Electronic component reliability prediction method, device, apparatus, storage medium, and program product

Abstract

The application relates to a reliability prediction method, device, equipment, storage medium and program product of electronic components. The method comprises the following steps: obtaining failure rate data of electronic components of the same category in reliability prediction manuals of different historical versions; determining a reliability characterization model of the electronic components according to the failure rate data; correcting a standard reliability prediction model in a latest version of the reliability prediction manual based on the reliability characterization model to obtain a corrected reliability prediction model; and determining a predicted failure rate of a target electronic component according to a time parameter of the target electronic component and the corrected reliability prediction model, wherein the time parameter represents production time information of the target electronic component. The method can provide more accurate theoretical basis for reliability index demonstration, design scheme comparison and task reliability evaluation.

Description

Technical Field

[0001] This application relates to the field of electronic components technology, and in particular to a method, apparatus, device, storage medium, and program product for predicting the reliability of electronic components. Background Technology

[0002] With the increasing integration and complexity of electronic equipment, high reliability and long lifespan have become core requirements in the development of electronic components. However, reliability cannot be achieved simply by testing after the electronic component is manufactured; it requires system construction from the design stage. To predict the future reliability level of electronic components during the design phase, reliability prediction methods have become one of the main means of evaluating and ensuring reliability during this stage. This technology can provide a theoretical basis for reliability index verification, index allocation, design scheme comparison, and mission reliability assessment in the early stages of electronic component design.

[0003] In traditional practice, the reliability prediction of electronic components mainly relies on various officially published prediction manuals. These manuals provide standardized prediction models and parameter values ​​for different types of electronic components, allowing engineers to conduct failure rate assessments simply by following the prediction models and parameters in the manuals. For a long time, governments and research institutions worldwide have relied on these prediction manuals to guide their national electronic component reliability prediction and assessment work.

[0004] However, this traditional method has significant limitations. Specifically, with the continuous application of new technologies and ongoing improvements in manufacturing processes, the actual reliability level of electronic components is increasing year by year. However, the update speed of forecasting manuals often lags behind the pace of technological development. The older the forecasting manual is, the more likely its basic data is to deviate from the actual level of current electronic components. In this situation, if outdated forecasting models and parameter values ​​are still applied to evaluate the reliability of new electronic components, the resulting failure rates are often inaccurate and may mislead design decisions for electronic products. Summary of the Invention

[0005] Therefore, it is necessary to provide a method, apparatus, device, storage medium, and program product for predicting the reliability of electronic components in response to the above-mentioned technical problems.

[0006] In a first aspect, this application provides a method for predicting the reliability of electronic components, including:

[0007] Obtain failure rate data for the same category of electronic components from different historical versions of reliability prediction manuals;

[0008] Based on failure rate data, a reliability characterization model for electronic components is determined;

[0009] The standard reliability prediction model in the latest version of the reliability prediction manual is modified based on the reliability characterization model to obtain the modified reliability prediction model.

[0010] Based on the time parameters of the target electronic component and the modified reliability prediction model, the expected failure rate of the target electronic component is determined, and the time parameters characterize the production time information of the target electronic component.

[0011] In one embodiment, a reliability characterization model for electronic components is determined based on failure rate data, including:

[0012] Based on the relationship between failure rate data and the release and reference time of the reliability prediction manual, the reliability growth rate of electronic components can be obtained.

[0013] The reliability growth rate is substituted into a pre-defined model framework to determine the reliability characterization model of the electronic component. In one embodiment, the reliability growth rate of the electronic component is obtained based on the relationship between failure rate data and the publication time and reference time of the reliability prediction manual, including:

[0014] Statistical analysis was conducted on the failure rate data and release dates of different historical versions of the reliability prediction manual;

[0015] Using the reference time as a benchmark, and based on the time interval between each release time and the reference time, a fitting analysis is performed on the failure rate data to obtain the reliability growth rate of electronic components.

[0016] In one embodiment, the standard reliability prediction model in the reliability prediction manual is modified based on the reliability characterization model to obtain a modified reliability prediction model, including:

[0017] Substituting the time parameter into the reliability characterization model generates a correction coefficient, which characterizes the change in the reliability of electronic components with the manufacturing time of the electronic components.

[0018] Based on the correction factor, the standard reliability prediction model in the reliability prediction manual is modified to obtain the modified reliability prediction model.

[0019] In one embodiment, the method for predicting the reliability of the above-mentioned electronic components further includes:

[0020] Based on the standard reliability prediction model and the modified reliability prediction model, the first and second predicted failure rates of electronic components of the same category are determined.

[0021] Obtain on-site data from manufacturers of the same category of electronic components, and use the on-site data as a reference failure rate;

[0022] The validity of the modified reliability prediction model is determined based on the first predicted failure rate, the second predicted failure rate, and the reference failure rate.

[0023] In one embodiment, the validity of the modified reliability prediction model is determined based on a first predicted failure rate, a second predicted failure rate, and a reference failure rate, including:

[0024] The first difference is determined based on the first predicted failure rate and the reference failure rate;

[0025] The second difference is determined based on the second predicted failure rate and the reference failure rate;

[0026] Based on the first difference and the second difference, determine the deviation value between the first difference and the second difference;

[0027] The validity of the revised reliability prediction model is determined based on the deviation value.

[0028] Secondly, this application also provides a device for predicting the reliability of electronic components, comprising:

[0029] The acquisition module is used to acquire failure rate data for the same category of electronic components in different historical versions of reliability prediction manuals;

[0030] The determination module is used to determine the reliability characterization model of electronic components based on failure rate data;

[0031] The correction module is used to correct the standard reliability prediction model in the latest version of the reliability prediction manual based on the reliability characterization model, so as to obtain the corrected reliability prediction model.

[0032] The failure module is used to determine the expected failure rate of the target electronic component based on the time parameters of the target electronic component and the modified reliability prediction model. The time parameters characterize the production time information of the target electronic component.

[0033] Thirdly, this application also provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to perform the following steps:

[0034] Obtain failure rate data for the same category of electronic components from different historical versions of reliability prediction manuals;

[0035] Based on failure rate data, a reliability characterization model for electronic components is determined;

[0036] The standard reliability prediction model in the latest version of the reliability prediction manual is modified based on the reliability characterization model to obtain the modified reliability prediction model.

[0037] Based on the time parameters of the target electronic component and the modified reliability prediction model, the expected failure rate of the target electronic component is determined, and the time parameters characterize the production time information of the target electronic component.

[0038] Fourthly, this application also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, performs the following steps:

[0039] Obtain failure rate data for the same category of electronic components from different historical versions of reliability prediction manuals;

[0040] Based on failure rate data, a reliability characterization model for electronic components is determined;

[0041] The standard reliability prediction model in the latest version of the reliability prediction manual is modified based on the reliability characterization model to obtain the modified reliability prediction model.

[0042] Based on the time parameters of the target electronic component and the modified reliability prediction model, the expected failure rate of the target electronic component is determined, and the time parameters characterize the production time information of the target electronic component.

[0043] Fifthly, this application also provides a computer program product, including a computer program that, when executed by a processor, performs the following steps:

[0044] Obtain failure rate data for the same category of electronic components from different historical versions of reliability prediction manuals;

[0045] Based on failure rate data, a reliability characterization model for electronic components is determined;

[0046] The standard reliability prediction model in the latest version of the reliability prediction manual is modified based on the reliability characterization model to obtain the modified reliability prediction model.

[0047] Based on the time parameters of the target electronic component and the modified reliability prediction model, the expected failure rate of the target electronic component is determined, and the time parameters characterize the production time information of the target electronic component.

[0048] The aforementioned methods, apparatus, equipment, storage media, and program products for predicting the reliability of electronic components acquire failure rate data from different historical versions of reliability prediction manuals for the same type of electronic components. Based on the failure rate data, a reliability characterization model for the electronic components is determined. The standard reliability prediction model in the latest version of the reliability prediction manual is then modified based on the reliability characterization model to obtain a modified reliability prediction model. The predicted failure rate of the target electronic component is determined based on its time parameters and the modified reliability prediction model. The time parameters characterize the production time information of the target electronic component. This method eliminates the need for additional accelerated life testing or the collection of field maintenance data; it can complete the reliability growth analysis of electronic components solely based on existing historical manual data, significantly reducing implementation costs and time. Furthermore, by introducing a reliability growth characterization model, the prediction results reflect the actual trend of annual improvements in electronic component reliability due to advancements in manufacturing processes, avoiding prediction biases caused by outdated manual data. This provides a more accurate theoretical basis for reliability index verification, design scheme comparison, and task reliability assessment. Attached Figure Description

[0049] To more clearly illustrate the technical solutions in the embodiments of this application or related technologies, the drawings used in the description of the embodiments of this application or related technologies will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0050] Figure 1 This is a diagram illustrating the application environment of a method for predicting the reliability of electronic components in one embodiment.

[0051] Figure 2 This is one of the flowcharts illustrating a method for predicting the reliability of electronic components in one embodiment;

[0052] Figure 3 This is a second flowchart illustrating a method for predicting the reliability of electronic components in one embodiment;

[0053] Figure 4 This is the third flowchart illustrating a method for predicting the reliability of electronic components in one embodiment;

[0054] Figure 5 This is a flowchart illustrating the method for predicting the reliability of electronic components in one embodiment;

[0055] Figure 6 Here is a flowchart of reliability prediction based on a manual in one embodiment;

[0056] Figure 7This is the fifth flowchart illustrating a method for predicting the reliability of electronic components in one embodiment;

[0057] Figure 8 This is a schematic diagram of the circuit board in one embodiment;

[0058] Figure 9 This is a comparative analysis chart of expected results in one embodiment;

[0059] Figure 10 This is a diagram showing the expected results in one embodiment;

[0060] Figure 11 This is a structural block diagram of a device for improving the reliability of electronic components in one embodiment. Detailed Implementation

[0061] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0062] It should be noted that the terms "first," "second," etc., used in this application can be used to describe various elements, but these elements are not limited by these terms. These terms are only used to distinguish the first element from the second element. The terms "comprising" and "having," and any variations thereof, used in this application, are intended to cover non-exclusive inclusion. The term "multiple" used in this application refers to two or more. The term "and / or" used in this application refers to one of the embodiments, or any combination of multiple embodiments.

[0063] With the increasing integration and complexity of electronic equipment, high reliability and long lifespan have become core requirements in the development of electronic components. However, reliability cannot be achieved simply by testing after the electronic component is manufactured; it requires system construction from the design stage. To predict the future reliability level of electronic components during the design phase, reliability prediction methods have become one of the main means of evaluating and ensuring reliability during this stage. This technology can provide a theoretical basis for reliability index verification, index allocation, design scheme comparison, and mission reliability assessment in the early stages of electronic component design.

[0064] In traditional practice, the reliability prediction of electronic components mainly relies on various officially published prediction manuals. These manuals provide standardized prediction models and parameter values ​​for different types of electronic components, allowing engineers to conduct failure rate assessments simply by following the prediction models and parameters in the manuals. For a long time, governments and research institutions worldwide have relied on these prediction manuals to guide their national electronic component reliability prediction and assessment work.

[0065] However, this traditional method has significant limitations. Specifically, with the continuous application of new technologies and ongoing improvements in manufacturing processes, the actual reliability level of electronic components is increasing year by year. However, the update speed of forecasting manuals often lags behind the pace of technological development. The older the forecasting manual is, the more likely its basic data is to deviate from the actual level of current electronic components. In this situation, if outdated forecasting models and parameter values ​​are still applied to evaluate the reliability of new electronic components, the resulting failure rates are often inaccurate and may mislead design decisions for electronic products.

[0066] In view of the above-mentioned technical problems, this application provides a method for predicting the reliability of electronic components. The following embodiments will specifically illustrate the method for predicting the reliability growth of electronic components.

[0067] The method for predicting the reliability of electronic components provided in this application embodiment can be applied to, for example, Figure 1 The computer device shown may be a server, and its internal structure diagram may be as follows. Figure 1 As shown, this computer device includes a processor, memory, input / output (I / O) interfaces, and a communication interface. The processor, memory, and I / O interfaces are connected via a system bus, and the communication interface is also connected to the system bus via the I / O interfaces. The processor provides computational and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system, computer programs, and a database. The internal memory provides the environment for the operating system and computer programs in the non-volatile storage media to run. The database stores reliability prediction manual data, historical electronic component failure rate data, reliability growth rate parameters, correction factors, and prediction results. The I / O interfaces are used for information exchange between the processor and external devices. The communication interface is used for communication with external terminals via a network connection. When executed by the processor, the computer program implements a method for predicting the reliability of electronic components.

[0068] Those skilled in the art will understand that Figure 1The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0069] In one exemplary embodiment, such as Figure 2 As shown, a method for predicting the reliability of electronic components is provided, and this method is applied to... Figure 1 Taking computer devices as an example, the explanation includes:

[0070] S201, obtain failure rate data for the same category of electronic components in different historical versions of reliability prediction manuals.

[0071] In this embodiment, the computer device first determines the component category of the target electronic component based on its model or specifications. Component categories include, but are not limited to, carbon film resistors, ceramic capacitors, ordinary diodes, and rectangular connectors. Subsequently, the computer device retrieves and obtains failure rate data for this type of electronic component from a pre-built reliability database, based on different historical versions of reliability prediction manuals. Specifically, the reliability prediction manual includes national standard manuals or industry standard manuals, such as the GJB / Z-299 series and the MIL-HDBK-217 series. Different historical versions refer to revised versions of the same manual released at different times, such as versions A, B, C, and D of GJB / Z-299. Each version of the manual corresponds to a release date and records the failure rate data for this type of electronic component as statistically analyzed at the time of revision. The computer device can obtain failure rate data through one of the following methods, including but not limited to extracting it from a locally stored reliability manual database; obtaining it from an external reliability data platform via a data interface; or parsing it from a manual file uploaded by the user in response to the user's manual input. The computer equipment correlates the acquired failure rate data with its corresponding manual version and release date to form a historical dataset for subsequent fitting analysis.

[0072] S202, Based on the failure rate data, determine the reliability characterization model of electronic components.

[0073] In this embodiment, the computer device first performs statistical analysis on the failure rate data to determine a reference time. This reference time is typically the release date of the latest version of the manual, serving as a benchmark for measuring reliability growth. Subsequently, using this reference time as a benchmark, the computer device performs fitting analysis on the failure rate data from various manual versions to obtain the reliability growth rate of this type of electronic component over different time spans. Based on this, the computer device constructs a reliability characterization model based on the reliability growth rate. This model describes the change in the reliability of electronic components over production time, and its input parameters include at least the reliability growth rate, the reference time, and time-related parameters of the target electronic component.

[0074] S203, based on the reliability characterization model, modifies the standard reliability prediction model in the latest version of the reliability prediction manual to obtain the modified reliability prediction model.

[0075] In this embodiment, the computer device first searches the latest version of the reliability prediction manual and determines the standard reliability prediction model corresponding to this type of electronic component. This standard model is the formula used in traditional methods to calculate the failure rate, such as the basic failure rate multiplied by various influence coefficients. Subsequently, based on the reliability characterization model and combined with the production time information of the target electronic component (such as manufacturing time), the computer device obtains a correction coefficient. The value of this correction coefficient is between 0 and 1; the later the production time, the smaller the correction coefficient. Finally, the computer device multiplies this correction coefficient by the standard reliability prediction model to obtain the corrected reliability prediction model.

[0076] S204. Based on the time parameters of the target electronic component and the modified reliability prediction model, determine the expected failure rate of the target electronic component.

[0077] Among them, the time parameter represents the production time information of the target electronic component.

[0078] In this embodiment, the computer device first acquires the time parameters of the target electronic component, which may be the manufacturing time, production batch number, or production date, etc. Then, the computer device substitutes the time parameters into the modified reliability prediction model. Specifically, the time parameters are used as time-related variables in the model and replaced in their corresponding positions in the modified reliability prediction model. Finally, the computer device executes the modified reliability prediction model to obtain the predicted failure rate of the target electronic component after reliability growth correction. This predicted failure rate reflects the reliability level that the component should have at the current production point in time, considering process advancements.

[0079] The aforementioned method for predicting the reliability of electronic components involves obtaining failure rate data for the same type of electronic components from different historical versions of reliability prediction manuals; determining a reliability characterization model for the electronic components based on the failure rate data; modifying the standard reliability prediction model in the latest version of the reliability prediction manual based on the reliability characterization model to obtain a modified reliability prediction model; and determining the predicted failure rate of the target electronic component based on its time parameters and the modified reliability prediction model, where the time parameters characterize the production time information of the target electronic component. This method does not require additional accelerated life testing or collection of field maintenance data; it can complete the reliability growth analysis of electronic components based solely on existing historical manual data, significantly reducing implementation costs and time. Furthermore, by introducing a reliability growth characterization model, the prediction results reflect the actual trend of electronic components improving year by year with advancements in manufacturing processes, avoiding prediction biases caused by outdated manual data. This provides a more accurate theoretical basis for reliability index verification, design scheme comparison, and task reliability assessment.

[0080] In an exemplary embodiment, the "determining the reliability characterization model of electronic components based on failure rate data" in S202 above, such as Figure 3 As shown, it includes:

[0081] S301, based on the relationship between failure rate data and the release time and reference time of the reliability prediction manual, obtain the reliability growth rate of electronic components.

[0082] In this embodiment, a computer device statistically analyzes failure rate data and their corresponding release dates from different historical versions of reliability prediction manuals. Each version of the manual corresponds to a release date, which identifies the chronological order of the manual. The failure rate data in that version reflects the failure rate level of that type of electronic component during the revision period of that version. The computer device then determines a reference time, which can be the latest release date among all versions of the manual (i.e., the release date of the latest version), or it can be specified by the user according to actual needs. Using the reference time as a benchmark, the computer device calculates the time interval between each release date and the reference time. Then, the computer device performs a fitting analysis on each failure rate data based on the time interval between each release date and the reference time. This yields the reliability growth rate of that type of electronic component.

[0083] S302, the reliability growth rate is substituted into the preset model framework to determine the reliability characterization model of the electronic component. In this embodiment, the computer device first obtains the preset model framework, which is used to describe the change law of the reliability of the electronic component with production time, and its basic form is an exponential function. The computer device substitutes the reliability growth rate, reference time, and time-related parameters of the target electronic component into the corresponding positions in the preset model framework. The reliability characterization model can be represented by the relation (1), which is shown below:

[0084] (1);

[0085] in, Indicates the rate of increase in reliability; Indicates the publication time; Indicates a reference time.

[0086] Through the above substitution operation, the computer equipment can construct a reliability characterization model for this type of electronic component. Depending on the production time of the target electronic component (i.e. and The difference between the two values ​​increases and decreases, thus reflecting the growth trend of the reliability of electronic components increasing year by year with the advancement of technology.

[0087] In an exemplary embodiment, the phrase "based on the reliability characterization model, the standard reliability prediction model in the latest version of the reliability prediction manual is modified to obtain the modified reliability prediction model" in S203 above, such as... Figure 4 As shown, it includes:

[0088] S401, substitute the time parameter into the reliability characterization model to generate correction coefficients.

[0089] The correction factor characterizes how the reliability of electronic components changes with the manufacturing time of the electronic components.

[0090] In this embodiment, the computer device substitutes the time parameter of the target electronic component as an input variable into the reliability characterization model (i.e., relation (1)). The computer device performs the calculation of the reliability characterization model to obtain the correction coefficient. The correction coefficient is negatively correlated with the time parameter, that is, the later the production time represented by the time parameter, the smaller the value of the correction coefficient.

[0091] S402, based on the correction factor, the standard reliability prediction model in the reliability prediction manual is modified to obtain the modified reliability prediction model.

[0092] In this embodiment, the computer device can modify the standard reliability prediction model in the reliability prediction manual according to the correction factor. The standard reliability prediction model can be represented by the relation (2), which is shown below:

[0093] (2);

[0094] in, Failure rate; It represents the influence coefficients of quality, environment, structure, or materials.

[0095] After correction, the revised reliability prediction model of electronic components can be represented by equation (3), which is shown below:

[0096] (3);

[0097] For example, the standard reliability prediction model for chip film resistors in GJB / Z 299D can be expressed by relation (4), which is shown below:

[0098] (4);

[0099] in, Failure rate; For environmental factors, For quality coefficient, The resistance coefficient, This represents the category coefficient.

[0100] After correction, the revised reliability prediction model of the chip film resistor can be expressed by equation (5), which is shown below:

[0101] (5).

[0102] In one exemplary embodiment, the method for predicting the reliability of the above-described electronic components, such as... Figure 5 As shown, it also includes:

[0103] S501, based on the standard reliability prediction model and the modified reliability prediction model, determines the first and second predicted failure rates of electronic components of the same category.

[0104] In this embodiment, the computer device uses both a standard reliability prediction model and a modified reliability prediction model to predict the reliability of the same type of electronic components. The predicted failure rate calculated using the standard reliability prediction model is denoted as the first predicted failure rate. The predicted failure rate calculated using the modified reliability prediction model is denoted as the second predicted failure rate. .

[0105] S502, Obtain manufacturer field data for the same category of electronic components and use the manufacturer field data as a reference failure rate.

[0106] In this embodiment, the computer device acquires on-site data from manufacturers of the same category of electronic components. This on-site data includes, but is not limited to, the cumulative operating hours of the components, the number of statistical samples, and the number of statistical failures. The computer device uses the chi-square estimation method to perform statistical analysis on the on-site data, calculates the failure rate of this type of electronic component, and uses this failure rate as a reference failure rate. This reference failure rate can be used to characterize the true reliability level of such electronic components under actual application or test conditions, serving as a benchmark for subsequent verification and comparison.

[0107] S503, determine the validity of the modified reliability prediction model based on the first predicted failure rate, the second predicted failure rate, and the reference failure rate.

[0108] In this embodiment of the application, the computer device first determines the expected failure rate. Compared with reference failure rate Calculate the first difference This first difference is used to characterize the prediction error of the standard reliability prediction model. Subsequently, the computer equipment calculates the second predicted failure rate. Compared with reference failure rate Calculate the second difference The second difference is used to characterize the prediction error of the revised reliability prediction model. Then, the computer device obtains the deviation value based on the first and second differences. The deviation value characterizes the degree of improvement in prediction error of the corrected reliability prediction model compared to the standard reliability prediction model. Finally, the computer compares the deviation value with a preset threshold. Optionally, this preset threshold can be set to 50%. When the deviation value is greater than or equal to 50%, the computer determines that the corrected reliability prediction model is valid; when the deviation value is less than 50%, the computer determines that the corrected reliability prediction model is invalid.

[0109] When verifying the effectiveness of the above-mentioned modified reliability prediction model, the embodiments of this application can use the following three methods to predict the reliability of the same type of electronic components:

[0110] The first method is a reliability prediction method based on a manual. This method is as follows: Figure 6 As shown, proceed according to the following steps;

[0111] The first step is to divide the reliability prediction units into relatively independent circuit functions and internally serial structures, based on the functional principles of the equipment and system, determine the reliability logical and mathematical relationships between each prediction unit, and establish a product reliability model.

[0112] The second step is to analyze the application method, electrical stress ratio, working environment temperature and other environmental stresses of each component.

[0113] The third step is to compile a list of stress data for the components of the equipment.

[0114] The fourth step is to develop failure rate models for various types of components and calculate the failure rate of each component within each expected unit.

[0115] Fifth, fill the data obtained from steps two through four into the failure rate prediction table;

[0116] The sixth step is to sum the expected failure rates of the components within the cell to obtain the expected failure rate of each cell.

[0117] Step 7: Based on the product's reliability model and the estimated failure rate of each unit, progressively estimate the reliability indices of the equipment and system. The estimated failure rate calculated using this method is denoted as the first estimated failure rate. .

[0118] The second method is the reliability growth-based prediction method. The implementation process of this method is similar to the manual-based reliability prediction method, but the difference lies in the following: when calculating the component failure rate, a reliability characterization model is added to the electronic component prediction model. The growth rate, manufacturing time, and reference time of each type of electronic component are substituted into the reliability growth characterization model, and the corrected predicted failure rate is calculated accordingly. The predicted failure rate calculated by this method is denoted as the second predicted failure rate. .

[0119] The third method is the prediction method based on manufacturer data. This method mainly relies on the reliability data held by the manufacturer, including the cumulative operating or testing hours of components, the number of statistical samples, the number of statistical failures, etc., and uses the chi-square estimation method to analyze its failure rate. Its calculation model can be represented by the relationship (6), which is shown below:

[0120] (6);

[0121] in, For failure rate, The number of failures. For confidence level The chi-square distribution value is used, where N is the sample size and H is the cumulative working or experimental hours. The failure rate calculated by this method is used as the reference failure rate. .

[0122] In summary, based on all the above embodiments, a method for predicting the reliability of electronic components is also provided, such as... Figure 7 As shown, the method includes:

[0123] S601, obtain failure rate data for the same category of electronic components in different historical versions of reliability prediction manuals;

[0124] S602, statistically analyzes the failure rate data and release time in different historical versions of the reliability prediction manual;

[0125] S603 uses a reference time as a benchmark and performs fitting analysis on each failure rate data based on the time interval between each release time and the reference time to obtain the reliability growth rate of electronic components.

[0126] S604, based on the reliability growth rate, substitutes the reliability growth rate into the preset model framework to determine the reliability characterization model of electronic components.

[0127] S605, substitute the time parameters of the target electronic components into the reliability characterization model to generate correction coefficients;

[0128] S606, Based on the correction factor, the standard reliability prediction model in the reliability prediction manual is modified to obtain the modified reliability prediction model;

[0129] S607, Based on the time parameters of the target electronic component and the modified reliability prediction model, determine the expected failure rate of the target electronic component;

[0130] S608, based on the standard reliability prediction model and the modified reliability prediction model, determines the first and second predicted failure rates of electronic components of the same category;

[0131] S609, Obtain on-site data from manufacturers of the same category of electronic components and use the on-site data as a reference failure rate;

[0132] S610, determine the first difference based on the first predicted failure rate and the reference failure rate;

[0133] S611, determine the second difference based on the second predicted failure rate and the reference failure rate;

[0134] S612, determine the deviation value between the first difference and the second difference based on the first difference and the second difference;

[0135] S613, Based on the deviation value, determine the validity of the corrected reliability prediction model.

[0136] The methods described in each of the above steps have been described in the foregoing embodiments. For details, please refer to the foregoing descriptions. They will not be repeated here.

[0137] The above embodiments are explained and illustrated by some examples below, which do not limit the technical solution.

[0138] Example 1: A circuit board is an AC transformer used in a switching power supply. Its function is to process non-sinusoidal signals to achieve voltage conversion. Its functional principle is as follows... Figure 8 As shown, the main components of this circuit board include capacitors, resistors, diodes, transistors, connectors, etc. The failure rate of the corresponding categories of components is analyzed using GJB / Z 299D and the reliability growth model.

[0139] The first step is reliability prediction based on the manual. Specifically, based on the commonly used domestic reliability prediction manual GJB / Z299D, the corresponding prediction model is determined according to the component category, the stress parameters of the product under actual operating conditions are collected, and the reliability prediction of the components in the pulse signal conversion board is carried out using the component stress method. The prediction results are shown in Table 1.

[0140] Table 1

[0141]

[0142] The second step is reliability prediction based on manufacturer data. Specifically, by developing a data collection template, extensive field and reliability test data from manufacturers are collected. Data of the same type are classified, stress reference values ​​are determined, and data under different stress accelerations are converted into data under the reference stress. The converted data are accumulated to obtain the cumulative operating time of the components, and the corresponding confidence level is taken. The failure rate of the corresponding components is estimated based on the chi-square method. The prediction results based on manufacturer data are shown in Table 2.

[0143] Table 2

[0144]

[0145] The third step is prediction based on the reliability characterization model. Specifically, prediction based on the reliability characterization model adds a reliability growth factor to the prediction manual model. To obtain the value of the reliability growth rate, it is necessary to collect failure rate data or manufacturer data from historical versions of the prediction manual. The logarithm of the collected data is then used for linear fitting, and the slope of the fitted equation is the value of the reliability growth rate. Taking connectors as an example, the basic failure rate data of connectors obtained through data collection and processing are shown in Table 3.

[0146] Table 3

[0147]

[0148] For each set of data, a linear fit was performed using the logarithm to obtain the slope and squared difference of the fitted equation. The slopes of multiple fitted equations were then weighted and averaged to obtain the reliability growth rate of this type of component. The connector failure rate data fitting is shown in Table 4.

[0149] Table 4

[0150]

[0151] Based on the above analysis, the coefficients of the fitted equation variables were categorized, and the mean value was taken. The final reliability growth rate of the connector was determined to be 0.0704. The reference time is the approval date of GJB / Z 299D, 2016. This is the connector reliability growth model. middle, =0.0704, =2016, Take the actual production time of the components.

[0152] According to the above process, the basic failure rates of components such as capacitors, resistors, diodes, and transistors are fitted and the arithmetic mean is taken to obtain the reliability growth rate of each type of component. Based on this, the reliability of the components in the pulse signal conversion board is predicted according to the reliability growth prediction model. The results of the component reliability growth rate are shown in Table 5 below.

[0153] Table 5

[0154]

[0155] Fourthly, to verify the effectiveness of the reliability-increase-based prediction method, predictions were made for the same component using both the manual-based prediction method and the reliability-increase-based prediction method. The prediction results were denoted as follows: and The failure rate was determined by selecting either the component manufacturer's predicted field reliability or the results of experimental reliability data analysis as a reference value, and the deviation between the two predicted results was obtained. This refers to the improvement effect of reliability growth-based projections compared to manual-based projections. A comparative analysis of the projections is shown below. Figure 9 As shown.

[0156] Based on the predicted results from the manual, the reliability growth model, and the manufacturer's data, the analysis shows the improvement effect of the reliability growth-based prediction compared to the manual-based prediction. Comparative analysis reveals that introducing a reliability growth coefficient can effectively correct the predicted results using information such as component growth rate and component manufacturing time, thus improving the accuracy and effectiveness of the predictions. The failure rate comparison analysis results are shown in Table 6. Figure 10 As shown;

[0157] Table 6

[0158]

[0159] It should be understood that although the steps in the flowcharts of the embodiments described above are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the embodiments described above may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages in other steps. It is understood that the steps in different embodiments can be freely combined as needed, and all non-contradictory solutions formed by such combinations are within the scope of protection of this application.

[0160] Based on the same inventive concept, this application also provides an electronic component reliability prediction apparatus for implementing the above-described method for predicting the reliability of electronic components. The solution provided by this apparatus is similar to the implementation described in the above-described method. Therefore, the specific limitations of one or more embodiments of the electronic component reliability prediction apparatus provided below can be found in the limitations of the electronic component reliability prediction method described above, and will not be repeated here.

[0161] In one exemplary embodiment, such as Figure 11 As shown, an apparatus for predicting the reliability of electronic components is provided, comprising:

[0162] Module 11 is used to acquire failure rate data for the same category of electronic components in different historical versions of reliability prediction manuals;

[0163] Module 12 is used to determine the reliability characterization model of electronic components based on failure rate data;

[0164] The correction module 13 is used to correct the standard reliability prediction model in the latest version of the reliability prediction manual based on the reliability characterization model, so as to obtain the corrected reliability prediction model.

[0165] Failure module 14 is used to determine the expected failure rate of the target electronic component based on the time parameters of the target electronic component and the modified reliability prediction model. The time parameters characterize the production time information of the target electronic component.

[0166] In one embodiment, the determining module 12 includes:

[0167] The growth unit is used to obtain the reliability growth rate of electronic components based on the relationship between failure rate data and the release time and reference time of the reliability prediction manual.

[0168] The substitution unit is used to substitute the reliability growth rate into a preset model framework to determine the reliability characterization model of the electronic component. In one embodiment, the growth unit includes:

[0169] The statistics subunit is used to statistically analyze the failure rate data and release time in different historical versions of the reliability prediction manual;

[0170] The reference subunit is used to perform fitting analysis on each failure rate data based on the reference time and the time interval between each release time and the reference time, so as to obtain the reliability growth rate of electronic components.

[0171] In one embodiment, the above-mentioned correction module 13 includes:

[0172] The first correction unit is used to substitute the time parameter into the reliability characterization model to generate correction coefficients. The correction coefficients characterize the change in the reliability of electronic components with the manufacturing time of electronic components.

[0173] The second correction unit is used to correct the standard reliability prediction model in the reliability prediction manual according to the correction coefficient, so as to obtain the corrected reliability prediction model.

[0174] In one embodiment, the above-mentioned device for predicting the reliability of electronic components further includes a verification module 15, which specifically includes:

[0175] The prediction unit is used to determine the first and second predicted failure rates of electronic components of the same category based on the standard reliability prediction model and the modified reliability prediction model.

[0176] The reference unit is used to acquire on-site data from manufacturers of the same category of electronic components and to use the on-site data as a reference failure rate.

[0177] The effective unit is used to determine the validity of the modified reliability prediction model based on the first predicted failure rate, the second predicted failure rate, and the reference failure rate.

[0178] In one embodiment, the above-mentioned effective unit includes:

[0179] The first effective sub-unit is used to determine a first difference based on the first expected failure rate and the reference failure rate;

[0180] The second effective sub-unit is used to determine the second difference based on the second predicted failure rate and the reference failure rate;

[0181] The third effective sub-unit is used to determine the deviation value between the first difference and the second difference based on the first difference and the second difference;

[0182] The fourth effective sub-unit is used to determine the effectiveness of the corrected reliability prediction model based on the deviation value.

[0183] Each module in the aforementioned device for predicting the reliability of electronic components can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in a computer device, or stored in the memory of a computer device as software, so that the processor can call and execute the operations corresponding to each module.

[0184] In one exemplary embodiment, a computer device is provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to perform the following steps:

[0185] Obtain failure rate data for the same category of electronic components from different historical versions of reliability prediction manuals;

[0186] Based on failure rate data, a reliability characterization model for electronic components is determined;

[0187] The standard reliability prediction model in the latest version of the reliability prediction manual is modified based on the reliability characterization model to obtain the modified reliability prediction model.

[0188] Based on the time parameters of the target electronic component and the modified reliability prediction model, the expected failure rate of the target electronic component is determined, and the time parameters characterize the production time information of the target electronic component.

[0189] In one embodiment, the processor, when executing a computer program, also performs the following steps:

[0190] Based on the relationship between failure rate data and the release and reference time of the reliability prediction manual, the reliability growth rate of electronic components can be obtained.

[0191] By substituting the reliability growth rate into a pre-defined model framework, a reliability characterization model for electronic components is determined. In one embodiment, the processor, when executing the computer program, further implements the following steps:

[0192] Statistical analysis was conducted on the failure rate data and release dates of different historical versions of the reliability prediction manual;

[0193] Using the reference time as a benchmark, and based on the time interval between each release time and the reference time, a fitting analysis is performed on the failure rate data to obtain the reliability growth rate of electronic components.

[0194] In one embodiment, the processor, when executing a computer program, also performs the following steps:

[0195] Substituting the time parameter into the reliability characterization model generates a correction coefficient, which characterizes the change in the reliability of electronic components with the manufacturing time of the electronic components.

[0196] Based on the correction factor, the standard reliability prediction model in the reliability prediction manual is modified to obtain the modified reliability prediction model.

[0197] In one embodiment, the processor, when executing a computer program, also performs the following steps:

[0198] Based on the standard reliability prediction model and the modified reliability prediction model, the first and second predicted failure rates of electronic components of the same category are determined.

[0199] Obtain on-site data from manufacturers of the same category of electronic components, and use the on-site data as a reference failure rate;

[0200] The validity of the modified reliability prediction model is determined based on the first predicted failure rate, the second predicted failure rate, and the reference failure rate.

[0201] In one embodiment, the processor, when executing a computer program, also performs the following steps:

[0202] The first difference is determined based on the first predicted failure rate and the reference failure rate;

[0203] The second difference is determined based on the second predicted failure rate and the reference failure rate;

[0204] Based on the first difference and the second difference, determine the deviation value between the first difference and the second difference;

[0205] The validity of the revised reliability prediction model is determined based on the deviation value.

[0206] 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:

[0207] Obtain failure rate data for the same category of electronic components from different historical versions of reliability prediction manuals;

[0208] Based on failure rate data, a reliability characterization model for electronic components is determined;

[0209] The standard reliability prediction model in the latest version of the reliability prediction manual is modified based on the reliability characterization model to obtain the modified reliability prediction model.

[0210] Based on the time parameters of the target electronic component and the modified reliability prediction model, the expected failure rate of the target electronic component is determined, and the time parameters characterize the production time information of the target electronic component.

[0211] In one embodiment, when the computer program is executed by a processor, it also performs the following steps:

[0212] Based on the relationship between failure rate data and the release and reference time of the reliability prediction manual, the reliability growth rate of electronic components can be obtained.

[0213] By substituting the reliability growth rate into a pre-defined model framework, a reliability characterization model for electronic components is determined. In one embodiment, when the computer program is executed by a processor, it further performs the following steps:

[0214] Statistical analysis was conducted on the failure rate data and release dates of different historical versions of the reliability prediction manual;

[0215] Using the reference time as a benchmark, and based on the time interval between each release time and the reference time, a fitting analysis is performed on the failure rate data to obtain the reliability growth rate of electronic components.

[0216] In one embodiment, when the computer program is executed by a processor, it also performs the following steps:

[0217] Substituting the time parameter into the reliability characterization model generates a correction coefficient, which characterizes the change in the reliability of electronic components with the manufacturing time of the electronic components.

[0218] Based on the correction factor, the standard reliability prediction model in the reliability prediction manual is modified to obtain the modified reliability prediction model.

[0219] In one embodiment, when the computer program is executed by a processor, it also performs the following steps:

[0220] Based on the standard reliability prediction model and the modified reliability prediction model, the first and second predicted failure rates of electronic components of the same category are determined.

[0221] Obtain on-site data from manufacturers of the same category of electronic components, and use the on-site data as a reference failure rate;

[0222] The validity of the modified reliability prediction model is determined based on the first predicted failure rate, the second predicted failure rate, and the reference failure rate.

[0223] In one embodiment, when the computer program is executed by a processor, it also performs the following steps:

[0224] The first difference is determined based on the first predicted failure rate and the reference failure rate;

[0225] The second difference is determined based on the second predicted failure rate and the reference failure rate;

[0226] Based on the first difference and the second difference, determine the deviation value between the first difference and the second difference;

[0227] The validity of the revised reliability prediction model is determined based on the deviation value.

[0228] In one embodiment, a computer program product is provided, including a computer program that, when executed by a processor, performs the following steps:

[0229] Obtain failure rate data for the same category of electronic components from different historical versions of reliability prediction manuals;

[0230] Based on failure rate data, a reliability characterization model for electronic components is determined;

[0231] The standard reliability prediction model in the latest version of the reliability prediction manual is modified based on the reliability characterization model to obtain the modified reliability prediction model.

[0232] Based on the time parameters of the target electronic component and the modified reliability prediction model, the expected failure rate of the target electronic component is determined, and the time parameters characterize the production time information of the target electronic component.

[0233] In one embodiment, the processor, when executing a computer program, also performs the following steps:

[0234] Based on the relationship between failure rate data and the release and reference time of the reliability prediction manual, the reliability growth rate of electronic components can be obtained.

[0235] By substituting the reliability growth rate into a pre-defined model framework, a reliability characterization model for electronic components is determined. In one embodiment, the processor, when executing the computer program, further implements the following steps:

[0236] Statistical analysis was conducted on the failure rate data and release dates of different historical versions of the reliability prediction manual;

[0237] Using the reference time as a benchmark, and based on the time interval between each release time and the reference time, a fitting analysis is performed on the failure rate data to obtain the reliability growth rate of electronic components.

[0238] In one embodiment, the processor, when executing a computer program, also performs the following steps:

[0239] Substituting the time parameter into the reliability characterization model generates a correction coefficient, which characterizes the change in the reliability of electronic components with the manufacturing time of the electronic components.

[0240] Based on the correction factor, the standard reliability prediction model in the reliability prediction manual is modified to obtain the modified reliability prediction model.

[0241] In one embodiment, the processor, when executing a computer program, also performs the following steps:

[0242] Based on the standard reliability prediction model and the modified reliability prediction model, the first and second predicted failure rates of electronic components of the same category are determined.

[0243] Obtain on-site data from manufacturers of the same category of electronic components, and use the on-site data as a reference failure rate;

[0244] The validity of the modified reliability prediction model is determined based on the first predicted failure rate, the second predicted failure rate, and the reference failure rate.

[0245] In one embodiment, the processor, when executing a computer program, also performs the following steps:

[0246] The first difference is determined based on the first predicted failure rate and the reference failure rate;

[0247] The second difference is determined based on the second predicted failure rate and the reference failure rate;

[0248] Based on the first difference and the second difference, determine the deviation value between the first difference and the second difference;

[0249] The validity of the revised reliability prediction model is determined based on the deviation value.

[0250] 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:

[0251] Obtain failure rate data for the same category of electronic components from different historical versions of reliability prediction manuals;

[0252] Based on failure rate data, a reliability characterization model for electronic components is determined;

[0253] The standard reliability prediction model in the latest version of the reliability prediction manual is modified based on the reliability characterization model to obtain the modified reliability prediction model.

[0254] Based on the time parameters of the target electronic component and the modified reliability prediction model, the expected failure rate of the target electronic component is determined, and the time parameters characterize the production time information of the target electronic component.

[0255] In one embodiment, when the computer program is executed by a processor, it also performs the following steps:

[0256] Based on the relationship between failure rate data and the release and reference time of the reliability prediction manual, the reliability growth rate of electronic components can be obtained.

[0257] By substituting the reliability growth rate into a pre-defined model framework, a reliability characterization model for electronic components is determined. In one embodiment, when the computer program is executed by a processor, it further performs the following steps:

[0258] Statistical analysis was conducted on the failure rate data and release dates of different historical versions of the reliability prediction manual;

[0259] Using the reference time as a benchmark, and based on the time interval between each release time and the reference time, a fitting analysis is performed on the failure rate data to obtain the reliability growth rate of electronic components.

[0260] In one embodiment, when the computer program is executed by a processor, it also performs the following steps:

[0261] Substituting the time parameter into the reliability characterization model generates a correction coefficient, which characterizes the change in the reliability of electronic components with the manufacturing time of the electronic components.

[0262] Based on the correction factor, the standard reliability prediction model in the reliability prediction manual is modified to obtain the modified reliability prediction model.

[0263] In one embodiment, when the computer program is executed by a processor, it also performs the following steps:

[0264] Based on the standard reliability prediction model and the modified reliability prediction model, the first and second predicted failure rates of electronic components of the same category are determined.

[0265] Obtain on-site data from manufacturers of the same category of electronic components, and use the on-site data as a reference failure rate;

[0266] The validity of the modified reliability prediction model is determined based on the first predicted failure rate, the second predicted failure rate, and the reference failure rate.

[0267] In one embodiment, when the computer program is executed by a processor, it also performs the following steps:

[0268] The first difference is determined based on the first predicted failure rate and the reference failure rate;

[0269] The second difference is determined based on the second predicted failure rate and the reference failure rate;

[0270] Based on the first difference and the second difference, determine the deviation value between the first difference and the second difference;

[0271] The validity of the revised reliability prediction model is determined based on the deviation value.

[0272] 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, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, artificial intelligence (AI) processors, etc., and are not limited to these.

[0273] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this application.

[0274] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.

Claims

1. A method for predicting the reliability of electronic components, characterized in that, The method includes: Obtain failure rate data for the same category of electronic components from different historical versions of reliability prediction manuals; Based on the failure rate data, a reliability characterization model for the electronic components is determined; Based on the aforementioned reliability characterization model, the standard reliability prediction model in the latest version of the reliability prediction manual is modified to obtain the modified reliability prediction model. Based on the time parameters of the target electronic component and the modified reliability prediction model, the predicted failure rate of the target electronic component is determined, wherein the time parameters characterize the production time information of the target electronic component.

2. The method according to claim 1, characterized in that, The step of determining the reliability characterization model of the electronic component based on the failure rate data includes: Based on the relationship between the failure rate data and the release time and reference time of the reliability prediction manual, the reliability growth rate of the electronic component is obtained; The reliability growth rate is substituted into a preset model framework to determine the reliability characterization model of the electronic component.

3. The method according to claim 2, characterized in that, The step of obtaining the reliability growth rate of the electronic component based on the relationship between the failure rate data and the publication time and reference time of the reliability prediction manual includes: Statistical analysis was performed on the failure rate data and release time of the reliability prediction manual in different historical versions; Using the reference time as a benchmark, and based on the time interval between each release time and the reference time, the failure rate data are fitted and analyzed to obtain the reliability growth rate of the electronic components.

4. The method according to claim 1, characterized in that, The process of modifying the standard reliability prediction model in the reliability prediction manual based on the reliability characterization model to obtain the modified reliability prediction model includes: Substituting the time parameter into the reliability characterization model generates a correction coefficient, which characterizes the change in the reliability of the electronic component with the manufacturing time of the electronic component. Based on the correction coefficient, the standard reliability prediction model in the reliability prediction manual is modified to obtain the modified reliability prediction model.

5. The method according to any one of claims 1-4, characterized in that, The method further includes: Based on the standard reliability prediction model and the modified reliability prediction model, the first predicted failure rate and the second predicted failure rate of the same category of electronic components are determined. Obtain on-site data from manufacturers of the same category of electronic components, and use the on-site data from manufacturers as a reference failure rate; The validity of the modified reliability prediction model is determined based on the first predicted failure rate, the second predicted failure rate, and the reference failure rate.

6. The method according to claim 5, characterized in that, Determining the validity of the modified reliability prediction model based on the first predicted failure rate, the second predicted failure rate, and the reference failure rate includes: A first difference is determined based on the first predicted failure rate and the reference failure rate; A second difference is determined based on the second predicted failure rate and the reference failure rate; Based on the first difference and the second difference, determine the deviation value between the first difference and the second difference; The validity of the corrected reliability prediction model is determined based on the deviation value.

7. A device for predicting the reliability of electronic components, characterized in that, The device includes: The acquisition module is used to acquire failure rate data for the same category of electronic components in different historical versions of reliability prediction manuals; The determination module is used to determine the reliability characterization model of the electronic component based on the failure rate data; The correction module is used to correct the standard reliability prediction model in the latest version of the reliability prediction manual based on the reliability characterization model, so as to obtain the corrected reliability prediction model. The failure module is used to determine the expected failure rate of the target electronic component based on the time parameters of the target electronic component and the modified reliability prediction model, wherein the time parameters characterize the production time information of the target electronic component.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 6.

10. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 6.

Images