CN115563887A - Ammunition reliability evaluation method and system based on multi-source information fusion - Google Patents
Ammunition reliability evaluation method and system based on multi-source information fusion Download PDFInfo
- Publication number
- CN115563887A CN115563887A CN202211533769.0A CN202211533769A CN115563887A CN 115563887 A CN115563887 A CN 115563887A CN 202211533769 A CN202211533769 A CN 202211533769A CN 115563887 A CN115563887 A CN 115563887A
- Authority
- CN
- China
- Prior art keywords
- reliability
- data
- information fusion
- density function
- ammunition
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 230000004927 fusion Effects 0.000 title claims abstract description 70
- 238000011156 evaluation Methods 0.000 title claims abstract description 36
- 238000002474 experimental method Methods 0.000 claims abstract description 92
- 238000009826 distribution Methods 0.000 claims abstract description 76
- 238000012360 testing method Methods 0.000 claims abstract description 68
- 238000007781 pre-processing Methods 0.000 claims abstract description 6
- 238000000034 method Methods 0.000 claims description 45
- 238000004458 analytical method Methods 0.000 claims description 13
- 238000012937 correction Methods 0.000 claims description 9
- 238000004364 calculation method Methods 0.000 claims description 6
- 238000007500 overflow downdraw method Methods 0.000 claims description 6
- 238000012545 processing Methods 0.000 claims description 5
- 238000006243 chemical reaction Methods 0.000 claims description 4
- 238000010276 construction Methods 0.000 claims description 3
- 238000005315 distribution function Methods 0.000 claims description 3
- 238000013507 mapping Methods 0.000 claims description 3
- 238000004806 packaging method and process Methods 0.000 claims description 3
- 230000006870 function Effects 0.000 description 30
- 230000008569 process Effects 0.000 description 7
- 238000011161 development Methods 0.000 description 6
- 238000011160 research Methods 0.000 description 6
- 230000008901 benefit Effects 0.000 description 4
- 230000006872 improvement Effects 0.000 description 3
- 230000008859 change Effects 0.000 description 2
- 238000007405 data analysis Methods 0.000 description 2
- 238000013461 design Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000003993 interaction Effects 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 238000012356 Product development Methods 0.000 description 1
- 238000003889 chemical engineering Methods 0.000 description 1
- 238000007418 data mining Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000012938 design process Methods 0.000 description 1
- 239000003814 drug Substances 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 238000007499 fusion processing Methods 0.000 description 1
- 238000013095 identification testing Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000011056 performance test Methods 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 238000004445 quantitative analysis Methods 0.000 description 1
- 238000012827 research and development Methods 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2111/00—Details relating to CAD techniques
- G06F2111/08—Probabilistic or stochastic CAD
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2119/00—Details relating to the type or aim of the analysis or the optimisation
- G06F2119/02—Reliability analysis or reliability optimisation; Failure analysis, e.g. worst case scenario performance, failure mode and effects analysis [FMEA]
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Evolutionary Computation (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Artificial Intelligence (AREA)
- Computer Hardware Design (AREA)
- Geometry (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention provides an ammunition reliability evaluation method and system based on multi-source information fusion, aiming at target ammunition, reliability probability data is obtained by analyzing historical experimental data; performing a whole-system reliability growth experiment to obtain reliability growth experiment data of success and failure conditions of each test stage; testing the subsystems to obtain components under the condition of success and failure of each component and subsystem experimental data; determining a prior distribution density function; preprocessing reliability probability data, reliability increase experiment data and subsystem experiment data, and performing homologous information fusion; calculating a hyper-parameter of a prior distribution density function; a hyperparameter unified data input format based on a prior distribution density function; calculating an inheritance factor based on a hyper-parameter of a prior distribution density function; and (3) based on the hyperparameter and the inheritance factor of the prior distribution density function, carrying out multisource information fusion by adopting Bayesian theorem Bayes to obtain the reliability of the target ammunition.
Description
Technical Field
The invention relates to the technical field of reliability multi-source information fusion, in particular to an ammunition reliability assessment method and system based on multi-source information fusion.
Background
Reliability is the most fundamental quality characteristic of equipment "good use, service". The reliability analysis and evaluation platform has important significance for researching product reliability, particularly high-precision product reliability with high cost and low yield, and has good application prospect, so that the reliability analysis and evaluation platform is widely valued by various countries. At present, many foreign scientific research institutions have harvested a great amount of scientific research achievements on tools and platform researches for reliability analysis. They use the reliability demonstration platform of research design for product reliability research, product life prediction, etc. The start is relatively late in China, but the investment of manpower and material resources is gradually increased, and part of the reliability analysis and evaluation tool platform is already put into use.
In the prior art, weber distribution is a tool for analyzing the reliability and service life data of thousands of companies all over the world, and can realize a series of standard data analysis, drawing and automatic reporting aiming at all service lives and reliability data types and evaluate the service life and reliability of products; the system reliability platform Block Sim uses two analysis methods, namely a reliability block diagram and a fault tree, to model a system and a process, so that reliability evaluation on corresponding repairable and non-repairable systems is realized; JMP is a comprehensive data analysis software platform, integrates all reliability analysis functions in the aspect of reliability, is widely applied to the fields of data mining, reliability analysis and the like by helping users to find the value behind data, and benefits various industries such as electronics, medicine, chemical engineering and the like.
However, the two software do not relate to a method for using reliable multi-source data, the necessity of multi-source information in the existing reliability evaluation is omitted, and a multi-source information fusion method is used for fusing different multi-source data such as reliability probability data, reliability growth information, component and subsystem information, similar product information, field test information and the like, so that the difficulty of how different types of information are converted into the same distribution type data exists in the process.
Disclosure of Invention
The invention provides an ammunition reliability evaluation method and system based on multi-source information fusion.
In order to solve the technical problem, the invention provides an ammunition reliability evaluation method based on multi-source information fusion, which comprises the following steps:
step S1: analyzing historical experimental data for target ammunition, quantizing character type influence factors, and mapping to a probability interval to obtain reliability probability data; performing a whole-system reliability growth experiment to obtain reliability growth experiment data of success and failure conditions of each test stage; testing the subsystems to obtain components under the condition of success and failure of the components and subsystem experimental data;
step S2: determining a prior distribution density function; preprocessing the reliability probability data, the reliability growth experiment data and the subsystem experiment data, and calculating the hyperparameter of the prior distribution density function; a super-parameter unified data input format based on the prior distribution density function and homologous information fusion are carried out;
and step S3: calculating an inheritance factor based on a hyper-parameter of the prior distribution density function;
and step S4: and based on the hyperparameter and the inheritance factor of the prior distribution density function, carrying out multisource information fusion by adopting Bayesian theorem Bayes to obtain the reliability of the target ammunition.
Preferably, the expression of the prior distribution density function is:
in the formula, a i ，b i Is a hyperparameter of the prior distribution density function,
indicating factorization, and R indicating the reliability of the prior information.
Preferably, in step S2, the reliability probability data is preprocessed, and the method for calculating the hyperparameter of the prior distribution density function includes: processing the reliability probability data by adopting an uncertain information fusion method D-S evidence theory to obtain a reliability interval with a confidence level gamma of the reliability interval, wherein the reliability interval is [ R1, R2], and is expressed as follows:
the information entropy of the prior distribution density function is set as follows:
when the formula (2) is satisfied, the formula (1) takes the maximum value to obtain the hyper-parameter a of the prior distribution density function i And b i 。
Preferably, in step S2, the reliability increase experimental data is preprocessed, and the method for calculating the hyper-parameter of the prior distribution density function includes:
1) Calculating the reliability R of the system in the i stage of the reliability increase experiment i Pre-test mean of (a):
2) According to the construction method of the maximum entropy pre-test distribution, R is calculated by the following formula i Pre-test distribution of (c):
in the formula, mu is a undetermined coefficient;
3) Obtained by equation (3) and equation (4):
4) Calculation of R i Second order moment E (R) i 2 ）：
5) With a conjugate Beta distribution (a) i ，b i ) Fitting R i Pre-test distribution of (c):
from the above formula one can obtain:
preferably, in step S2, the subsystem experimental data is preprocessed, and the method for calculating the hyperparameter of the prior distribution density function includes: performing conversion processing on the subsystem experiment data to obtain equivalent experiment information (n, s, f), wherein n represents the total number of experiments, s represents the success number of the experiments, f represents the failure number of the experiments, and a is taken i = s and b i =f。
Preferably, the method for calculating the inheritance factor in step S3 is as follows:
step S31: the correction amount K is calculated by the following formula i ：
Wherein x represents the total number of experiments in the ith reliability experiment information, y represents the number of successful experiments in the ith reliability experiment information, z represents the number of failed experiments in the ith reliability experiment information, n represents the total number of experiments in the system field experiment information, s represents the number of successful experiments in the system field experiment information, and f represents the number of failed experiments in the system field experiment information;
step S32: based on the correction amount K i Removing data of which the ith kind of reliability information and the system field test information belong to different populations;
step S33: based on the correction amount K i Checking a chi-square distribution table to obtain goodness of fit;
step S34: based on the goodness-of-fit, an inheritance factor is calculated by the formula:
in the formula, the Q function represents the goodness of fit.
Preferably, the method of calculating the reliability of the target ammunition in step S4 is: the posterior distribution was calculated by bayes' theorem:
wherein R represents reliability, beta represents beta distribution, D represents field test condition, pi probability distribution function, and rho i Representing an inheritance factor; then, based on the confidence γ, the reliability R is calculated by the following formula L ：
The invention also provides an ammunition reliability evaluation system based on multi-source information fusion, which comprises a data acquisition module, a homologous information fusion module, a multi-source information fusion module and a reliability evaluation module;
the data acquisition module is used for acquiring reliability probability data, reliability increase experiment data and part and subsystem experiment data of target ammunition;
the homologous information fusion module is used for carrying out homologous information fusion on the reliability probability data, the reliability increase experiment data and the part and subsystem experiment data and outputting the fused data to the multisource information fusion module;
the multi-source information fusion module is used for carrying out multi-source information fusion through Bayesian theorem to obtain a lower confidence limit of the target ammunition and outputting the lower confidence limit to the reliability evaluation module;
and the reliability evaluation module is used for calculating the reliability of the target ammunition based on the reliability information lower limit.
Further, the homologous information fusion module determines a prior distribution density function; preprocessing the reliability probability data, the reliability growth experiment data and the subsystem experiment data, and calculating the hyperparameter of the prior distribution density function; and (4) carrying out a super-parameter unified data input format based on the prior distribution density function, and carrying out homologous information fusion.
Still further, the system further comprises a method execution module, wherein the method execution module is used for packaging the Matlab function into a java package so as to execute the data acquisition module, the homologous information fusion module, the pre-test information analysis module, the multi-source information fusion module and the reliability evaluation module.
Drawings
FIG. 1 is a flow chart of the method of the present invention;
FIG. 2 is a block diagram of the present invention.
Detailed Description
The invention is described in further detail below with reference to the figures and specific embodiments.
The flow chart of the method of the invention is shown in figure 1, and comprises the following steps:
step S1: analyzing historical experimental data for target ammunition, quantizing character type influence factors, and mapping the character type influence factors to a probability interval to obtain reliability probability data; performing a whole-system reliability growth experiment to obtain reliability growth experiment data of success and failure conditions of each test stage; and testing the subsystem to obtain the parts and subsystem experimental data under the condition of success and failure of each part.
Ammunition is used as a disposable consumption product, the reliability index requirement is high, and reliability information can be divided into subjective information and objective information according to different properties. The subjective information comprises reliability probability data, the reliability probability data is usually deduced by personnel participating in product research and development, production, manufacture and experiments based on historical experimental data according to professional knowledge, and the reliability probability data plays a certain role in reliability evaluation of products for reliability evaluation of newly researched and developed ammunition.
The objective information comprises reliability growth test information and component and subsystem information of each stage of product development, and the reliability growth test information is as follows: the equipment development is subjected to the process of testing, exposing, analyzing, improving and retesting TAAF, the reliability is gradually increased along with the improvement of the design, the test information is used for carrying out quantitative analysis and management on the reliability increase of the product, and the test information comprises reliability improvement test data, reliability verification, reliability screening test data and the like. The reliability increase test information is system-level test information with a high application value, and the defect of small system experiment number in small subsample reliability evaluation is overcome to a certain extent, so that the acquisition and fusion of the information have an important role.
The device comprises a plurality of components and subsystems, a large amount of component and subsystem test data are accumulated in the development process, and the problem of insufficient test times in small subsample reliability evaluation can be solved to a certain extent by collecting and utilizing the test information.
Step S2: determining a prior distribution density function; preprocessing the reliability probability data, the reliability growth experiment data and the subsystem experiment data, and calculating the hyperparameter of the prior distribution density function; and (4) carrying out a super-parameter unified data input format based on the prior distribution density function, and carrying out homologous information fusion.
Specifically, the reliability probability data are processed and fused by different methods according to different description methods, the reliability probability data fusion algorithm is generally divided into behavior fusion and mathematical fusion, and the behavior fusion is mainly performed by methods such as conferences and information interaction; the mathematical fusion is mainly to fuse probability distribution converted by quantizing character type influence factors of various historical experimental data, and the uncertain information fusion method has the capability of directly expressing uncertainty and ignorance by adopting an uncertain information fusion method D-S evidence theory in consideration of two characteristics of subjectivity and uncertainty in selection and analysis of the historical experimental data. The D-S evidence theory is used as an uncertain reasoning method, the evidence refers to a part of expert experience and knowledge, and used data has intuition and easy acquirement, so that the D-S evidence theory is an ideal fusion method and solves the influence caused by uncertainty and subjectivity; aiming at the reliability growth test information, an American army equipment system analysis center AMSAA model is adopted, and the AMSSA model realizes the description of the reliability change trend through growth trend test, growth parameter estimation and fitting goodness test according to the multi-stage reliability growth test information in the reliability analysis, so that the staged reliability evaluation is realized; aiming at the test information of the components and the subsystems, an information entropy method of information folding degree is adopted, the basic idea of the fusion of the test information of the components and the subsystems is to fold the information, namely the test information (ni, si) of each subsystem is folded into the test information (n, s) of the system, wherein the n and the s are the total number of virtual experiments and the success number of the experiments, and the folding of the information amount in the information fusion plays a vital role in the evaluation of reliability and is also a difficult point in the fusion process of the test information of the components and the subsystems. After the credible equivalent virtual system experiment information is obtained, the lower confidence limit of the system can be solved according to the given confidence by using a classical reliability solving method.
For the reliability growth experimental data, it is not practical to require each stage to evaluate the reliability of the product through an identification test because the ammunition product has the characteristics of high reliability requirement, small batch, expensive development cost and the like. Performance tests, environmental tests or comprehensive tests are usually performed at various stages in the development process. Therefore, to economically and efficiently promote a product to achieve a predetermined reliability goal, it is necessary to combine reliability tests with non-reliability tests by using the resources and information of each test in the development process as much as possible. According to the multi-stage reliability growth test information, the reliability change trend is described through growth trend test, growth parameter estimation and goodness-of-fit test, so that the staged reliability evaluation is realized.
Aiming at experimental data of components and subsystems, an information entropy method of information folding degree is adopted, and the basic idea of test information fusion of the components and the subsystems is to convert information, namely experimental information (n) of each subsystem i ，s i ) The data are converted into experimental information (n, s) of the system, wherein n and s are virtual total experimental number and successful experimental number, and the conversion of information quantity in information fusion plays a crucial role in reliability evaluation and is also a difficult point in the process of fusing experimental data of components and subsystems. After the credible equivalent virtual system experiment information is obtained, the lower confidence limit of the system can be solved according to the given confidence by using a classical reliability solving method. The method fully utilizes the given information in the sample, adds the least information amount to the random and fuzzy parts, and can determine the probability density distribution and the related parameters most accurately. This allows the structure response to have greater randomness and ambiguity in the calculation, so the reliability calculation problem under the complex load has higher application value.
The specific process steps are as follows:
1. determining a prior distribution
In reliability engineering applications, a Beta distribution is used as a prior distribution, and the density function is as follows:
in the formula a i ，b i For each pre-test distribution of hyper-parameters, determined from corresponding multi-source reliability information, i.e. hyper-parameter a i ，b i As a result of considering the information of the pre-test trial,
indicating factorization, and R indicating the reliability of the prior information.
Reliability probability data, reliability growth experimental data, and hyper-parameter a of three types of reliability data of component and subsystem experimental data i ，b i The solving method of (2) is as follows:
(1) Hyper-parameter a of reliability probability data i ，b i Solving:
reliability probability data is shown in Table 1, m 1 And m 2 Two different target charges are represented and,
TABLE 1
After the reliability probability data is fused by a D-S evidence theory, the reliability interval of the confidence level gamma is [ R1, R2], which is expressed as:
the information entropy of the prior distribution density function is set as follows:
converting reliability probability data into hyperparameter a in prior distribution i ，b i The basic idea is to use the maximum entropy principle as a constraint condition, namely to solve the parameter value (a) which enables the equation (1) to be maximum under the condition of satisfying the constraint condition equation (2) i ，b i ) For this problem, table 2 shows a reference table of the reliability probability data corresponding to the parameter estimation values:
(2) Hyper-parameter a of component and subsystem experimental data i ，b i Solving:
the part and subsystem experimental data are shown in Table 3
Specifically, the component and subsystem reliability information are fused in a homologous mode, on the basis that the converted system equivalent experiment information (n, s, f) is obtained by adopting a conversion processing method in the embodiment of the invention, n represents the total number of experiments, s represents the success number of the experiments, f represents the failure number of the experiments, and a can be directly taken i = s and b i =f。
(3) Hyperparameter a of reliability growth experimental data i ，b i Solving:
the reliability growth experimental data are shown in tables 4 and 5:
reliability increase experiment i stage system reliability R i The pre-test mean values of (a) are:
R i the pre-test distribution can be obtained according to a construction method of the maximum entropy pre-test distribution:
wherein mu is a undetermined coefficient and is obtained by the formula:
R i second order moment E (R) i 2 ) Comprises the following steps:
with a conjugate Beta distribution (a) i ，b i ) Fitting R i The two pre-test distributions have equal first and second moments, namely:
from the above formula, one can obtain:
and step S3: calculating an inheritance factor based on a hyper-parameter of a prior distribution density function;
step S31: the correction amount K is calculated by the following formula i ：
In obtaining the hyper-parameter a i ，b i Further, the system site test information is acquired, and if the reliability information and the system site test information are assumed to be from the same population, x = a may be directly acquired i ，y=b i 。
In the formula, x represents the total number of experiments in the ith reliability experiment information, y represents the number of success of the experiments in the ith reliability experiment information, z represents the number of failure of the experiments in the ith reliability experiment information, n represents the total number of the experiments in the system field experiment information, s represents the number of success of the experiments in the system field experiment information, and f represents the number of failure of the experiments in the system field experiment information;
step S32: based on the correction quantity K i Removing data of which the ith kind of reliability information and the system field test information belong to different populations;
specifically, based on a given test level α, the α quantile with a degree of freedom of 1 is found out by the chi-square distribution table
If, if
The data indicates that the ith reliability information and the system field test information belong to different populations.
Step S33: based on the correction quantity K i Looking up a chi-square distribution table to obtain the goodness of fit;
using goodness of fit Q (K) i ) Representing the similarity degree of the ith reliability information and the system field test information, wherein the greater the goodness of fit is, the greater the similarity degree of the two samples is, and the goodness of fit Q (K) i ) The method can be obtained by looking up a chi-square distribution table according to the following formula:
step S34: based on goodness of fit, the factors are inherited by the following formula:
in the formula, the Q function represents goodness of fit.
And step S4: and (3) based on the hyperparameter and the inheritance factor of the prior distribution density function, carrying out multisource information fusion by adopting Bayesian theorem Bayes to obtain the reliability of the target ammunition.
In particular, the inheritance factor ρ is utilized i And combining with field test information (n, s, f) and Bayesian theorem to deduce posterior distribution as follows:
wherein R represents reliability, β represents beta distribution, D represents field test condition, pi probability distribution function, and p i Representing an inheritance factor; under the condition of given confidence coefficient gamma, the lower limit R of the confidence coefficient of the product after fusing multi-source information can be solved according to the following formula L Namely, the device reliability:
as shown in fig. 2, the invention further provides an ammunition reliability evaluation system based on multi-source information fusion, which comprises a data acquisition module, a homologous information fusion module, a multi-source information fusion module, a reliability evaluation module and a method execution module.
The data acquisition module is used for acquiring reliability probability data, reliability increase experiment data and part and subsystem experiment data of the target ammunition;
the homologous information fusion module is used for carrying out homologous information fusion on the reliability probability data, the reliability increase experiment data and the part and subsystem experiment data and outputting the fused data to the homologous information fusion module;
the multi-source information fusion module is used for carrying out multi-source information fusion through Bayesian theorem to obtain a lower limit of confidence of the target ammunition and outputting the lower limit to the reliability evaluation module;
and the reliability evaluation module is used for calculating the reliability of the target ammunition based on the lower confidence limit of the reliability signal.
The method execution module is used for packaging Matlab functions into java packages so as to execute the data acquisition module, the homologous information fusion module, the pre-test information analysis module, the multi-source information fusion module and the reliability evaluation module.
The homologous information fusion module determines a prior distribution density function; preprocessing reliability probability data, reliability increase experiment data and subsystem experiment data, and calculating a hyper-parameter of a prior distribution density function; and (3) carrying out super-parameter unified data input format based on the prior distribution density function, and carrying out homologous information fusion.
The research results of reliability analysis and evaluation are found as follows: the related knowledge points have strong theoretical performance and the traditional classroom learning difficulty is large; the reliability calculation formula is complex, a large number of iterative approximation algorithms are used, the executed operation is high, the universality of the traditional execution method is insufficient, and the achievement benefit is difficult to exert.
The Java language, as a simple dynamic programming language, is characterized by being object-oriented, and implementing specific program operations by initializing objects with different attributes. Based on the characteristic, the Java language is widely applied to software platform development and is the programming language which is the widest in use range in the world at present, but the efficiency of analyzing and processing data by using the Java language is very low; matlab as commercial mathematical software produced by MathWorks company has outstanding advantages in the fields of matrix calculation, data analysis and the like, and has strong human-computer interaction and relatively simple operation. In the integrated design process of the software platform, different works are realized by the programming language with advantages in corresponding aspects, the difficulty of software design can be greatly reduced, and the use performance of the software platform is improved.
It will be understood by those skilled in the art that the foregoing is only a preferred embodiment of the present invention, and is not intended to limit the invention, and that any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the scope of the present invention.
Claims (10)
1. An ammunition reliability assessment method based on multi-source information fusion is characterized in that: the method comprises the following steps:
step S1: analyzing historical experimental data for target ammunition, quantizing character type influence factors, and mapping the character type influence factors to a probability interval to obtain reliability probability data; performing a whole-system reliability growth experiment to obtain reliability growth experiment data of success and failure conditions of each test stage; testing the subsystems to obtain components under the condition of success and failure of the components and subsystem experimental data;
step S2: determining a prior distribution density function; preprocessing the reliability probability data, the reliability growth experiment data and the subsystem experiment data, and calculating the hyperparameter of the prior distribution density function; a super-parameter unified data input format based on the prior distribution density function and homologous information fusion are carried out;
and step S3: calculating an inheritance factor based on a hyper-parameter of the prior distribution density function;
and step S4: and based on the hyperparameter and the inheritance factor of the prior distribution density function, carrying out multisource information fusion by adopting Bayesian theorem Bayes to obtain the reliability of the target ammunition.
2. An ammunition reliability assessment method based on multi-source information fusion according to claim 1, characterized in that: the expression of the prior distribution density function is:
in the formula, a i ，b i Is a hyperparameter of the prior distribution density function,
indicating factorization and R indicating the reliability of the prior information.
3. An ammunition reliability assessment method based on multi-source information fusion according to claim 2, characterized in that: in step S2, the reliability probability data is preprocessed, and the method for calculating the hyperparameter of the prior distribution density function includes: processing the reliability probability data by adopting an uncertain information fusion method D-S evidence theory to obtain a reliability interval with a confidence level gamma of the reliability interval as [ R [ [ R ] 1 ，R 2 ]Watch, watchShown as follows:
the information entropy of the prior distribution density function is set as:
under the condition of satisfying the formula (2), the formula (1) takes the maximum value to obtain the hyperparameter a of the prior distribution density function i And b i 。
4. The ammunition reliability evaluation method based on multi-source information fusion according to claim 2, characterized in that: in step S2, the reliability increase experimental data is preprocessed, and the method for calculating the hyperparameter of the prior distribution density function includes:
1) Calculating the reliability R of the system in the i stage of the reliability increase experiment i Pre-test mean of (a):
2) According to the construction method of the maximum entropy pre-test distribution, R is calculated by the following formula i Pre-test distribution of (c):
in the formula, mu is a undetermined coefficient;
3) Obtained by equation (3) and equation (4):
4) Calculation of R i Second order moment E (R) i 2 ）：
5) With a conjugate Beta distribution (a) i ，b i ) Fitting R i Pre-test distribution of (c):
from the above formula, one can obtain:
5. an ammunition reliability assessment method based on multi-source information fusion according to claim 2, characterized in that: in step S2, the subsystem experimental data is preprocessed, and the method for calculating the hyperparameter of the prior distribution density function includes: performing conversion processing on the subsystem experiment data to obtain equivalent experiment information (n, s, f), wherein n represents the total number of experiments, s represents the success number of the experiments, f represents the failure number of the experiments, and a is taken i = s and b i =f。
6. The ammunition reliability evaluation method based on multi-source information fusion according to claim 1, characterized in that: the method for calculating the inheritance factor in the step S3 comprises the following steps:
step S31: the correction amount K is calculated by the following formula i ：
In the formula, x represents the total number of experiments in the ith reliability experiment information, y represents the number of success of the experiments in the ith reliability experiment information, z represents the number of failure of the experiments in the ith reliability experiment information, n represents the total number of the experiments in the system field experiment information, s represents the number of success of the experiments in the system field experiment information, and f represents the number of failure of the experiments in the system field experiment information;
step S32: based on the correction amount K i Removing data of which the ith kind of reliability information and the system field test information belong to different populations;
step S33: based on the correction amount K i Checking a chi-square distribution table to obtain goodness of fit;
step S34: based on the goodness-of-fit, an inheritance factor is calculated by the formula:
in the formula, the Q function represents the goodness of fit.
7. An ammunition reliability assessment method based on multi-source information fusion according to claim 6, characterized in that: the method for calculating the reliability of the target ammunition in the step S4 comprises the following steps: the posterior distribution is calculated by bayes theorem:
wherein R represents reliability, beta represents beta distribution, D represents field test condition, pi represents probability distribution function, rho i Representing an inheritance factor; then, based on the confidence γ, the reliability R is calculated by the following formula L：
8. The utility model provides an ammunition reliability evaluation system based on multisource information fusion which characterized in that: the system comprises a data acquisition module, a homologous information fusion module, a multi-source information fusion module and a reliability evaluation module;
the data acquisition module is used for acquiring reliability probability data, reliability increase experiment data and part and subsystem experiment data of target ammunition;
the homologous information fusion module is used for carrying out homologous information fusion on the reliability probability data, the reliability increase experiment data and the part and subsystem experiment data and outputting the fused data to the multisource information fusion module;
the multi-source information fusion module is used for carrying out multi-source information fusion through Bayesian theorem to obtain a lower limit of confidence of the target ammunition and outputting the lower limit to the reliability evaluation module;
and the reliability evaluation module is used for calculating the reliability of the target ammunition based on the reliability information lower limit.
9. An ammunition reliability assessment system based on multi-source information fusion according to claim 8, characterized in that: the homologous information fusion module determines a prior distribution density function, preprocesses the reliability probability data, the reliability increase experiment data and the subsystem experiment data, and calculates the hyperparameter of the prior distribution density function; and (4) carrying out a super-parameter unified data input format based on the prior distribution density function, and carrying out homologous information fusion.
10. An ammunition reliability assessment system based on multi-source information fusion according to claim 8, characterized in that: the system also comprises a method execution module which is used for packaging the Matlab function into a java package so as to execute the data acquisition module, the homologous information fusion module, the pre-test information analysis module, the multi-source information fusion module and the reliability evaluation module.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211533769.0A CN115563887A (en) | 2022-12-02 | 2022-12-02 | Ammunition reliability evaluation method and system based on multi-source information fusion |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211533769.0A CN115563887A (en) | 2022-12-02 | 2022-12-02 | Ammunition reliability evaluation method and system based on multi-source information fusion |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115563887A true CN115563887A (en) | 2023-01-03 |
Family
ID=84770284
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211533769.0A Pending CN115563887A (en) | 2022-12-02 | 2022-12-02 | Ammunition reliability evaluation method and system based on multi-source information fusion |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115563887A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117851266A (en) * | 2024-03-05 | 2024-04-09 | 中国人民解放军海军工程大学 | Safety key software reliability Bayesian verification method and device |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106777814A (en) * | 2017-01-18 | 2017-05-31 | 电子科技大学 | Method for predicting reliability with faulty physical is updated based on multi-source hierarchical information |
| CN107808169A (en) * | 2017-11-16 | 2018-03-16 | 中国航天标准化研究所 | A kind of space flight phased mission systems reliability estimation method and system |
| CN110414552A (en) * | 2019-06-14 | 2019-11-05 | 中国人民解放军海军工程大学 | A kind of spare part reliability Bayesian Assessment Method and system based on multi-source fusion |
| CN110874502A (en) * | 2019-11-11 | 2020-03-10 | 中国人民解放军国防科技大学 | Aerospace product reliability assessment method based on multi-stage test data reduction |
| CN111222736A (en) * | 2019-09-29 | 2020-06-02 | 中国人民解放军空军工程大学 | Ammunition storage reliability evaluation method based on mixed correlation vector machine model |
| CN112069732A (en) * | 2020-09-03 | 2020-12-11 | 中国人民解放军陆军工程大学 | Comprehensive evaluation method for artillery reliability identification test |
| CN112381456A (en) * | 2020-12-03 | 2021-02-19 | 中国人民解放军海军工程大学 | Equipment development phase testability evaluation and system based on conflict data fusion |
| CN112883497A (en) * | 2021-03-22 | 2021-06-01 | 中国人民解放军国防科技大学 | Aerospace valve reliability assessment method based on multi-source information fusion |
| CN114326475A (en) * | 2021-11-30 | 2022-04-12 | 安徽海博智能科技有限责任公司 | Unmanned area controller reliability optimization method based on competitive failure mode |
| CN114355094A (en) * | 2022-03-18 | 2022-04-15 | 中国电子产品可靠性与环境试验研究所（（工业和信息化部电子第五研究所）（中国赛宝实验室）） | Product reliability weak link comprehensive evaluation method and device based on multi-source information |
-
2022
- 2022-12-02 CN CN202211533769.0A patent/CN115563887A/en active Pending
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106777814A (en) * | 2017-01-18 | 2017-05-31 | 电子科技大学 | Method for predicting reliability with faulty physical is updated based on multi-source hierarchical information |
| CN107808169A (en) * | 2017-11-16 | 2018-03-16 | 中国航天标准化研究所 | A kind of space flight phased mission systems reliability estimation method and system |
| CN110414552A (en) * | 2019-06-14 | 2019-11-05 | 中国人民解放军海军工程大学 | A kind of spare part reliability Bayesian Assessment Method and system based on multi-source fusion |
| CN111222736A (en) * | 2019-09-29 | 2020-06-02 | 中国人民解放军空军工程大学 | Ammunition storage reliability evaluation method based on mixed correlation vector machine model |
| CN110874502A (en) * | 2019-11-11 | 2020-03-10 | 中国人民解放军国防科技大学 | Aerospace product reliability assessment method based on multi-stage test data reduction |
| CN112069732A (en) * | 2020-09-03 | 2020-12-11 | 中国人民解放军陆军工程大学 | Comprehensive evaluation method for artillery reliability identification test |
| CN112381456A (en) * | 2020-12-03 | 2021-02-19 | 中国人民解放军海军工程大学 | Equipment development phase testability evaluation and system based on conflict data fusion |
| CN112883497A (en) * | 2021-03-22 | 2021-06-01 | 中国人民解放军国防科技大学 | Aerospace valve reliability assessment method based on multi-source information fusion |
| CN114326475A (en) * | 2021-11-30 | 2022-04-12 | 安徽海博智能科技有限责任公司 | Unmanned area controller reliability optimization method based on competitive failure mode |
| CN114355094A (en) * | 2022-03-18 | 2022-04-15 | 中国电子产品可靠性与环境试验研究所（（工业和信息化部电子第五研究所）（中国赛宝实验室）） | Product reliability weak link comprehensive evaluation method and device based on multi-source information |
Non-Patent Citations (1)
| Title |
|---|
| 孔耀等: "基于信息融合的复杂系统可靠性综合评估", 《兵工自动化》 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117851266A (en) * | 2024-03-05 | 2024-04-09 | 中国人民解放军海军工程大学 | Safety key software reliability Bayesian verification method and device |
| CN117851266B (en) * | 2024-03-05 | 2024-05-28 | 中国人民解放军海军工程大学 | Safety key software reliability Bayesian verification method and device |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113792825B (en) | Fault classification model training method and device for electricity information acquisition equipment | |
| CN106779505B (en) | Power transmission line fault early warning method and system based on big data driving | |
| US5655074A (en) | Method and system for conducting statistical quality analysis of a complex system | |
| CN106780121B (en) | Power consumption abnormity identification method based on power consumption load mode analysis | |
| CN106201871A (en) | Based on the Software Defects Predict Methods that cost-sensitive is semi-supervised | |
| CN110222991B (en) | Metering device fault diagnosis method based on RF-GBDT | |
| CN106021771A (en) | Method and device for diagnosing faults | |
| EP2978095A1 (en) | Power system operation | |
| CN108664700A (en) | Acceleration degradation information Fusion Modeling Method based on uncertain data Envelope Analysis | |
| CN111738462A (en) | Fault first-aid repair active service early warning method for electric power metering device | |
| CN104008143A (en) | Vocational ability index system establishment method based on data mining | |
| Singh et al. | Software fault proneness prediction using support vector machines | |
| CN111967717A (en) | Data quality evaluation method based on information entropy | |
| CN115563887A (en) | Ammunition reliability evaluation method and system based on multi-source information fusion | |
| CN111950850B (en) | Evidence network-based unmanned aerial vehicle system guarantee capability evaluation method | |
| CN114036654A (en) | Random multi-parameter fatigue test spectrum compiling method based on damage equivalence | |
| Neela et al. | Modeling Software Defects as Anomalies: A Case Study on Promise Repository. | |
| CN110781959A (en) | Power customer clustering method based on BIRCH algorithm and random forest algorithm | |
| CN112926686B (en) | BRB and LSTM model-based power consumption anomaly detection method and device for big power data | |
| CN117371861B (en) | Digital-based household service quality intelligent analysis method and system | |
| CN111539492A (en) | Abnormal electricity utilization judgment system and method based on reinforcement learning | |
| Maharani et al. | The MFEP and MAUT methods in selecting the best employees | |
| CN105931133A (en) | Distribution transformer replacement priority evaluation method and device | |
| CN116307242A (en) | Construction method of larch site quality and productivity model | |
| CN115759263A (en) | Strategy effect evaluation method and device based on cause and effect inference |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20230103 |