CN115809569A

CN115809569A - Reliability evaluation method and device based on coupling competition failure model

Info

Publication number: CN115809569A
Application number: CN202310049362.9A
Authority: CN
Inventors: 潘广泽; 李丹; 丁小健; 陈勃琛; 孙立军; 王远航; 刘文威; 杨剑锋
Original assignee: China Electronic Product Reliability and Environmental Testing Research Institute
Current assignee: China Electronic Product Reliability and Environmental Testing Research Institute
Priority date: 2023-02-01
Filing date: 2023-02-01
Publication date: 2023-03-17
Anticipated expiration: 2043-02-01
Also published as: CN115809569B

Abstract

The application relates to a reliability evaluation method and device based on a coupling competition failure model. The method comprises the following steps: acquiring a target correlation coefficient of a target product under an acceleration test, and determining a target linear conversion function to which the target correlation coefficient belongs; establishing a nonlinear wiener process of a target product based on a target linear conversion function; according to the solving result of the parameters in the nonlinear wiener process, a first unreliability function when the target product is subjected to multi-element performance degradation failure is obtained, and a second unreliability function when the target product is subjected to sudden failure is obtained; constructing a coupling competition failure model based on a coupling competition relationship between the multi-element performance degradation failure and the burst failure, a first unreliability function and a second unreliability function, and determining a target reliability function of a target product according to the coupling competition failure model; and obtaining a reliability evaluation result of the target product under the acceleration test according to the target reliability function. By adopting the method, the accuracy of the reliability evaluation result of the product can be improved.

Description

Reliability evaluation method and device based on coupling competition failure model

Technical Field

The application relates to the technical field of product performance degradation and reliability analysis, in particular to a reliability evaluation method and device based on a coupling competition failure model.

Background

The accelerated test is to accelerate the failure of a tested product through strengthening test conditions on the premise of not changing the failure mechanism of the product so as to obtain enough information in a short time and evaluate the reliability or service life index of the product under the normal use condition. Since the accelerated test can evaluate the reliability and life of a product in a short time, it is widely used for the reliability evaluation of a highly reliable and long-life product.

However, the reliability evaluation method under the conventional accelerated test only considers the competitive relationship between multiple degradation failures or the competitive relationship between a single degradation failure and a sudden failure, thereby causing the problem of low accuracy of the reliability evaluation result of the product.

Disclosure of Invention

In view of the above, it is necessary to provide a reliability evaluation method and apparatus based on a coupling competition failure model, which can improve the accuracy of the reliability evaluation result of the product.

In a first aspect, the present application provides a reliability evaluation method based on a coupling competition failure model, where the method includes:

acquiring a target correlation coefficient of a target product under an acceleration test, and determining a target linear conversion function to which the target correlation coefficient belongs; the target correlation coefficient represents a linear relationship between the performance degradation of the target product and time;

establishing a nonlinear wiener process of the target product based on the target linear conversion function;

according to the solving result of the parameters in the nonlinear wiener process, a first unreliability function of the target product when the multi-element performance is degraded and failed is obtained, and a second unreliability function of the target product when the target product is suddenly failed is obtained;

constructing a coupling competition failure model based on the coupling competition relationship between the multi-element performance degradation failure and the burst failure, the first unreliability function and the second unreliability function, and determining a target reliability function of the target product according to the coupling competition failure model;

and obtaining a reliability evaluation result of the target product under the acceleration test according to the target reliability function.

In one embodiment, the obtaining a target correlation coefficient of a target product under an acceleration test and determining a target linear transfer function to which the target correlation coefficient belongs includes:

acquiring performance degradation data and a plurality of linear conversion functions of a plurality of target products under an acceleration test;

for each linear conversion function, substituting the performance degradation data of a plurality of target products into a function formed by the linear conversion function to obtain a correlation coefficient corresponding to the linear conversion function;

determining a target correlation coefficient satisfying a target condition among the correlation coefficients based on the numerical value of each of the correlation coefficients;

and determining a target linear conversion function for establishing a nonlinear wiener process according to the target correlation coefficient.

In one embodiment, the determining a target linear transfer function for establishing a nonlinear wiener process according to the target correlation coefficient includes:

determining a maximum likelihood function corresponding to a function term of the target correlation coefficient based on the numerical value of the target correlation coefficient;

solving the maximum likelihood function corresponding to the function item of the target correlation coefficient to obtain the value of each parameter in the target linear conversion function to which the target correlation coefficient belongs;

and determining a target linear conversion function for establishing a nonlinear wiener process according to the value of each parameter.

In one embodiment, after the establishing of the non-linear wiener process of the target product based on the target linear conversion function, the method includes:

constructing a probability density function of the target product when the multi-element performance is degraded and failed;

determining a maximum likelihood function of a non-linear wiener process of the target product based on the probability density function;

and solving the maximum likelihood function of the target product in the nonlinear wiener process to obtain a solving result of each parameter in the nonlinear wiener process.

In one embodiment, the obtaining a first unreliability function of the target product when the multivariate performance degradation fails and obtaining a second unreliability function of the target product when the target product suddenly fails according to the solution result of the parameter in the nonlinear wiener process includes:

obtaining a solving result of each parameter in the nonlinear wiener process, and constructing an unreliable degree sub-function corresponding to each performance of the target product;

substituting the solving result into the unreliable subfunction corresponding to each performance to obtain a first unreliable function of the target product when the multi-element performance is degraded and failed;

establishing a sudden unreliability function of the target product when the target product suddenly fails, and acquiring sudden failure time of the target product;

and performing parameter solving processing on parameters in the maximum likelihood function corresponding to the burst unreliability function based on the burst unreliability function and the time of the burst failure to obtain a second unreliability function of the target product when the burst failure occurs.

In one embodiment, the determining a target reliability function of the target product according to the coupling competition failure model includes:

establishing a maximum likelihood function corresponding to the coupling competition failure model to calculate parameter values in the coupling competition failure model to obtain a parameter solving result;

substituting the parameter solving result into the coupling competition failure model to obtain a target reliability function.

In one embodiment, the obtaining, according to the target reliability function, a reliability evaluation result of the target product under the accelerated test includes:

performing integral processing on a function item of the target reliability function to obtain a first average fault interval time of the target product under the acceleration test;

performing product processing on the first average fault interval time and the acceleration factor of the target product to obtain a second average fault interval time of the target product under a normal test;

and obtaining a reliability evaluation result of the target product according to the first average fault interval time and the second average fault interval time.

In a second aspect, the present application provides a reliability evaluation apparatus based on a coupling contention failure model, where the apparatus includes:

the target linear conversion function determining module is used for acquiring a target correlation coefficient of a target product under an acceleration test and determining a target linear conversion function to which the target correlation coefficient belongs;

the nonlinear wiener process building module is used for building a nonlinear wiener process of the target product based on the target linear conversion function;

the unreliability function determination module is used for obtaining a first unreliability function of the target product when the multivariate performance degradation fails according to the solving result of the parameters in the nonlinear wiener process, and obtaining a second unreliability function of the target product when the target product fails suddenly;

a target reliability function determination module, configured to construct a coupling competition failure model based on a coupling competition relationship between the multivariate performance degradation failure and the sudden failure, the first unreliability function, and the second unreliability function, and determine a target reliability function of the target product according to the coupling competition failure model;

and the reliability evaluation result acquisition module is used for acquiring a reliability evaluation result of the target product under the acceleration test according to the target reliability function.

In a third aspect, the present application provides a computer device comprising a memory storing a computer program and a processor implementing the steps of the method described above when the processor executes the computer program.

In a fourth aspect, the present application provides a computer-readable storage medium having stored thereon a computer program which, when executed by a processor, performs the steps of the method described above.

In a fifth aspect, the present application provides a computer program product comprising a computer program which, when executed by a processor, performs the steps of the method described above.

According to the reliability evaluation method and device based on the coupling competition failure model, the target conversion function is obtained from the plurality of linear conversion functions according to the obtained target correlation coefficient, the nonlinear wiener process of the target product is established according to the target conversion function, the optimization of the conversion function can be realized, the nonlinear characteristic of the performance degradation of the target product is described, and the problem that the traditional reliability evaluation method is low in accuracy is solved; by considering the coupling competition relationship between the multi-element performance degradation failure and the burst failure and establishing a coupling competition failure model and a target reliability function of the target product according to the first unreliability function and the second unreliability function, the accuracy of the reliability evaluation result of the target product can be further improved.

Drawings

FIG. 1 is a diagram of an embodiment of an application environment of a reliability evaluation method based on a coupling race failure model;

FIG. 2 is a schematic flow chart illustrating a reliability evaluation method based on a coupling race failure model according to an embodiment;

FIG. 3 is a schematic flowchart of a reliability evaluation method based on a coupling race failure model according to another embodiment;

FIG. 4 is a block diagram illustrating an exemplary reliability evaluation apparatus based on a coupling race failure model;

FIG. 5 is a diagram illustrating an internal structure of a computer device according to an embodiment.

Detailed Description

In order to make the objects, technical solutions and advantages of the present application more clearly understood, the present application is further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of and not restrictive on the broad application.

The reliability evaluation method based on the coupling competition failure model provided by the embodiment of the application can be applied to the application environment shown in fig. 1. Wherein the terminal 102 communicates with the server 104 via a network. The data storage system may store data that the server 104 needs to process. The data storage system may be integrated on the server 104, or may be located on the cloud or other network server. The server 104 may obtain a target correlation coefficient of the target product under the accelerated test by enhancing the test condition of the target product, and determine a target linear transformation function to which the target correlation coefficient belongs. The server 104 can establish a non-linear wiener process of the target product under an accelerated test according to the obtained target linear conversion function, and solve parameters in the non-linear wiener process, so that a first unreliability function of the target product when the multi-element performance degradation fails can be obtained. The server 104 also obtains a second unreliability function for the target product in the event of a catastrophic failure. The server 104 may obtain a coupling competition failure model and a target reliability function of the target product by using a first unreliability function of the target product when the multi-element performance degradation fails and a second unreliability function of the target product when the target product suddenly fails according to the coupling competition relationship between the multi-element performance degradation failure and the sudden failure of the target product. The server 104 may obtain a reliability evaluation result of the target product under the acceleration test by performing operation processing on the target reliability function. The terminal 102 may be, but not limited to, various personal computers, notebook computers, smart phones, tablet computers, internet of things devices and portable wearable devices, and the internet of things devices may be smart speakers, smart televisions, smart air conditioners, smart car-mounted devices, and the like. The portable wearable device can be a smart watch, a smart bracelet, a head-mounted device, and the like. The server 104 may be implemented as a stand-alone server or as a server cluster comprised of multiple servers.

In one embodiment, as shown in fig. 2, a reliability evaluation method based on a coupling competition failure model is provided, which is described by taking the method as an example applied to the server in fig. 1, and includes the following steps:

step 202, obtaining a target correlation coefficient of the target product under an acceleration test, and determining a target linear conversion function to which the target correlation coefficient belongs. The target correlation coefficient represents a linear relationship between the performance degradation of the target product and time.

Wherein, the target product refers to a product which can be subjected to an accelerated test.

The accelerated test is to accelerate the failure of a tested target product by strengthening test conditions on the premise of ensuring that the failure mechanism of the target product is not changed, so that necessary information can be obtained in a short time to evaluate the reliability or service life index of the target product under normal conditions. Through an accelerated test, the failure reason of the target product can be quickly found out, and the reliability index of the target product can be quickly evaluated. For example, raising the temperature of the target product to be tested to a temperature point above which the material properties change or a dormancy activation threshold temperature results in failure that does not occur in normal use, thereby completing accelerated testing of the target product.

The target correlation coefficient is a correlation coefficient that meets the condition selected from the obtained plurality of correlation coefficients, and is a measure of the degree of linear correlation between the study variables. For example, the use of target correlation coefficients can be used to describe a linear relationship between the performance degradation of the target product and time.

The target linear conversion function is a linear conversion function to which the target correlation coefficient belongs. For example, the correlation coefficient obtained using the linear transfer function 1 is A ₁ The correlation coefficient obtained using the linear transfer function 2 is A ₂ But coefficient of correlation A ₁ Greater than the correlation coefficient A ₂ Then the correlation coefficient A ₁ The correlation coefficient is the target correlation coefficient, and the associated linear transfer function 1 is the target linear transfer function.

Optionally, the server selects a target correlation coefficient meeting the condition from the plurality of correlation coefficients, and then determines a linear conversion function to which the target correlation coefficient belongs as a target linear conversion function.

And step 204, establishing a nonlinear wiener process of the target product based on the target linear conversion function.

Wherein the nonlinear wiener process is a tool for describing nonlinear characteristics of the target product performance degradation.

Optionally, the server linearly transforms the target to which the target correlation coefficient belongs

The obtained parameters are taken as parameters and substituted into another function, so that the nonlinear wiener process of the target product under the accelerated test can be obtained

，yIs a target productxThe value of the performance at the moment in time,μfor the intermediate unknown parameters that need to be solved,μobey mean value ofηAnd variance ofσ _η The normal distribution of (a) is,

in order to be a function of the brownian drift,σ、ηandσ _η are intermediate unknown parameters that need to be solved.

And step 206, obtaining a first unreliability function of the target product when the multi-element performance is degraded and failed according to the solving result of the parameters in the nonlinear wiener process, and obtaining a second unreliability function of the target product when the target product is suddenly failed.

Wherein, the multiple performance degradation failure means that multiple performances of the target product are gradually degraded and finally exceed a specified range. A sudden failure refers to a sudden loss of a specified function of a target product at a certain time, also referred to as a hard failure.

Optionally, the server obtains parameters according to the solutionσ、ηAndσ _η can obtain a parameterμAnd a parameter ofσAndμthe first unreliable function when a plurality of performances of the target product gradually degrade and finally exceed a specified range can be obtained by substituting the value of (A) into the nonlinear wiener processF _d (x)=1-C(1-F ₁ (x),1-F ₂ (x),…,1-F _k (x),θ)，θFor the intermediate unknown parameter, C (-) represents 1-F ₁ (x),1-F ₂ (x),…,1-F ₂ (x) The connection function of (a) is selected,F _k (x) And representing the unreliable subfunction corresponding to the kth individual performance of the target product. The server also acquires a second unreliable function F when the target product suddenly loses the specified function at a certain moment _s (x)。

And 208, constructing a coupling competition failure model based on the coupling competition relationship between the multi-element performance degradation failure and the burst failure, the first unreliability function and the second unreliability function, and determining a target reliability function of the target product according to the coupling competition failure model.

The coupling competition relationship refers to an interaction relationship between two things.

Optionally, the server constructs a coupling competition failure model of the target product by considering a coupling competition relationship between interaction and mutual influence between the multi-element performance degradation failure and the sudden failure of the target product and on the basis of the obtained first unreliability function when the multi-element performance degradation failure occurs and the obtained second unreliability function when the multi-element performance degradation failure occurs, and obtains a target reliability function of the target product by solving unknown parameters in the coupling competition failure model.

And step 210, obtaining a reliability evaluation result of the target product under the acceleration test according to the target reliability function.

The reliability evaluation result refers to the evaluation result of the capability of the element or the system to continuously realize the function within a given time interval and under a specified condition.

Optionally, the server solves the average interval time of the target product with faults by using a target reliability function, and evaluates the reliability of the target product under an acceleration test according to the length of the average interval time of the target product with faults, so as to obtain a capability evaluation result of the target product, which continuously realizes the function of the target product within a given time interval under a specified condition.

According to the reliability evaluation method based on the coupling competition failure model, the target conversion function is obtained from the plurality of linear conversion functions according to the obtained target correlation coefficient, and the nonlinear wiener process of the target product is established according to the target conversion function, so that the optimization of the conversion function can be realized, the nonlinear characteristic of the performance degradation of the target product can be described, and the problem that the traditional reliability evaluation method is low in accuracy is solved; by considering the coupling competition relationship between the multi-element performance degradation failure and the burst failure and establishing a coupling competition failure model and a target reliability function of the target product according to the first unreliability function and the second unreliability function, the accuracy of the reliability evaluation result of the target product can be further improved.

In one embodiment, obtaining a target correlation coefficient of a target product under an acceleration test, and determining a target linear transfer function to which the target correlation coefficient belongs includes:

and acquiring performance degradation data and a plurality of linear conversion functions of a plurality of target products under an accelerated test.

And substituting the performance degradation data of the plurality of target products into the function formed by the linear conversion functions aiming at each linear conversion function to obtain the correlation coefficient corresponding to the linear conversion function.

Based on the value of each correlation coefficient, a target correlation coefficient satisfying a target condition among the correlation coefficients is determined.

The performance degradation data is obtained by testing the target product in the test process, and can provide rich and key information for life prediction and reliability evaluation of the target product.

The linear transfer function mainly comprises

Etc., x represents the time of the accelerated test,

is time of dayxAs a function of (a) or (b),aandbare unknown parameters.

Optionally, the server obtains performance degradation data obtained by a plurality of performance tests on the target product under the accelerated test (x _i ,y _i )，x _i Is the time of the i-th test,y _i the test performance value of the ith time. The server also obtains the commonly used linear transfer function

. Performance degradation data to be obtained by the server (x _i ,y _i ) Substituting into a function with linear conversion function as parameter to obtain

（1）

In the formula (1), the first and second groups of the compound,x _i is the time of the i-th test,y _i for the performance value of the test at the ith time,

represents the average of all the performance test values,

means all of

Is determined by the average value of (a) of (b),

the linear transfer function substituted into the test data of the ith time is shown, and r represents the correlation coefficient. The server calculates the correlation coefficients obtained by all target products under the accelerated test and solves the average value of the correlation coefficients of all the target products under each linear transfer function, so that the linear transfer function corresponding to the maximum average value, namely the target linear transfer function to which the target correlation function meeting the target condition belongs, can be obtained. Maximum mean value

The calculation formula of (2) is as follows:

（2）

in the formula (2)mThe total number of the target products is,r _j a correlation coefficient representing performance degradation of the jth target product.

In this embodiment, the relationship between the performance degradation of the target product and time can be more fully expressed by selecting the linear conversion function corresponding to the correlation coefficient of the maximum average value as the target conversion function.

In one embodiment, determining a target linear transfer function for establishing a non-linear wiener process according to the target correlation coefficient includes:

and determining a maximum likelihood function corresponding to the function item of the target correlation coefficient based on the numerical value of the target correlation coefficient.

And solving the maximum likelihood function corresponding to the function item of the target correlation coefficient to obtain the value of each parameter in the target linear conversion function to which the target correlation coefficient belongs.

And determining a target linear conversion function for establishing the nonlinear wiener process according to the value of each parameter.

The maximum likelihood function is used for estimating the probability of the occurrence of the event in an approximate mathematical mode, and compared with the method for estimating the probability according to the proportion, the maximum likelihood function has more mathematical reasoning and rigor.

Optionally, the server takes a logarithm of a function item composed of parameters of a target linear conversion function to which the target correlation coefficient belongs, and obtains a maximum likelihood function corresponding to the function item based on a numerical value of the target correlation coefficient. And the server solves each parameter in the maximum likelihood function corresponding to the function item according to the solving mode of the maximum likelihood function, so as to obtain the value of each unknown parameter in the target linear conversion function. And the server substitutes the solved parameter values into the target linear conversion function again, so that the target linear conversion function for constructing the nonlinear wiener process can be obtained.

In this embodiment, the maximum likelihood function is used to solve the unknown parameters in the target linear transformation function, so that the solving process of the unknown parameters can be simplified, and the rate of obtaining the solving result of the unknown parameters is increased.

In one embodiment, after establishing the non-linear wiener process of the target product based on the target linear transfer function, the method includes:

and constructing a probability density function of the target product when the multi-element performance is degraded and failed.

And determining a maximum likelihood function of the nonlinear wiener process of the target product based on the probability density function.

And solving the maximum likelihood function of the target product in the nonlinear wiener process to obtain the solving result of each parameter in the nonlinear wiener process.

The probability density function is a function describing the possibility that the output value of the random variable is near a certain value taking point, and the probability that the value of the random variable falls in a certain area is the integral of the probability density function in the area.

Optionally, the server constructs a probability density function of the target product when the multi-element performance degradation fails according to the condition of the target product when the multi-element performance degradation fails under the acceleration testf(x;σ,η,σ _η ) Therefore, the maximum likelihood function of the target product in the nonlinear wiener process when the multi-element performance degradation fails can be obtained as follows:

（3）

in the formula (3)x _ji The performance value of the ith test of the jth target product, m represents the total number of the target products, n represents the number of performance tests,σ、ηandσ _η are intermediate unknown parameters that need to be solved. The server solves the system of equations by

Obtaining intermediate unknown parametersσ,η,σ _η The value of (c).

In this embodiment, the maximum likelihood function is used to solve the unknown parameters in the nonlinear wiener process, so that the solving process of each parameter in the nonlinear wiener process can be simplified, and the rate of obtaining the solving result of each parameter in the nonlinear wiener process is increased.

In one embodiment, obtaining a first unreliability function of a target product when the multivariate performance degradation fails and obtaining a second unreliability function of the target product when the target product suddenly fails according to a solution result of parameters in a nonlinear wiener process includes:

step 302, obtaining a solving result of each parameter in the nonlinear wiener process, and constructing an unreliable subfunction corresponding to each performance of the target product.

Wherein, the unreliability subfunction refers to functions respectively established according to a plurality of performances of the target product. For example, for performance 1 of the target product, a corresponding unreliability subfunction B is established ₁ Aiming at the performance 2 of the target product, establishing corresponding unavailabilityReliability function B ₂ 。

Optionally, after the server establishes the maximum likelihood function of the nonlinear wiener process, the value of each unknown parameter in the nonlinear wiener process can be obtained by solving. The server also constructs a corresponding unreliability subfunction for each performance of the target product.

And 304, substituting the solution result into the unreliability subfunction corresponding to each performance to obtain a first unreliability function of the target product when the multi-performance degradation fails.

The first unreliability function is obtained according to the coupling competition relationship when the multiple performances of the target product are subjected to degradation failure. For example, the target product has k properties, and the unreliable subfunctions of the performance degradation failure corresponding to the k properties are respectively F ₁ (x),F ₂ (x),…,F _k (x) Then the first unreliability function of the target product at the time of multivariate performance degradation failure isF _d (x)=1-C(1-F ₁ (x),1-F ₂ (x),…,1-F _k (x),θ) Parameter ofθIntermediate unknown parameters.

Optionally, after obtaining the solution result of each unknown parameter in the nonlinear wiener process, the server substitutes the solution result into the unreliability subfunction corresponding to each performance, so as to obtain the unreliability subfunction corresponding to the performance k

. Where D is a critical value for performance degradation, A and B are intermediate parameters,

，

. The server combines the unreliable subfunctions corresponding to all the performances of the target product, thereby obtaining a first unreliable function of the target product when the multi-element performance is degraded and failedF _d (x)=1-C(1-F ₁ (x),1-F ₂ (x),…,1-F _k (x),θ) Parameter ofθIntermediate unknown parameters. The server adopts maximum likelihood function to obtain parametersθValue of (2)。

And step 306, establishing a sudden unreliability function of the target product when the target product is suddenly failed, and acquiring the time of the sudden failure of the target product.

Wherein a sudden failure is a spontaneous unpredictable failure of the target product.

Optionally, the server establishes a sudden unreliability function of the target product in sudden failure for the target product in response to the sudden failure of the target product

Whereinα、βAndx ₀ intermediate unknown parameters. The server also obtains the time of each sudden failure of the target product.

And 308, performing parameter solving processing on parameters in the maximum likelihood function corresponding to the sudden unreliability function based on the sudden unreliability function and the time of sudden failure to obtain a second unreliability function of the target product when sudden failure occurs.

Optionally, the server performs a function F according to the sudden unreliability of the target product when sudden failure occurs under the acceleration test _t (x) And the time of the sudden failure of p target productsx ₁ ,x ₂ ,…,x _p And obtaining a maximum likelihood function lnL corresponding to the burst unreliability function:

(4)

in the formula (4)α、βAndx ₀ for intermediate unknown parameters, x _q The time of the sudden failure for the qth target product. The server can obtain intermediate unknown parameters by solving the maximum likelihood function lnLα、βAndx ₀ the server substitutes the solved parameter values into a burst unreliability function F _t (x) Then, the accelerated test is obtainedSecond uncertainty function of target product burst failureF _s (x)。

In the embodiment, unknown parameters are added to the burst unreliability function when the target product is in burst failurex ₀ The application range of the sudden failure unreliability function can be enlarged, and therefore the application range of the constructed second unreliability function is wider.

In one embodiment, determining the target reliability function for the target product based on the coupled race failure model comprises:

and establishing a maximum likelihood function corresponding to the coupling competition failure model to calculate parameter values in the coupling competition failure model and obtain a parameter solving result.

The coupling competition failure model is a model which is constructed according to the coupling competition relationship among multiple performance failure modes of the target product and the unreliability function corresponding to each performance failure mode and is used for calculating the reliability of the product.

The target reliability function is obtained after unknown parameters in the coupling competition model are solved.

Optionally, the server uses a first unreliability function F when the multivariate performance fails according to the coupling competition relationship between the multivariate performance failure and the sudden failure of the target product _d (x) And a second unreliability function F in case of a sudden failure _s (x) On the basis, a coupling competition failure model of the target product under an acceleration test is established:

R(x)=C ₁ (1-F _d (x),1-F _s (x),θ ₁ ) (5)

in the formula (5)θ ₁ As an unknown parameter, C ₁ (. Is) 1-F _d (x),1-F _s (x) The connection function of (2). The server adopts the maximum likelihood function to carry out logarithm taking on the functions at the equal sign ends of the coupling competition failure model and the unknown parameters in the coupling competition modelθ ₁ Solving is carried out to obtain parametersθ ₁ The result is solved for the parameters of (2). The server will be right to the parameterθ ₁ Substituting the parameter solving result into the coupling competition failure model, thereby obtaining a target reliability function R (x) without unknown parameters.

In the embodiment, the target reliability function is determined by considering the coupling competition relationship between the multi-element performance degradation failure and the burst failure, so that the problem of low evaluation precision of an analysis method based on a single failure mode or multiple failure modes which are independent from each other can be solved.

In one embodiment, obtaining a reliability evaluation result of a target product under an acceleration test according to a target reliability function includes:

and performing integral processing on the function item of the target reliability function to obtain the first average fault interval time of the target product under the acceleration test.

And performing product processing on the first average fault interval time and the acceleration factor of the target product to obtain a second average fault interval time of the target product under a normal test.

The first average fault interval time and the second average fault interval time refer to the average time of the target product working correctly in the interval between two adjacent faults, also called average no-fault working time, and are quantities for marking how long the target product can work on average. The first mean time between failures is the amount of mean working time of the target product under the accelerated test, and the second mean time between failures is the amount of mean working time of the target product under the normal test.

The acceleration factor is an acceleration effect reflecting the level of acceleration stress in the accelerated life test, i.e., is a function of the acceleration stress.

The reliability evaluation result is determined according to the duration of the first average fault interval time and the second average fault interval time, and the longer the interval time is, the higher the reliability of the target product is.

Optionally, a server to target reliability functionIntegrating function terms of the number R (x) to obtain a first average fault interval time of the target product, which represents the average time of correct work in two adjacent fault intervals under an acceleration test

. The server multiplies the first Mean Time Between Failures (MTBF) by an acceleration factor M which reflects the acceleration effect of the acceleration stress level in the acceleration life test, so that a second Mean Time Between Failures (MTBF) which represents the mean time of correct work in two adjacent failure intervals under normal test of the target product is obtained ₀ = M × MTBF. And the server obtains the reliability evaluation result of the target product according to the duration of the first average fault interval time and the duration of the second average fault interval time.

In this embodiment, the average time of the target product working correctly in the two adjacent fault intervals can be obtained by obtaining the average fault interval time of the target product under the acceleration test and the normal test, respectively, so as to obtain the accurate reliability evaluation result of the target product.

The application also provides an application scenario, and the reliability evaluation method based on the coupling competition failure model is applied to the application scenario. Specifically, the reliability evaluation method based on the coupling competition failure model is applied to the application scene as follows: analyzing the target product by utilizing the performance 1 and the performance 2 of the target product, and firstly, fitting and optimizing the performance 1 by adopting a common linear transfer function to obtain

The correlation coefficient of the linear conversion function is maximum, and the fitting result is optimal. Then select

The linear transfer function is used as a target linear transfer function and the values of the unknown parameters a and b are solved to obtain a target linear transfer function of performance 1 of

. According to a target linear transfer function

The nonlinear wiener process is established as

. Solving to obtain unknown parameters in the nonlinear wiener process through a maximum likelihood functionμ、σAndσ _η to obtain an unreliable subfunction of performance degradation failure of target product Performance 1 under accelerated testF ₁ (x). Obtaining the unreliable subfunction of Performance degradation failure under accelerated stress for Performance 2 of the target product in the same wayF ₂ (x). According to the coupling competition relationship between the performance 1 and the performance 2 of the target product, a first unreliability function of the target product in the multi-element performance degradation failure is obtainedF _d (x)=1-C(1-F ₁ (x),1-F ₂ (x),θ) Solving to obtain parametersθIs 1.231, substituting the parametersθValue of 1.231 to F _d (x) Then, a first unreliability function of the target product with multi-element performance degradation failure under the accelerated test is obtainedF _d (x)=1-C(1-F ₁ (x),1-F ₁ (x),1.231)。

Modeling the sudden failure of the target product in the acceleration test to obtain a second unreliability function of the sudden failure of the product in the acceleration test of the target product

. Considering the coupling competition relationship between the multiple performance degradation failures and the burst failures, and taking the first unreliability degree function into accountF _d (x) And a second unreliability functionF _s (x) On the basis, a coupling competition failure model of a target product under an acceleration test is established:R(x)=C ₁ (1-F _d (x),1-F _s (x),θ ₁ ). Solving unknown parameters in the coupling competition failure model by using a maximum likelihood function to obtainθ ₁ It was 1.351. Finally obtaining a target reliability function of the target product under the acceleration test asR(x)=C ₁ (1-F _d (x),1-F _s (x),1.351). Integrating the function item of the target reliability function to obtain the first average fault interval time of the target product under the accelerated stress test

. The acceleration factor of the target product under the acceleration test is 9.8, and the second Mean Time Between Failures (MTBF) of the target product under the normal stress test is obtained ₀ =9.8 x 3462h =33927.6h. And obtaining a reliability evaluation result of the target product according to the duration of the first average fault interval time and the duration of the second average fault interval time.

It should be understood that, although the steps in the flowcharts related to the embodiments as described above are sequentially displayed as indicated by arrows, the steps are not necessarily performed sequentially as indicated by the arrows. The steps are not performed in the exact order shown and described, and may be performed in other orders, unless explicitly stated otherwise. Moreover, at least a part of the steps in the flowcharts related to the embodiments described above may include multiple steps or multiple stages, which are not necessarily performed at the same time, but may be performed at different times, and the execution order of the steps or stages is not necessarily sequential, but may be rotated or alternated with other steps or at least a part of the steps or stages in other steps.

Based on the same inventive concept, the embodiment of the application also provides a reliability evaluation device based on the coupling competition failure model, which is used for realizing the reliability evaluation method based on the coupling competition failure model. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the method, so that specific limitations in one or more embodiments of the reliability evaluation device based on the coupling competition failure model provided below can be referred to the limitations of the reliability evaluation method based on the coupling competition failure model, and details are not repeated herein.

In one embodiment, as shown in fig. 4, there is provided a reliability evaluation apparatus based on a coupling competition failure model, including:

a target linear transformation function determining module 402, configured to obtain a target correlation coefficient of a target product under an acceleration test, and determine a target linear transformation function to which the target correlation coefficient belongs; the target correlation coefficient represents a linear relationship between the performance degradation of the target product and time.

And a nonlinear wiener process building module 404, configured to build a nonlinear wiener process of the target product based on the target linear transfer function.

And the unreliability function determination module 406 is configured to obtain a first unreliability function of the target product when the multivariate performance degradation fails according to a solution result of the parameter in the nonlinear wiener process, and obtain a second unreliability function of the target product when the target product fails suddenly.

And the target reliability function determining module 408 is configured to construct a coupling competition failure model based on the coupling competition relationship between the multivariate performance degradation failure and the sudden failure, the first unreliability function and the second unreliability function, and determine a target reliability function of the target product according to the coupling competition failure model.

And the reliability evaluation result obtaining module 410 is configured to obtain a reliability evaluation result of the target product under the acceleration test according to the target reliability function.

In one embodiment, the target linear transfer function determining module comprises:

and the data acquisition unit is used for acquiring performance degradation data and a plurality of linear conversion functions of a plurality of target products under an accelerated test.

And the correlation coefficient acquisition unit is used for substituting the performance degradation data of the plurality of target products into a function formed by the linear conversion functions aiming at each linear conversion function to obtain the correlation coefficient corresponding to the linear conversion function.

And the target correlation coefficient acquisition unit is used for determining a target correlation coefficient which meets the target condition in the correlation coefficients based on the numerical value of each correlation coefficient.

And the target linear conversion function determining unit is used for determining a target linear conversion function for establishing a nonlinear wiener process according to the target correlation coefficient.

In one embodiment, the target linear transfer function determining unit includes:

and the maximum likelihood function determining subunit is used for determining a maximum likelihood function corresponding to the function item of the target correlation coefficient based on the numerical value of the target correlation coefficient.

And the parameter solving subunit is used for solving the maximum likelihood function corresponding to the function item of the target correlation coefficient to obtain the value of each parameter in the target linear conversion function to which the target correlation coefficient belongs.

And the target linear conversion function determining subunit is used for determining a target linear conversion function for establishing the nonlinear wiener process according to the value of each parameter.

In one embodiment, the nonlinear wiener process building module comprises:

and the probability density function constructing unit is used for constructing a probability density function of the target product when the multivariate performance is degraded and failed.

And the maximum likelihood function determining unit is used for determining the maximum likelihood function of the nonlinear wiener process of the target product based on the probability density function.

And the first parameter solving unit is used for solving the maximum likelihood function of the nonlinear wiener process of the target product to obtain the solving result of each parameter in the nonlinear wiener process.

In one embodiment, the unreliability function determination module comprises:

and the unreliability subfunction building unit is used for obtaining the solving result of each parameter in the nonlinear wiener process and building an unreliability subfunction corresponding to each performance of the target product.

And the first unreliability function obtaining unit is used for substituting the solving result into the unreliability subfunction corresponding to each performance to obtain a first unreliability function of the target product when the multi-element performance is degraded and failed.

And the sudden unreliability function building unit is used for building a sudden unreliability function of the target product when the target product is in sudden failure and acquiring the time of the target product in sudden failure.

And the second unreliability function obtaining unit is used for carrying out parameter solving processing on parameters in the maximum likelihood function corresponding to the burst unreliability function based on the burst unreliability function and the time of the burst failure to obtain a second unreliability function of the target product when the burst failure occurs.

In one embodiment, the target reliability function determination module comprises:

and the second parameter solving unit is used for establishing a maximum likelihood function corresponding to the coupling competition failure model so as to calculate the parameter values in the coupling competition failure model and obtain a parameter solving result.

And the target reliability function acquisition unit is used for substituting the parameter solving result into the coupling competition failure model to obtain a target reliability function.

In one embodiment, the reliability evaluation result obtaining module includes:

and the first average fault interval time acquisition unit is used for performing integral processing on the function item of the target reliability function to obtain the first average fault interval time of the target product under the acceleration test.

And the second average fault interval time acquisition unit is used for multiplying the first average fault interval time by the acceleration factor of the target product to obtain the second average fault interval time of the target product under the normal test.

And the reliability evaluation result acquisition unit is used for acquiring the reliability evaluation result of the target product according to the first average fault interval time and the second average fault interval time.

The modules in the reliability evaluation device based on the coupling competition failure model can be wholly or partially realized by software, hardware and a combination thereof. The modules can be embedded in a hardware form or independent from a processor in the computer device, and can also be stored in a memory in the computer device in a software form, so that the processor can call and execute operations corresponding to the modules.

In one embodiment, a computer device is provided, which may be a server, the internal structure of which may be as shown in fig. 5. The computer device includes a processor, a memory, an Input/Output interface (I/O for short), and a communication interface. The processor, the memory and the input/output interface are connected through a system bus, and the communication interface is connected to the system bus through the input/output interface. Wherein the processor of the computer device is configured 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 an operating system and computer programs in the non-volatile storage medium. The database of the computer equipment is used for storing a target correlation coefficient, a target linear conversion function, a nonlinear wiener process of a target product, a solving result of parameters in the nonlinear wiener process, a first unreliability function, a second unreliability function, a target reliability function and reliability evaluation result data of the target product under an acceleration test. The input/output interface of the computer device is used for exchanging information between the processor and an external device. The communication interface of the computer device is used for connecting and communicating with an external terminal through a network. The computer program is executed by a processor to implement a reliability evaluation method based on a coupling race failure model.

It will be appreciated by those skilled in the art that the configuration shown in fig. 5 is a block diagram of only a portion of the configuration associated with the present application, and is not intended to limit the computing device to which the present application may be applied, and that a particular computing device may include more or less components than those shown, or may combine certain components, or have a different arrangement of components.

In one embodiment, a computer device is provided, comprising a memory and a processor, the memory having a computer program stored therein, the processor implementing the following steps when executing the computer program:

acquiring a target correlation coefficient of a target product under an acceleration test, and determining a target linear conversion function to which the target correlation coefficient belongs; the target correlation coefficient represents a linear relationship between the performance degradation of the target product and time. And establishing a nonlinear wiener process of the target product based on the target linear conversion function. According to the solving result of the parameters in the nonlinear wiener process, a first unreliability function of the target product when the multi-element performance degradation fails is obtained, and a second unreliability function of the target product when the target product suddenly fails is obtained. And constructing a coupling competition failure model based on the coupling competition relationship between the multi-element performance degradation failure and the burst failure, the first unreliability function and the second unreliability function, and determining a target reliability function of the target product according to the coupling competition failure model. And obtaining a reliability evaluation result of the target product under the accelerated test according to the target reliability function.

In one embodiment, the processor, when executing the computer program, further performs the steps of:

and acquiring performance degradation data and a plurality of linear conversion functions of a plurality of target products under an accelerated test. And substituting the performance degradation data of a plurality of target products into a function formed by the linear conversion functions aiming at each linear conversion function to obtain a correlation coefficient corresponding to the linear conversion function. Based on the value of each correlation coefficient, a target correlation coefficient satisfying a target condition among the correlation coefficients is determined. And determining a target linear conversion function for establishing a nonlinear wiener process according to the target correlation coefficient.

and determining a maximum likelihood function corresponding to the function item of the target correlation coefficient based on the numerical value of the target correlation coefficient. And solving the maximum likelihood function corresponding to the function item of the target correlation coefficient to obtain the value of each parameter in the target linear conversion function to which the target correlation coefficient belongs. And determining a target linear conversion function for establishing the nonlinear wiener process according to the value of each parameter.

In one embodiment, the processor when executing the computer program further performs the steps of:

and constructing a probability density function of the target product when the multi-element performance is degraded and failed. And determining a maximum likelihood function of the nonlinear wiener process of the target product based on the probability density function. And solving the maximum likelihood function of the target product in the nonlinear wiener process to obtain a solving result of each parameter in the nonlinear wiener process.

and obtaining a solving result of each parameter in the nonlinear wiener process, and constructing an unreliable subfunction corresponding to each performance of the target product. And substituting the solution result into the unreliable subfunction corresponding to each performance to obtain a first unreliable function of the target product when the multiple performances are degraded and failed. And establishing a sudden unreliability function of the target product when the target product is suddenly failed, and acquiring the time of the sudden failure of the target product. And performing parameter solving processing on parameters in the maximum likelihood function corresponding to the sudden unreliability function based on the sudden unreliability function and the time of sudden failure to obtain a second unreliability function of the target product when sudden failure occurs.

and establishing a maximum likelihood function corresponding to the coupling competition failure model to calculate parameter values in the coupling competition failure model and obtain a parameter solving result. And substituting the parameter solving result into the coupling competition failure model to obtain a target reliability function.

and performing integral processing on the function item of the target reliability function to obtain the first average fault interval time of the target product under the acceleration test. And multiplying the first average fault interval time by the acceleration factor of the target product to obtain a second average fault interval time of the target product under a normal test. And obtaining a reliability evaluation result of the target product according to the first average fault interval time and the second average fault interval time.

In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored which, when executed by a processor, performs the steps of:

acquiring a target correlation coefficient of a target product under an acceleration test, and determining a target linear conversion function to which the target correlation coefficient belongs; the target correlation coefficient represents a linear relationship between the performance degradation of the target product and time. And establishing a nonlinear wiener process of the target product based on the target linear conversion function. According to the solving result of the parameters in the nonlinear wiener process, a first unreliability function of the target product when the multi-element performance degradation fails is obtained, and a second unreliability function of the target product when the target product suddenly fails is obtained. And constructing a coupling competition failure model based on the coupling competition relationship between the multi-element performance degradation failure and the burst failure, the first unreliability function and the second unreliability function, and determining a target reliability function of the target product according to the coupling competition failure model. And obtaining a reliability evaluation result of the target product under the acceleration test according to the target reliability function.

In one embodiment, the computer program when executed by the processor further performs the steps of:

and constructing a probability density function of the target product when the multi-element performance is degraded and failed. And determining a maximum likelihood function of the nonlinear wiener process of the target product based on the probability density function. And solving the maximum likelihood function of the target product in the nonlinear wiener process to obtain the solving result of each parameter in the nonlinear wiener process.

and obtaining a solving result of each parameter in the nonlinear wiener process, and constructing an unreliable subfunction corresponding to each performance of the target product. And substituting the solution result into the unreliability subfunction corresponding to each performance to obtain a first unreliability function of the target product when the multi-performance degradation fails. And establishing a sudden unreliability function of the target product when the target product is suddenly failed, and acquiring the time of the sudden failure of the target product. And performing parameter solving processing on parameters in the maximum likelihood function corresponding to the burst unreliability function based on the burst unreliability function and the time of the burst failure to obtain a second unreliability function of the target product during the burst failure.

and performing integral processing on the function item of the target reliability function to obtain the first average fault interval time of the target product under the acceleration test. And performing product processing on the first average fault interval time and the acceleration factor of the target product to obtain a second average fault interval time of the target product under a normal test. And obtaining a reliability evaluation result of the target product according to the first average fault interval time and the second average fault interval time.

In one embodiment, a computer program product is provided, comprising a computer program which when executed by a processor performs the steps of:

acquiring a target correlation coefficient of a target product under an acceleration test, and determining a target linear conversion function to which the target correlation coefficient belongs; the target correlation coefficient represents a linear relationship between the performance degradation of the target product and time. And establishing a nonlinear wiener process of the target product based on the target linear conversion function. According to the solving result of the parameters in the nonlinear wiener process, a first unreliability function of the target product when the multi-element performance is degraded and failed is obtained, and a second unreliability function of the target product when the target product is suddenly failed is obtained. And determining a target reliability function of the target product based on the coupling competition relationship between the multi-element performance degradation failure and the burst failure, the first unreliability function and the second unreliability function. And obtaining a reliability evaluation result of the target product under the acceleration test according to the target reliability function.

and obtaining a solving result of each parameter in the nonlinear wiener process, and constructing an unreliable subfunction corresponding to each performance of the target product. And substituting the solution result into the unreliable subfunction corresponding to each performance to obtain a first unreliable function of the target product when the multiple performances are degraded and failed. And establishing a sudden unreliability function of the target product when the target product is suddenly failed, and acquiring the time of the sudden failure of the target product. And performing parameter solving processing on parameters in the maximum likelihood function corresponding to the burst unreliability function based on the burst unreliability function and the time of the burst failure to obtain a second unreliability function of the target product during the burst failure.

and establishing a maximum likelihood function corresponding to the coupling competition failure model to calculate parameter values in the coupling competition failure model and obtain a parameter solving result. Substituting the parameter solving result into the coupling competition failure model to obtain a target reliability function.

It should be noted that, the user information (including but not limited to user equipment information, user personal information, etc.) and data (including but not limited to data for analysis, stored data, displayed data, etc.) referred to in the present application are information and data authorized by the user or sufficiently authorized by each party, and the collection, use and processing of the related data need to comply with the relevant laws and regulations and standards of the relevant country and region.

It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by hardware instructions of a computer program, which can be stored in a non-volatile computer-readable storage medium, and when executed, can include the processes of the embodiments of the methods described above. Any reference to memory, database, or other medium used in the embodiments provided herein may include at least one of non-volatile and volatile memory. The nonvolatile Memory may include Read-only Memory (ROM), magnetic tape, floppy disk, flash Memory, optical Memory, high-density embedded nonvolatile Memory, resistive Random Access Memory (ReRAM), magnetic Random Access Memory (MRAM), ferroelectric Random Access Memory (FRAM), phase Change Memory (PCM), graphene Memory, and the like. Volatile Memory can include Random Access Memory (RAM), external cache Memory, and the like. 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), among others. The databases involved in the embodiments provided herein may include at least one of relational and non-relational databases. The non-relational database may include, but is not limited to, a block chain based distributed database, and the like. The processors referred to in the various embodiments provided herein may be, without limitation, general purpose processors, central processing units, graphics processors, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, or the like.

All possible combinations of the technical features in the above embodiments may not be described for the sake of brevity, but should be considered as being within the scope of the present disclosure as long as there is no contradiction between the combinations of the technical features.

The above-mentioned embodiments only express several embodiments of the present application, and the description thereof is more specific and detailed, but not construed as limiting the scope of the present application. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the concept of the present application, which falls within the scope of protection of the present application. Therefore, the protection scope of the present application should be subject to the appended claims.

Claims

1. A reliability evaluation method based on a coupling competition failure model is characterized by comprising the following steps:

2. The method according to claim 1, wherein the obtaining a target correlation coefficient of a target product under an acceleration test and determining a target linear transfer function to which the target correlation coefficient belongs comprises:

3. The method according to claim 2, wherein determining a target linear transfer function for establishing a non-linear wiener process according to the target correlation coefficient comprises:

4. The method of claim 1, wherein the establishing the non-linear wiener process of the target product based on the target linear transfer function comprises:

5. The method according to claim 1, wherein the obtaining a first unreliability function of the target product when the multivariate performance degradation fails and obtaining a second unreliability function of the target product when the target product suddenly fails according to the solution result of the parameters in the nonlinear wiener process comprises:

substituting the solving result into the unreliable subfunction corresponding to each performance to obtain a first unreliable function of the target product when the multi-performance degradation fails;

establishing a sudden unreliability function of the target product when the target product is suddenly failed, and acquiring the time of the sudden failure of the target product;

6. The method of claim 1, wherein determining the target reliability function for the target product based on the coupling race failure model comprises:

and substituting the parameter solving result into the coupling competition failure model to obtain a target reliability function.

7. The method according to claim 1, wherein obtaining the reliability evaluation result of the target product under the accelerated test according to the target reliability function comprises:

performing integral processing on a function term of the target reliability function to obtain a first average fault interval time of the target product under the acceleration test;

8. A reliability evaluation apparatus based on a coupling competition failure model, the apparatus comprising:

the nonlinear wiener process construction module is used for establishing a nonlinear wiener process of the target product based on the target linear conversion function;

9. A computer device comprising a memory and a processor, the memory storing a computer program, characterized in that the processor, when executing the computer program, implements the steps of the method of any of claims 1 to 7.

10. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the method of any one of claims 1 to 7.