parameter fitting;

[0115] The second module: compares the goodness-of-fit index of the failure distribution model and outputs the best fitting model and corresponding detailed parameters;

[0116] Module 3: Build and refine the reliability model of components;

[0117] Module 4: Output evaluation results based on the corresponding reliability model.

[0118] Optionally, also include:

[0119] The first module includes: the key information includes reliability data, stress conditions, and failure modes;

[0120] The second module includes: the reliability data includes failure time and failure number;

[0121] The third module includes: the stress conditions include temperature, humidity, voltage, current, power, and vibration;

[0122] The fourth module includes: the failure mode includes short circuit and open circuit;

[0123] The first matching module: inputs the pre-processed key information into the preset failure distribution model library to match the corresponding failure distribution model;

[0124] The fifth module includes: the failure distribution model includes exponential distribution, parametric Weibull distribution, normal distribution, lognormal distribution, Gamma distribution, and Logistic distribution;

[0125] The first input module: based on the reliability data, matching the corresponding fitting analysis method to perform parameter fitting;

[0126] The sixth module includes: the fitting analysis methods include maximum likelihood, rank regression, standard rank regression, Fisher matrix, interval confidence method, median order, and Kaplan-Meier ranking method.

[0127] Optionally, also include:

[0128] The first output module: Based on the statistical test method, the failure distribution model after parameter fitting is evaluated to what extent the failure distribution model fits the actual data in the preset actual database, and outputs the goodness of fit index;

[0129] The second output module: compares the goodness-of-fit indices of different failure distribution models and outputs the best fitting model;

[0130] The third output module is used to output the detailed parameters of the best fitting model, including the life distribution curve, characteristic parameters, and the life distribution curve within the confidence interval;

[0131] Fourth output module: the characteristic parameters include reliability curve and failure density curve;

[0132] The fifth output module: the confidence interval includes a one-sided interval and a two-sided interval;

[0133] Optionally, also include:

[0134] The first establishment module: for the key information of the degradation type, based on the specific information of the components, establish the corresponding degradation model;

[0135] The seventh module includes: the specific information includes the working principle, degradation or failure mechanism of key materials and structures;

[0136] The eighth module includes: the degradation model includes linear, exponential, and power functions;

[0137] Prediction module: extrapolating key information and predicting pseudo-failure life distribution when failure criteria are reached based on the degradation model;

[0138] The seventh output module: outputs pseudo-failure life distribution and performs life characteristic analysis.

[0139] Optionally, also include:

[0140] Classification module: for key information of competitive failures, classify the key information based on the main failure modes and failure mechanisms of components under stress;

[0141] The eighth output module: Based on the fitting analysis method, parameter fitting is performed on the classified key information to output reliability characteristic parameters.

[0142] Optionally, also include:

[0143] Collection module: collects and analyzes the accelerated life test data of the components under different stress conditions;

[0144] The second matching module: matches the failure physical model based on data characteristics and failure mechanism;

[0145] Model module: The failure physics model includes Arrhenius model, Eyring model, inverse power law model, hygrothermal-non-thermal stress model, and cumulative damage model;

[0146] Extraction module: Based on the least squares method, the matching failure physical model is estimated and the failure physical model parameters are extracted;

[0147] Parameter module: The failure physical model parameters include activation energy, voltage acceleration factor, moisture acceleration factor, temperature cycle acceleration factor, power acceleration factor, and vibration fatigue acceleration factor;

[0148] The second establishment module: establishes the corresponding reliability model based on the extracted failure physical model parameters.

[0149] Optionally, also include:

[0150] Calculation module: Based on the reliability model, calculate the acceleration coefficient under different stress conditions;

[0151] An extrapolation module: extrapolating and predicting a reliability characteristic curve under normal stress conditions based on the acceleration coefficient and the reliability model;

[0152] Conventional module: The conventional stress conditions include an ambient temperature of 20°C-25°C, a relative humidity of 50%, and a nominal voltage;

[0153] Ninth output module: outputs evaluation results, which include failure physical model parameters, acceleration coefficients, and reliability characteristic curves.

[0154] The specific definition of an intelligent component reliability assessment system can be found in the definition of an intelligent component reliability assessment method described above and will not be repeated here. Each module in the aforementioned intelligent component reliability assessment control system can be implemented in whole or in part through software, hardware, or a combination thereof. Each of the aforementioned modules can be embedded in or independent of a processor in a computer device in hardware form, or can be stored in a memory in the computer device in software form, so that the processor can call and execute the corresponding operations of each of the aforementioned modules.

[0155] In one embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as follows: Figure 4 As shown. The computer device includes a processor, a memory, a network interface, and a database connected via a system bus. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of the operating system and computer program in the non-volatile storage medium. The database of the computer device is used to store key information. The network interface of the computer device is used to communicate with an external terminal via a network connection. When the computer program is executed by the processor, an intelligent component reliability assessment method is implemented.

[0156] 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. When the processor executes the computer program, an intelligent component reliability evaluation method is implemented.

[0157] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, a method for intelligently evaluating component reliability is provided.

[0158] Those skilled in the art will appreciate that all or part of the processes in the above-mentioned embodiments can be implemented by instructing the relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

[0159] Those skilled in the art will clearly understand that for the sake of convenience and brevity of description, only the division of the above-mentioned functional units and modules is used as an example. In actual applications, the above-mentioned functions can be distributed and completed by 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.

Claims

1. An intelligent evaluation method for component reliability, characterized in that: Including steps: Collect key information of components and perform preprocessing, input the preprocessed key information into the corresponding failure distribution model, and perform parameter fitting; Comparing the goodness-of-fit indices of the failure distribution models, and outputting the best-fit model and corresponding detailed parameters; Build and refine component reliability models; Based on the corresponding reliability model, the evaluation results are output.

2. The intelligent component reliability evaluation method according to claim 1, characterized in that: The step of collecting and preprocessing key information of components, inputting the preprocessed key information into a corresponding failure distribution model, and performing parameter fitting includes the following steps: The key information includes reliability data, stress conditions, and failure modes; The reliability data includes failure time and failure number; The stress conditions include temperature, humidity, voltage, current, power, and vibration; The failure modes include short circuit and open circuit; Input the pre-processed key information into the preset failure distribution model library to match the corresponding failure distribution model; The failure distribution model includes exponential distribution, parametric Weibull distribution, normal distribution, lognormal distribution, Gamma distribution, and Logistic distribution; Based on the reliability data, matching the corresponding fitting analysis method to perform parameter fitting; The fitting analysis methods include maximum likelihood, rank regression, standard rank regression, Fisher matrix, interval confidence method, median order, and Kaplan-Meier ranking method.

3. The intelligent component reliability evaluation method according to claim 1, characterized in that: The step of comparing the goodness-of-fit indexes of the failure distribution models and outputting the best-fit model and corresponding detailed parameters comprises the following steps: Based on statistical testing methods, the failure distribution model after parameter fitting is evaluated to see how well it fits the actual data in the preset actual database, and a goodness of fit index is output; Compare the goodness-of-fit indicators of different failure distribution models and output the best fitting model; Outputting detailed parameters of the best fitting model, the detailed parameters including the life distribution curve, characteristic parameters, and the life distribution curve within the confidence interval; The characteristic parameters include reliability curve and failure density curve; The confidence interval includes a one-sided interval and a two-sided interval.

4. The intelligent component reliability evaluation method according to claim 1, characterized in that: The steps of constructing and refining the reliability model of components include the following steps: For the key information of degradation, a corresponding degradation model is established based on the specific information of the components; The specific information includes operating principles, degradation or failure mechanisms of key materials and structures; The degradation model includes linear, exponential, and power functions; Extrapolating key information to predict pseudo-failure life distribution when failure criteria are reached based on the degradation model; Output pseudo-failure life distribution and perform life characteristic analysis.

5. The intelligent component reliability evaluation method according to claim 1, characterized in that: The step of constructing and refining the reliability model of components further includes the steps of: For the key information of competitive failure, the key information is classified based on the main failure modes and failure mechanisms of components under stress; Based on the fitting analysis method, parameter fitting is performed on the classified key information to output reliability characteristic parameters.

6. The intelligent component reliability evaluation method according to claim 1, characterized in that: The step of constructing and refining the reliability model of components further includes the steps of: Collect and analyze accelerated life test data of the components under different stress conditions; Match failure physical models based on data characteristics and failure mechanisms; The failure physics models include Arrhenius model, Eyring model, inverse power rate model, hygrothermal-non-thermal stress model, and cumulative damage model; Based on the least squares method, the parameters of the matched failure physical model are estimated and the failure physical model parameters are extracted; The failure physical model parameters include activation energy, voltage acceleration factor, moisture acceleration factor, temperature cycle acceleration factor, power acceleration factor, and vibration fatigue acceleration factor; Based on the extracted failure physical model parameters, the corresponding reliability model is established.

7. The intelligent component reliability evaluation method according to claim 1, characterized in that: The step of outputting the evaluation result based on the reliability model comprises the steps of: Based on the reliability model, calculating the acceleration factor under different stress conditions; Based on the acceleration factor and the reliability model, extrapolating and predicting a reliability characteristic curve under normal stress conditions; The conventional stress conditions include an ambient temperature of 20°C-25°C, a relative humidity of 50%, and a nominal voltage; Output evaluation results, including failure physical model parameters, acceleration coefficients, and reliability characteristic curves.

8. An intelligent component reliability evaluation system, characterized in that: include: The first module collects key information of components and preprocesses it, inputs the preprocessed key information into the corresponding failure distribution model, and performs parameter fitting; The second module: compares the goodness-of-fit index of the failure distribution model and outputs the best fitting model and corresponding detailed parameters; Module 3: Build and refine the reliability model of components; Module 4: Output evaluation results based on the corresponding reliability model.

9. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the steps of the intelligent component reliability evaluation method according to claims 1 to 7 are implemented.

10. A computer-readable storage medium storing a computer program, wherein the computer program, when executed by a processor, implements the steps of the intelligent component reliability evaluation method according to claims 1 to 7.

Images