CN110457776A - A kind of Test Strategy rapid generation based on failure decision networks - Google Patents
A kind of Test Strategy rapid generation based on failure decision networks Download PDFInfo
- Publication number
- CN110457776A CN110457776A CN201910661767.1A CN201910661767A CN110457776A CN 110457776 A CN110457776 A CN 110457776A CN 201910661767 A CN201910661767 A CN 201910661767A CN 110457776 A CN110457776 A CN 110457776A
- Authority
- CN
- China
- Prior art keywords
- measuring point
- failure
- test
- cost
- optimal
- 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.)
- Granted
Links
Abstract
The invention discloses a kind of Test Strategy rapid generations based on failure decision networks, by the failure dependence matrix and failure decision networks that construct test system to be measured, optimal measuring point is generated by heuristic search algorithm, and then optimal Test Strategy is obtained, to isolate the failure in network by optimum search path；The influence for combining Dependency Specification to generate optimal policy in this way, accurately estimate heuristic function value, reduce the deviation of heuristic function estimation and search strategy decision in the application, simultaneously, pass through the setting of opportunity cost, to search for the setting optimal solution upper limit each time, so that command deployment process, achievees the purpose that improve efficiency.
Description
Technical field
The invention belongs to fault diagnosis technology fields, more specifically, are related to a kind of survey based on failure decision networks
Try tactful rapid generation.
Background technique
Increasingly developed with electronic information technology, the circuit design inside complex equipment is increasingly sophisticated, timely and accurately
It determines system mode and internal fault is isolated, can effectively shorten the development, test and setting time of change system.How to set
Count one of the research hotspot that efficient fault test scheme has become complex equipment system design field.
In existing fault test Design Method, sequential test is based on the signal flow diagram and phase provided in Preliminary design
The circuit relationships of closing property model description, provide cycle tests test method, reduce the cost that test generates, can effectively improve
The efficiency of late design and verifying assessment, therefore, which is widely used in the design for Measurability of change system.
In recent years, AO* algorithm by using it is heuristic search element and with or graph search in conjunction with mode improve optimal solution
Search efficiency becomes widely used Diagnostic Strategy generation method.Logic of this method based on failure fuzzy set and measuring point information
Relationship generates the decision-tree model that each failure is isolated, and greatly improves the efficiency of fault diagnosis.However AO* algorithm and its
Relevant improved method only accounts for the probabilistic information of failure and the cost information of each measuring point in heuristic cost evaluation, and
Influence of the failure dependence relationship to heuristic search is had ignored, this causes the strategy of heuristic search to be limited to, and affects calculation
The test optimization efficiency of method.
Patent 201910438846.0 combines heuristic search with Dynamic Programming, by reducing optimal solution repeat search
Number promote solution efficiency, however, the setting of the heuristic function of the patent takes into consideration only test cost and probability of malfunction
Relationship, and having ignored in heuristic search Dependency Specification bring influences, thus the estimation of heuristic function may with it is true
Test cost has very big deviation, and then affects the solution efficiency of optimal Test Strategy.Not with patent 201910438846.0
Together, a kind of Test Strategy rapid generation based on failure decision networks is provided, by the dependence between failure and measuring point,
Optimal Test Strategy is generated using heuristic evaluation value, to isolate the failure in network by optimum search path.
Summary of the invention
It is an object of the invention to overcome the deficiencies of the prior art and provide a kind of Test Strategies based on failure decision networks
Rapid generation generates optimal Test Strategy using heuristic evaluation value by the dependence between failure and measuring point, thus
The failure in network is isolated by optimum search path.
For achieving the above object, a kind of Test Strategy rapid generation based on failure decision networks of the present invention,
Characterized by comprising the following steps:
(1), failure dependence matrix H={ S, P, T, C, the D } of test system to be measured is constructed wherein, S={ s1,s2,…,
si,…,sNIt is the set that fault type is constituted, siIndicate that i-th of fault type, N indicate the total number of fault type；P=
{p1,p2,…,pi,…,pNIt is the set that the corresponding priori probability of malfunction of fault type is constituted, piFor siCorresponding failure priori
Probability；T={ t1,t2,…,tj,…,tMIt is the corresponding set of test measuring point, tjIndicate that j-th of test measuring point, M indicate that test is surveyed
The total number of point；C={ c1,c2,…,cj,…,cMIt is the set that the corresponding test cost of test measuring point is constituted, cjFor tjIt is corresponding
Test cost；D={ dijIt is the Dependency Specification matrix that N*M is tieed up, dij=1, indicate siBy tjIt measures, otherwise dij=0；
(2), the failure decision networks G={ g of test system to be measured is constructedik, wherein gikIt indicates for s to be isolatediAnd skMost
Excellent measuring point, k ≠ i, k=1,2 ..., N；
Optimal measuring point gikCalculation formula are as follows:
gik=argmin { cj|dijΔdkj=1 }
Wherein, Δ indicates XOR operation；
(3), optimal Test Strategy is generated by heuristic search algorithm
(3.1), the fault set S*=S of initial ranging node is set, test set T*=T, opportunity cost value C*=can be used
Cmax, CmaxFor the test cost maximum value of setting；Optimal measuring point t is setopt；
(3.2), the heuristic function assessed value based on failure decision networks is calculated；
Wherein,Indicate measuring point tjIn failure siUnder heuristic function assessed value,WithIt is the two of separation respectively
The valuation functions value of a sub- fault set；
(3.3), measuring point t to be searched is found outo；
(3.4) if, measuring point toTest optimal solution found out or corresponding heuristic function value be greater than opportunity cost value
C*, then by measuring point toLabeled as optimal measuring point topt, and go to step (4), otherwise it is directly entered step (3.5)；
(3.5), according to measuring point toThe Dependency Specification for including, separation failure subsetWith
(3.6) if,It only include single failure, then it represents that the failure is isolated out, recordIsolated fault
Number F0=1 and test cost Cost0=0；Otherwise, willAs new fault set, T* is removed into measuring point toAfterwards as new measuring point
Collection calculatesOpportunity cost beStep (3.2) are returned again to, until findingIsolation therefore
Hinder number F0With test cost Cost0；
(3.7) if,It only include single failure, which is isolated out, recordsIsolated fault number F1=
1, Cost1=0；Otherwise, willAs new fault set, T* is removed into measuring point toAfterwards as new measuring point collection, calculateChance
Cost isStep (3.2) are returned again to, until findingIsolated fault number F1And test
Cost Cost1；
(3.8), measuring point t is updatedoCorresponding heuristic function value；
(3.9), current optimal Fault Isolation number is calculated；
(3.10), updating opportunity cost value C* is
(3.11), measuring point to be searched is updatedAnd by measuring pointLabeled as optimal measuring point topt, and enter step (4)；
(4), Test Strategy is generated
(4.1), the fault set for initializing root node is S'=S；
(4.2), the corresponding optimal measuring point t of S' is found outopt, and separate the subset that is out of order；
Wherein,Indicate siBy toptIt measures, otherwise
(4.3) if, S'0It only include single failure, then it represents that the failure is isolated out, and algorithm terminates；Otherwise, by S'0
As new fault set S', return again to step (4.2), until S'0In only include single failure, algorithm terminates；
(4.4) if, S'1It only include single failure, then it represents that the failure is isolated out, and algorithm terminates；Otherwise, by S'1
As new fault set S', return again to step (4.2), until S'1In only include single failure, algorithm terminates.
Goal of the invention of the invention is achieved in that
The present invention is based on the Test Strategy rapid generations of failure decision networks, by the failure for constructing test system to be measured
Matrix and failure decision networks are relied on, optimal measuring point is generated by heuristic search algorithm, and then obtain optimal Test Strategy, from
And the failure in network is isolated by optimum search path；The influence for combining Dependency Specification to generate optimal policy in this way,
Heuristic function value is accurately estimated, the deviation of heuristic function estimation and search strategy decision in the application is reduced, meanwhile, pass through machine
The optimal solution upper limit is arranged for search each time, so that command deployment process, achievees the purpose that improve efficiency in the setting of meeting cost.
Detailed description of the invention
Fig. 1 is the Test Strategy rapid generation flow chart the present invention is based on failure decision networks；
Fig. 2 is the flow chart that heuristic search generates optimal solution；
Fig. 3 is the comparison figure of heuristic function codomain actual test cost；
Fig. 4 is that left sub- fault set optimizes the upper bound to the isolation effect figure of solution to be searched at root node；
Fig. 5 is that right sub- fault set optimizes the upper bound to the isolation effect figure of solution to be searched at root node；
Fig. 6 is the diagnostic tree generated.
Specific embodiment
A specific embodiment of the invention is described with reference to the accompanying drawing, preferably so as to those skilled in the art
Understand the present invention.Requiring particular attention is that in the following description, when known function and the detailed description of design perhaps
When can desalinate main contents of the invention, these descriptions will be ignored herein.
Embodiment
Fig. 1 is the Test Strategy rapid generation flow chart the present invention is based on failure decision networks.
In the present embodiment, as shown in Figure 1, a kind of Test Strategy side of quickly generating based on failure decision networks of the present invention
Method establishes more accurate heuristic evaluation mechanism by establishing figure decision networks to promote the efficiency of optimal solution search, while structure
It has built opportunity cost and has advanced optimized solution procedure, specifically includes the following steps:
Failure dependence matrix H={ S, P, T, C, the D } of S1, building test system to be measured, wherein S={ s1,s2,…,
si,…,sNIt is the set that fault type is constituted, siIndicate that i-th of fault type, N indicate the total number of fault type；P=
{p1,p2,…,pi,…,pNIt is the set that the corresponding priori probability of malfunction of fault type is constituted, piFor siCorresponding failure priori
Probability；T={ t1,t2,…,tj,…,tMIt is the corresponding set of test measuring point, tjIndicate that j-th of test measuring point, M indicate that test is surveyed
The total number of point；C={ c1,c2,…,cj,…,cMIt is the set that the corresponding test cost of test measuring point is constituted, cjFor tjIt is corresponding
Test cost；D={ dijIt is the Dependency Specification matrix that N*M is tieed up, dij=1, indicate siBy tjIt measures, otherwise dij=0；
The failure decision networks G={ g of S2, building test system to be measuredik, wherein gikIt indicates for s to be isolatediAnd skMost
Excellent measuring point, k ≠ i, k=1,2 ..., N；
Optimal measuring point gikCalculation formula are as follows:
gik=argmin { cj|dijΔdkj=1 }
Wherein, Δ indicates XOR operation；
S3, as shown in Fig. 2, generating optimal test point by heuristic search algorithm
S3.1, the fault set S*=S that initial ranging node is arranged, can use test set T*=T, opportunity cost value C*=
Cmax, CmaxFor the test cost maximum value of setting；Optimal measuring point t is setopt；
S3.2, the heuristic function assessed value based on failure decision networks is calculated；
Wherein,Indicate measuring point tjIn failure siUnder heuristic function assessed value,WithIt is separation respectively
The valuation functions value of the two sub- fault sets in left and right；
Wherein, valuation functions valueWithCalculation method are as follows:
Wherein, L0+L1=N,Indicate isolation siAnd skThe corresponding measuring point cost of optimal measuring point；
S3.3, measuring point t to be searched is found outo；
If S3.4, measuring point toTest optimal solution found out or corresponding heuristic function value be greater than opportunity cost value
C*, then by measuring point toLabeled as optimal measuring point topt, and the S4 that gos to step, otherwise it is directly entered step S3.5；
S3.5, according to measuring point toThe Dependency Specification for including separates left and right failure subsetWith
If S3.6,It only include single failure, then it represents that the failure is isolated out, recordIsolated fault number
F0=1 and test cost Cost0=0；Otherwise, willAs new fault set, T* is removed into measuring point toAfterwards as new measuring point
Collection calculatesOpportunity cost beStep S3.2 is returned again to, until findingIsolated fault
Number F0With test cost Cost0；
If S3.7,It only include single failure, which is isolated out, recordsIsolated fault number F1=
1, Cost1=0；Otherwise, willAs new fault set, T* is removed into measuring point toAfterwards as new measuring point collection, calculateMachine
Cost isStep S3.2 is returned again to, until finding S1 *Isolated fault number F1And test
Cost Cost1；
S3.8, measuring point t is updatedoCorresponding heuristic function value；
S3.9, current optimal Fault Isolation number is calculated；
S3.10, update opportunity cost value C* are
S3.11, measuring point to be searched is updatedAnd by measuring pointLabeled as optimal measuring point topt, and enter step S4；
S4, Test Strategy is generated
S4.1, the fault set for initializing root node are S'=S；
S4.2, the corresponding optimal measuring point t of S' is found outopt, and separate the subset that is out of order；
Wherein,Indicate siBy toptIt measures, otherwise
If S4.3, S'0It only include single failure, then it represents that the failure is isolated out, exports Test Strategy, algorithm knot
Beam；Otherwise, by S'0As new fault set S', return again to step S4.2, until S'0In only include single failure, algorithm knot
Beam；
If S4.4, S'1It only include single failure, then it represents that the failure is isolated out, exports Test Strategy, algorithm knot
Beam；Otherwise, by S'1As new fault set S', return again to step S4.2, until S'1In only include single failure, algorithm knot
Beam.
Example
Technical effect to illustrate the invention, using being verified for antitank system to the present invention.
Antitank system is a complete weapon system, is made of hydraulic, fuel and environmental Kuznets Curves subsystem, for beating
Heavy armored vehicle is hit and destroys, which has 13 system modes and a 12 available measuring points, failure dependence matrix, every
The test cost of a corresponding prior probability of system mode and each measuring point is as shown in table 1.For verifying, the present invention proposes algorithm
Effect, choose antitank system as example, meanwhile, algorithm calculates the example to traditional AO* algorithm together as a comparison.
Table 1 is failure-dependence matrix of antitank system；
Table 1
Left and right subtree heuristic function assessed value by the test method about failure complete or collected works under each measuring point, is totally opened
Several assessed values of sending a letter and the attainable actual test optimal cost of each measuring point are as shown in Figure 2.As can be seen that algorithm from Fig. 2
Effective estimation is made that the test cost under each measuring point, for guiding the search routine of test optimization.
Fig. 3 is that heuristic function value figure compared with actual test cost is obtained by figure network as seen in Figure 3
Heuristic function assessed value it is close with true optimal solution test cost, therefore algorithm can by figure network carry out heuristic function
Accurate assessment, promotes solution efficiency.
Fig. 4 and Fig. 5 is respectively the scatterplot under each measuring point between the search upper bound and heuristic evaluation cost of left and right subtree
Figure, can be seen that influence of the upper dividing value for heuristic search by Fig. 4 and Fig. 5, inspire when the cost upper bound of optimal solution is less than
Function evaluation value, i.e., when scatterplot is below line of demarcation, program stopped searches for the Test Strategy of sub- fault set under the measuring point, thus
Search process is simplified.
By above-mentioned optimization, by the optimal fault diagnosis tree of the invention generated as shown in fig. 6, the present invention is in antitank system
On performance it is as shown in table 2.From Table 2, it can be seen that the present invention has significant advantage on the test optimization time.
| Algorithm | Optimize the time | Searching times | Percent Isolated | Test cost |
| AO* | 32.678s | 168249 | 100% | 4.752 |
| DPAO* | 0.711s | 131 | 100% | 4.752 |
| AOL | 25.61s | 31101 | 100% | 4.752 |
| The present invention | 0.22s | 178 | 100% | 4.752 |
Table 2
To sum up, as seen from Figure 6, the optimal fault tree that the present invention generates can accurately isolate all in system
Failure, and by comparing the performance of algorithm, the fault tree average cost that can obtain the generation of two kinds of algorithms is identical, and in time
It can boosting algorithm efficiency to a certain extent using dynamic programming method.
Although the illustrative specific embodiment of the present invention is described above, in order to the technology of the art
Personnel understand the present invention, it should be apparent that the present invention is not limited to the range of specific embodiment, to the common skill of the art
For art personnel, if various change the attached claims limit and determine the spirit and scope of the present invention in, these
Variation is it will be apparent that all utilize the innovation and creation of present inventive concept in the column of protection.
Claims (2)
1. a kind of Test Strategy rapid generation based on failure decision networks, which comprises the following steps:
(1), failure dependence matrix H={ S, P, T, C, the D } of test system to be measured is constructed, wherein S={ s1,s2,…,si,…,sN}
For the set that fault type is constituted, siIndicate that i-th of fault type, N indicate the total number of fault type；P={ p1,p2,…,
pi,…,pNIt is the set that the corresponding priori probability of malfunction of fault type is constituted, piFor siCorresponding failure prior probability；T=
{t1,t2,…,tj,…,tMIt is the corresponding set of test measuring point, tjIndicate that j-th of test measuring point, M indicate total of test measuring point
Number；C={ c1,c2,…,cj,…,cMIt is the set that the corresponding test cost of test measuring point is constituted, cjFor tjCorresponding test generation
Valence；D={ dijIt is the Dependency Specification matrix that N*M is tieed up, dij=1, indicate siBy tjIt measures, otherwise dij=0；
(2), the failure decision networks G={ g of test system to be measured is constructedik, wherein gikIt indicates for s to be isolatediAnd skOptimal survey
Point, k ≠ i, k=1,2 ..., N；
Optimal measuring point gikCalculation formula are as follows:
gik=argmin { cj|dijΔdkj=1 }
Wherein, Δ indicates XOR operation；
(3), optimal test point is generated by heuristic search algorithm
(3.1), the fault set S*=S of initial ranging node is set, test set T*=T, opportunity cost value C*=C can be usedmax, Cmax
Most it is worth significantly for the test cost of setting；Optimal measuring point t is setopt；
(3.2), the heuristic function assessed value based on failure decision networks is calculated；
Wherein,Indicate measuring point tjIn failure siUnder heuristic function assessed value,WithIt is two sons of separation respectively
The valuation functions value of fault set；
(3.3), measuring point t to be searched is found outo；
to=argmin { heftj,tj∈T*}
(3.4) if, measuring point toTest optimal solution found out or corresponding heuristic function value be greater than opportunity cost value C*, then
By measuring point toLabeled as optimal measuring point topt, and go to step (4), otherwise it is directly entered step (3.5)；
(3.5), according to measuring point toThe Dependency Specification for including, separation failure subsetWith
(3.6) if,It only include single failure, then it represents that the failure is isolated out, recordIsolated fault number F0
=1 and test cost Cost0=0；Otherwise, willAs new fault set, T* is removed into measuring point measuring point toAfterwards as new survey
Point set calculatesOpportunity cost beStep (3.2) are returned again to, until findingIsolation
Failure number F0With test cost Cost0；
(3.7) if,It only include single failure, which is isolated out, recordsIsolated fault number F1=1,
Cost1=0；Otherwise, willAs new fault set, T* is removed into measuring point measuring point toAfterwards as new measuring point collection, calculateMachine
Cost isStep (3.2) are returned again to, until findingIsolated fault number F1And survey
Try cost Cost1；
(3.8), measuring point t is updatedoCorresponding heuristic function value；
(3.9), current optimal Fault Isolation number is calculated；
(3.10), updating opportunity cost value C* is
(3.11), measuring point to be searched is updatedAnd by measuring pointLabeled as optimal measuring point topt, and enter step (4)；
(4), Test Strategy is generated
(4.1), the fault set for initializing root node is S'=S；
(4.2), the corresponding optimal measuring point t of S' is found outopt, and separate the subset that is out of order；
Wherein,Indicate siBy toptIt measures, otherwise
(4.3) if, S '0It only include single failure, then it represents that the failure is isolated out, and algorithm terminates；Otherwise, by S '0As
New fault set S' is returned again to step (4.2), until S '0In only include single failure, terminate；
(4.4) if, S '1It only include single failure, then it represents that the failure is isolated out, and algorithm terminates；Otherwise, by S '1As
New fault set S' is returned again to step (4.2), until S '1In only include single failure, algorithm terminates.
2. a kind of Test Strategy rapid generation based on failure decision networks according to claim 1, feature exist
In the valuation functions valueWithCalculation method are as follows:
Wherein, L0+L1=N,Indicate isolation siAnd skThe corresponding measuring point cost of optimal measuring point.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910661767.1A CN110457776B (en) | 2019-07-22 | 2019-07-22 | Test strategy rapid generation method based on fault decision network |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910661767.1A CN110457776B (en) | 2019-07-22 | 2019-07-22 | Test strategy rapid generation method based on fault decision network |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110457776A true CN110457776A (en) | 2019-11-15 |
| CN110457776B CN110457776B (en) | 2022-06-14 |
Family
ID=68481669
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910661767.1A Active CN110457776B (en) | 2019-07-22 | 2019-07-22 | Test strategy rapid generation method based on fault decision network |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110457776B (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111274540A (en) * | 2020-02-24 | 2020-06-12 | 电子科技大学 | Fault diagnosis tree generation method based on information entropy and dynamic programming |
| CN113221496A (en) * | 2021-05-06 | 2021-08-06 | 电子科技大学 | Fault diagnosis method based on three-dimensional testability analysis model |
| CN114528948A (en) * | 2022-03-10 | 2022-05-24 | 电子科技大学 | Method for generating sequential test sequence of complex system |
Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101126929A (en) * | 2007-09-05 | 2008-02-20 | 东北大学 | Continuous miner remote real-time failure forecast and diagnosis method and device |
| CN102520342A (en) * | 2011-12-07 | 2012-06-27 | 南京航空航天大学 | Analog circuit test node selecting method based on dynamic feedback neural network modeling |
| US20120303348A1 (en) * | 2011-05-23 | 2012-11-29 | Gm Global Technology Operation Llc | System and methods for fault-isolation and fault-mitigation based on network modeling |
| US8745440B1 (en) * | 2010-09-21 | 2014-06-03 | F5 Networks, Inc. | Computer-implemented system and method for providing software fault tolerance |
| CN105629156A (en) * | 2016-03-10 | 2016-06-01 | 电子科技大学 | Genetic programming-based analog circuit fault test optimal sequential search method |
| CN105699882A (en) * | 2016-01-22 | 2016-06-22 | 电子科技大学 | Analog circuit fault diagnosis method based on oscillation testing technology |
| CN106095608A (en) * | 2016-06-17 | 2016-11-09 | 电子科技大学 | Sequential test dynamic adjusting method based on AO* algorithm |
| US9866161B1 (en) * | 2014-05-21 | 2018-01-09 | Williams RDM, Inc. | Universal monitor and fault detector in fielded generators and method |
| FR3059432A1 (en) * | 2016-11-25 | 2018-06-01 | Commissariat A L'energie Atomique Et Aux Energies Alternatives | METHOD AND DEVICE FOR FAULT ANALYSIS IN A NETWORK OF TRANSMISSION LINES |
| CN109581190A (en) * | 2018-12-05 | 2019-04-05 | 电子科技大学 | A kind of optimal diagnosis tree generation method for circuit fault diagnosis |
| CN109581194A (en) * | 2018-12-18 | 2019-04-05 | 电子科技大学 | A kind of electronic system malfunction Test Strategy dynamic creation method |
-
2019
- 2019-07-22 CN CN201910661767.1A patent/CN110457776B/en active Active
Patent Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101126929A (en) * | 2007-09-05 | 2008-02-20 | 东北大学 | Continuous miner remote real-time failure forecast and diagnosis method and device |
| US8745440B1 (en) * | 2010-09-21 | 2014-06-03 | F5 Networks, Inc. | Computer-implemented system and method for providing software fault tolerance |
| US20120303348A1 (en) * | 2011-05-23 | 2012-11-29 | Gm Global Technology Operation Llc | System and methods for fault-isolation and fault-mitigation based on network modeling |
| CN102520342A (en) * | 2011-12-07 | 2012-06-27 | 南京航空航天大学 | Analog circuit test node selecting method based on dynamic feedback neural network modeling |
| US9866161B1 (en) * | 2014-05-21 | 2018-01-09 | Williams RDM, Inc. | Universal monitor and fault detector in fielded generators and method |
| CN105699882A (en) * | 2016-01-22 | 2016-06-22 | 电子科技大学 | Analog circuit fault diagnosis method based on oscillation testing technology |
| CN105629156A (en) * | 2016-03-10 | 2016-06-01 | 电子科技大学 | Genetic programming-based analog circuit fault test optimal sequential search method |
| CN106095608A (en) * | 2016-06-17 | 2016-11-09 | 电子科技大学 | Sequential test dynamic adjusting method based on AO* algorithm |
| FR3059432A1 (en) * | 2016-11-25 | 2018-06-01 | Commissariat A L'energie Atomique Et Aux Energies Alternatives | METHOD AND DEVICE FOR FAULT ANALYSIS IN A NETWORK OF TRANSMISSION LINES |
| CN109581190A (en) * | 2018-12-05 | 2019-04-05 | 电子科技大学 | A kind of optimal diagnosis tree generation method for circuit fault diagnosis |
| CN109581194A (en) * | 2018-12-18 | 2019-04-05 | 电子科技大学 | A kind of electronic system malfunction Test Strategy dynamic creation method |
Non-Patent Citations (3)
| Title |
|---|
| PEDRO SANTOS 等: "Identifying maximum imbalance in datasets for fault diagnosis of gearboxes", 《J INTELL MANUF》 * |
| 吕游 等: "基于β系数的序贯测试优化方法", 《计算机工程与设计》 * |
| 杨成林等: "多值故障字典的测点选择与序测试设计", 《系统工程与电子技术》 * |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111274540A (en) * | 2020-02-24 | 2020-06-12 | 电子科技大学 | Fault diagnosis tree generation method based on information entropy and dynamic programming |
| CN113221496A (en) * | 2021-05-06 | 2021-08-06 | 电子科技大学 | Fault diagnosis method based on three-dimensional testability analysis model |
| CN113221496B (en) * | 2021-05-06 | 2022-06-14 | 电子科技大学 | Fault diagnosis method based on three-dimensional testability analysis model |
| CN114528948A (en) * | 2022-03-10 | 2022-05-24 | 电子科技大学 | Method for generating sequential test sequence of complex system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110457776B (en) | 2022-06-14 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110457776A (en) | A kind of Test Strategy rapid generation based on failure decision networks | |
| CN109142946A (en) | Transformer fault detection method based on ant group algorithm optimization random forest | |
| CN103336885B (en) | A kind of method solving Weapon-Target Assignment Problem based on differential evolution algorithm | |
| CN105373601B (en) | A kind of multi-model matching method based on keyword words-frequency feature | |
| CN110750655B (en) | Knowledge base optimization method of intelligent IETM fault maintenance auxiliary system | |
| CN109581190A (en) | A kind of optimal diagnosis tree generation method for circuit fault diagnosis | |
| CN109254219B (en) | A kind of distribution transforming transfer learning method for diagnosing faults considering multiple factors Situation Evolution | |
| CN106485089A (en) | The interval parameter acquisition methods of harmonic wave user's typical condition | |
| CN105512783A (en) | Comprehensive evaluation method used for loop-opening scheme of electromagnetic looped network | |
| CN104680262A (en) | Receiving-end grid optimal layering and districting scheme obtaining method | |
| CN114330094A (en) | Wind power short-term prediction method based on TCN-GRU combined model | |
| CN106228002A (en) | A kind of high efficiency exception time series data extracting method based on postsearch screening | |
| CN106056235A (en) | Power transmission grid efficiency and benefit detection method based on Klee method and matter element extension model | |
| Acampora et al. | Applying NSGA-II for solving the ontology alignment problem | |
| Lin et al. | A rule activation method for extended belief rule base with VP-tree and MVP-tree | |
| CN109066651A (en) | The calculation method of wind-powered electricity generation-load scenarios limit transmitted power | |
| Li et al. | An extended TODIM method and its application in the stock selection under dual hesitant fuzzy linguistic information | |
| CN110033126A (en) | Shot and long term memory network prediction technique based on attention mechanism and logistic regression | |
| Liu et al. | Simga: A simple and effective heterophilous graph neural network with efficient global aggregation | |
| Daoudi et al. | Constraint Acquisition with Recommendation Queries. | |
| CN109213869A (en) | Hot spot technology prediction technique based on multi-source data | |
| Daoudi et al. | Detecting types of variables for generalization in constraint acquisition | |
| Liu et al. | Research on node importance of power communication network based on multi-attribute analysis | |
| Yan et al. | Improved ELM optimization model for automobile insurance fraud identification based on AFSA | |
| Liu et al. | Link Prediction in Signed Networks based on The Similarity and Structural Balance Theory. |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |