CN110457776B - Test strategy rapid generation method based on fault decision network - Google Patents
Test strategy rapid generation method based on fault decision network Download PDFInfo
- Publication number
- CN110457776B CN110457776B CN201910661767.1A CN201910661767A CN110457776B CN 110457776 B CN110457776 B CN 110457776B CN 201910661767 A CN201910661767 A CN 201910661767A CN 110457776 B CN110457776 B CN 110457776B
- Authority
- CN
- China
- Prior art keywords
- fault
- test
- point
- optimal
- cost
- 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.)
- Active
Links
Images
Abstract
The invention discloses a test strategy rapid generation method based on a fault decision network, which comprises the steps of constructing a fault dependency matrix and the fault decision network of a system to be tested, generating an optimal test point through a heuristic search algorithm, and further obtaining an optimal test strategy, so that faults in the network are isolated through an optimal search path; therefore, by combining the influence of the dependence information on the generation of the optimal strategy, the heuristic function value is accurately estimated, the deviation of the heuristic function estimation and the search strategy decision in application is reduced, and meanwhile, the optimal solution upper limit is set for each search through the setting of opportunity cost, so that the search process is controlled, and the aim of improving the efficiency is fulfilled.
Description
Technical Field
The invention belongs to the technical field of fault diagnosis, and particularly relates to a test strategy rapid generation method based on a fault decision network.
Background
With the increasing development of electronic information technology, the circuit design inside the complex equipment becomes complex, the system state is determined timely and accurately, internal faults are isolated, and the development, test and setting time of the equipment system can be effectively shortened. How to design an efficient fault testing scheme has become one of the research hotspots in the field of complex equipment system design.
In the existing design method of the fault test scheme, a test sequence test method is provided based on a signal flow diagram given in preliminary design and a circuit relation described by a correlation model in sequential test, so that the cost generated by the test is reduced, and the efficiency of later-stage design and verification evaluation can be effectively improved.
In recent years, the AO algorithm improves the search efficiency of the optimal solution by adopting a mode of combining heuristic search and or graph search, and becomes a widely used diagnostic strategy generation method. The method generates a decision tree model for isolating each fault based on the logical relationship of the fault fuzzy set and the measuring point information, thereby greatly improving the efficiency of fault diagnosis. However, in the AO algorithm and the related improved method thereof, only probability information of a fault and cost information of each measuring point are considered in heuristic cost evaluation, and influence of a fault dependency relationship on heuristic search is ignored, so that a strategy of the heuristic search is limited, and test optimization efficiency of the algorithm is influenced.
Patent 201910438846.0 combines heuristic search with dynamic programming, and improves the solving efficiency by reducing the number of repeated search of the optimal solution, however, the setting of the heuristic function of the patent only considers the relation between the test cost and the failure probability, and ignores the influence caused by information dependence in the heuristic search, so that the estimation of the heuristic function may have great deviation from the real test cost, and further influences the solving efficiency of the optimal test strategy. Different from patent 201910438846.0, a method for rapidly generating a test strategy based on a fault decision network is provided, which generates an optimal test strategy by using a heuristic evaluation value through a dependency relationship between a fault and a test point, thereby isolating the fault in the network through an optimal search path.
Disclosure of Invention
The invention aims to overcome the defects of the prior art and provides a test strategy rapid generation method based on a fault decision network.
In order to achieve the above object, the present invention provides a method for rapidly generating a test policy based on a fault decision network, which is characterized by comprising the following steps:
(1) and constructing a fault dependence matrix H ═ { S, P, T, C, D } of the system to be tested, wherein S ═ S { (S) }1,s2,…,si,…,sNIs a set of fault types, siRepresenting the ith fault type, and N representing the total number of the fault types; p ═ P1,p2,…,pi,…,pNIs a set formed by prior fault probabilities corresponding to fault types, piIs as siCorresponding fault prior probability; t ═ T1,t2,…,tj,…,tMIs the set corresponding to the test point, tjRepresenting the jth test point, and M representing the total number of the test points; c ═ C1,c2,…,cj,…,cMIs a set of test costs corresponding to the test points, cjIs tjCorresponding test cost; d ═ DijIs a dependency information matrix of dimension N x M, d ij1 denotes siQuilt tjMeasure, otherwise dij=0;
(2) And constructing a fault decision network G ═ G of the system to be testedikIn which g isikRepresentation for isolating siAnd skK ≠ i, k ═ 1,2 …, N;
optimal measuring point gikThe calculation formula of (2) is as follows:
gik=argmin{cj|dijΔdkj=1}
wherein Δ represents an exclusive or operation;
(3) generating an optimal test strategy through a heuristic search algorithm
(3.1) setting a fault set S ═ S of the initial search node, a usable test set T ═ T, and an opportunity cost value C ═ Cmax,CmaxIs the set maximum value of the test cost; setting an optimal measuring point topt;
(3.2) calculating a heuristic function evaluation value based on a fault decision network;
wherein the content of the first and second substances,represents the measured point tjAt fault siThe evaluation value of the heuristic function in the following,andthe evaluation function values of the two separate sub-fault sets are respectively;
(3.3) finding out a measuring point t to be searchedo;
(3.4) if the point t is measuredoIf the test optimal solution has been found or the corresponding heuristic function value is greater than the opportunity cost value C, the test point t is measuredoMarked as optimal measurement point toptAnd jumping to the step (4), otherwise, directly entering the step (3.5);
(3.5) according to the measuring point toIncluding dependency information, separating fault subsetsAnd
(3.6) ifContaining only a single fault, indicating that the fault has been isolated, and recordingNumber of isolation faults F 01 and a test Cost 00; otherwise, it willRemoving T as new fault setRemoving measuring point toThen as a new measuring point set, calculatingAt the opportunity cost ofAnd returning to the step (3.2) until the step is foundNumber of isolation faults of F0And a test Cost0;
(3.7) ifContaining only a single fault, which has been isolated, recordedNumber of isolation faults of F1=1,Cost 10; otherwise, it willAs a new fault set, removing T from the measuring point ToThen as a new measuring point set, calculatingAt the opportunity cost ofAnd returning to the step (3.2) until the step is foundNumber of isolation faults F1And a test Cost1;
(3.8) updating the measuring point toA corresponding heuristic function value;
(3.9) calculating the current optimal fault isolation number;
(3.11) updating the measuring point to be searchedAnd measure the pointMarked as optimal measurement point toptAnd entering the step (4);
(4) generating a test strategy
(4.1) initializing a fault set of the root node as S' ═ S;
(4.2) finding out the optimal measuring point t corresponding to SoptAnd separating out the fault subset;
wherein the content of the first and second substances,denotes siQuilt toptMeasure otherwise, otherwise
(4.3) if S'0If only a single fault is contained, the fault is isolated, and the algorithm is ended; otherwise, will S'0And returning to the step (4.2) as a new fault set S 'until S'0Only contains a single fault, and the algorithm is ended;
(4.4) if S'1If only a single fault is contained, the fault is isolated, and the algorithm is ended; otherwise, will S'1And returning to the step (4.2) as a new fault set S 'until S'1Contains only a single fault and the algorithm ends.
The invention aims to realize the following steps:
the invention relates to a test strategy rapid generation method based on a fault decision network, which comprises the steps of constructing a fault dependence matrix and the fault decision network of a system to be tested, generating an optimal measuring point through a heuristic search algorithm, and further obtaining an optimal test strategy, so that faults in the network are isolated through an optimal search path; therefore, the heuristic function value is accurately estimated by combining the influence of the dependence information on the generation of the optimal strategy, the deviation of the heuristic function estimation and the search strategy decision in the application is reduced, and meanwhile, the optimal solution upper limit is set for each search through the setting of opportunity cost, so that the search process is controlled, and the aim of improving the efficiency is fulfilled.
Drawings
FIG. 1 is a flow chart of a method for rapidly generating a test strategy based on a fault decision network according to the present invention;
FIG. 2 is a flow chart of a heuristic search to generate an optimal solution;
FIG. 3 is a comparison graph of heuristic function value field actual test costs;
FIG. 4 is a graph of the effect of upper optimization of left sub-fault sets at a root node on isolation of a solution to be searched;
FIG. 5 is a diagram of the effect of right sub-fault set optimization upper bound on the isolation of the solution to be searched at the root node;
FIG. 6 is a generated diagnostic tree.
Detailed Description
The following description of the embodiments of the present invention is provided in order to better understand the present invention for those skilled in the art with reference to the accompanying drawings. It is to be expressly noted that in the following description, a detailed description of known functions and designs will be omitted when it may obscure the subject matter of the present invention.
Examples
FIG. 1 is a flow chart of a test strategy rapid generation method based on a fault decision network according to the present invention.
In this embodiment, as shown in fig. 1, the method for quickly generating a test strategy based on a fault decision network according to the present invention establishes a more accurate heuristic evaluation mechanism to improve the efficiency of optimal solution search by establishing a graph decision network, and simultaneously establishes an opportunity cost further optimization solution process, and specifically includes the following steps:
s1, constructing a fault dependence matrix H ═ { S, P, T, C, D } of the system to be tested, wherein S ═ S { (S) }1,s2,…,si,…,sNIs a set of fault types, siRepresenting the ith fault type, and N representing the total number of the fault types; p ═ P1,p2,…,pi,…,pNIs a set formed by prior fault probabilities corresponding to fault types, piIs s isiCorresponding fault prior probability; t ═ T1,t2,…,tj,…,tMIs the set corresponding to the test point, tjRepresenting the jth test point, and M representing the total number of the test points; c ═ C1,c2,…,cj,…,cMIs a set of test costs corresponding to the test points, cjIs tjCorresponding test cost; d ═ DijIs a dependency information matrix of dimension N x M, d ij1 denotes siQuilt tjMeasure, otherwise dij=0;
S2, constructing a fault decision network G-G of the system to be testedikIn which g isikRepresentation for isolating siAnd skK is not equal to i, k is 1,2 …, N;
optimal measuring point gikThe calculation formula of (c) is:
gik=argmin{cj|dijΔdkj=1}
wherein Δ represents an exclusive or operation;
s3, as shown in figure 2, generating the optimal test point by a heuristic search algorithm
S3.1, setting a fault set S ═ S of the initial search node, setting a usable test set T ═ T, and setting an opportunity cost value C ═ Cmax,CmaxIs the set maximum value of the test cost; setting an optimal measuring point topt;
S3.2, calculating a heuristic function evaluation value based on a fault decision network;
wherein the content of the first and second substances,represents the measured point tjAt fault siThe evaluation value of the heuristic function in the following,andthe evaluation function values of the left and right sub-fault sets are separated respectively;
wherein L is0+L1=N,Represents the isolation siAnd skThe cost of the measuring point corresponding to the optimal measuring point;
s3.3, finding out a measuring point t to be searchedo;
S3.4, if measure point toIf the test optimal solution has been found or the corresponding heuristic function value is greater than the opportunity cost value C, the test point t is measuredoMarked as optimal measurement point toptAnd jumping to step S4, otherwise, directly entering step S3.5;
s3.5, according to the measuring point toIncluding dependency information, separating left and right subsets of faultsAnd
s3.6, ifContaining only a single fault, indicating that the fault has been isolated, and recordingNumber of isolation faults of F 01 and a test Cost 00; otherwise, it willAs a new fault set, removing T from the measuring point ToThen as a new measuring point set, calculatingAt the opportunity cost ofAnd then returns to step S3.2 until the search is foundNumber of isolation faults F0And a test Cost0;
S3.7, ifContaining only a single fault, which has been isolated, recordedNumber of isolation faults F1=1,Cost 10; otherwise, it willAs a new fault set, removing T from the measuring point ToThen as a new measuring point set, calculatingAt the opportunity cost ofAnd then returns to step S3.2 until the search is foundNumber of isolation faults F1And a test Cost1;
S3.8, updating the measuring point toA corresponding heuristic function value;
s3.9, calculating the current optimal fault isolation number;
S3.11, updating measuring points to be searchedAnd measure the pointMarked as optimal measurement point toptAnd proceeds to step S4;
s4, generating test strategy
S4.1, initializing a fault set of the root node as S' ═ S;
s4.2, finding out the optimal measuring point t corresponding to SoptAnd separating out the fault subsets;
S4.3, if S'0If only a single fault is contained, the fault is isolated, a test strategy is derived, and the algorithm is ended; otherwise, will S'0And returning to the step S4.2 as a new fault set S 'until S'0Only contains a single fault, and the algorithm is ended;
s4.4, if S'1If only a single fault is contained, the fault is isolated, a test strategy is derived, and the algorithm is ended; otherwise, will S'1And returning to the step S4.2 as a new fault set S 'until S'1Contains only a single fault and the algorithm ends.
Examples of the invention
In order to illustrate the technical effect of the invention, the invention is verified by taking an antitank system as an example.
The anti-tank system is a complete weapon system, consists of hydraulic, fuel and environment control subsystems and is used for striking and destroying heavy armored vehicles, the system has 13 system states and 12 available measuring points, and a fault dependence matrix, the prior probability corresponding to each system state and the test cost of each measuring point are shown in table 1. In order to verify the effect of the algorithm provided by the invention, an antitank system is selected as an example, and meanwhile, the conventional AO algorithm is used as a comparison algorithm to calculate the example together.
Table 1 is the fault-dependency matrix of the anti-tank system;
TABLE 1
The left and right subtree heuristic function evaluation values of the fault complete set under each measuring point, the overall heuristic function evaluation value and the actual test optimal cost which can be achieved by each measuring point are shown in FIG. 2. As can be seen from FIG. 2, the algorithm effectively estimates the test cost at each test point, and the estimation is used for guiding the search flow of test optimization.
Fig. 3 is a comparison graph of the heuristic function value and the actual test cost, and it can be seen from fig. 3 that the heuristic function evaluation value obtained through the graph network is close to the actual optimal solution test cost, so that the algorithm can perform accurate evaluation of the heuristic function by means of the graph network, and the solution efficiency is improved.
Fig. 4 and 5 are scatter diagrams between the upper search bound and the heuristic evaluation cost of the left and right subtrees at each measurement point respectively, the influence of the upper bound value on heuristic search can be seen through fig. 4 and 5, and when the upper cost bound of the optimal solution is smaller than the heuristic function evaluation value, that is, the scatter point is below the boundary, the program stops the test strategy search on the sub-fault set at the measurement point, thereby simplifying the search process.
Through the above optimization, the optimal troubleshooting tree generated by the present invention is shown in fig. 6, and the performance of the present invention on the antitank system is shown in table 2. As can be seen from table 2, the present invention has significant advantages in test optimization time.
Algorithm | Optimizing time | Number of searches | Fault isolation rate | Testing costs |
AO* | 32.678s | 168249 | 100% | 4.752 |
DPAO* | 0.711s | 131 | 100% | 4.752 |
AOL | 25.61s | 31101 | 100% | 4.752 |
The invention | 0.22s | 178 | 100% | 4.752 |
TABLE 2
In summary, it can be seen from fig. 6 that the optimal fault tree generated by the present invention can accurately separate all faults in the system, and by comparing performance of the algorithms, the average cost of the fault trees generated by the two algorithms is the same, and the dynamic planning method is adopted in time to improve algorithm efficiency to a certain extent.
Although illustrative embodiments of the present invention have been described above to facilitate the understanding of the present invention by those skilled in the art, it should be understood that the present invention is not limited to the scope of the embodiments, and various changes may be made apparent to those skilled in the art as long as they are within the spirit and scope of the present invention as defined and defined by the appended claims, and all matters of the invention which utilize the inventive concepts are protected.
Claims (1)
1. A test strategy rapid generation method based on a fault decision network is characterized by comprising the following steps:
(1) and constructing a fault dependence matrix H ═ { S, P, T, C, D } of the system to be tested, wherein S ═ S { (S) }1,s2,…,si,…,sNIs a set of fault types, siRepresenting the ith fault type, and N representing the total number of the fault types; p ═ P1,p2,…,pi,…,pNIs a set formed by prior fault probabilities corresponding to fault types, piIs s isiA corresponding fault prior probability; t ═ T1,t2,…,tj,…,tMIs the set corresponding to the test point, tjRepresenting the jth test point, and M representing the total number of the test points; c ═ C1,c2,…,cj,…,cMIs a set of test costs corresponding to the test points, cjIs tjCorresponding test cost; d ═ DijIs a dependency information matrix of dimension N x M, dij1 denotes siQuilt tjMeasure, otherwise dij=0;
(2) And constructing a fault decision network G ═ G of the system to be testedikIn which g isikRepresentation for isolating siAnd skK ≠ i, k ═ 1,2 …, N;
optimal measuring point gikThe calculation formula of (c) is:
gik=argmin{cj|dijΔdkj=1}
wherein Δ represents an exclusive or operation;
(3) generating the optimal test point by a heuristic search algorithm
(3.1) setting a fault set S ═ S of the initial search node, a usable test set T ═ T, and an opportunity cost value C ═ Cmax,CmaxIs the set maximum value of the test cost; setting an optimal measuring point topt;
(3.2) calculating a heuristic function evaluation value based on a fault decision network;
wherein the content of the first and second substances,represents the measured point tjAt fault siThe value of the lower heuristic function evaluated,andrespectively two separate sub-fault setsAndthe evaluation function value of (1);
(3.3) finding out a measuring point t to be searchedo;
(3.4) if the point t is measuredoIf the test optimal solution has been found or the corresponding heuristic function value is greater than the opportunity cost value C, the test point t is measuredoMarked as optimal measurement point toptAnd jumping to the step (4), otherwise, directly entering the step (3.5);
(3.5) according to the measuring point toIncluding dependency information, separating fault subsetsAnd
(3.6) ifContaining only a single fault, indicating that the fault has been isolated, and recordingNumber of isolation faults F01 and a test Cost00; otherwise, it willAs a new fault set, remove T from the measure point ToThen as a new measuring point set, calculatingAt the opportunity cost ofAnd returning to the step (3.2) until the step is foundNumber of isolation faults F0And a test Cost0;
(3.7) ifContaining only a single fault, which has been isolated, recordedNumber of isolation faults F1=1,Cost10; otherwise, it willAs a new fault set, remove T from the measure point ToThen as a new measuring point set, calculatingAt the opportunity cost ofAnd returning to the step (3.2) until the step is foundNumber of isolation faults F1And a test Cost1;
(3.8) updating the measuring point toA corresponding heuristic function value;
(3.9) calculating the current optimal fault isolation number;
(3.11) updating the measuring point to be searchedAnd measure the pointMarked as optimal measurement point toptAnd entering the step (4);
(4) generating a test strategy
(4.1) initializing a fault set of the root node as S' ═ S;
(4.2) finding out the optimal measuring point t corresponding to SoptAnd separating out the fault subset;
(4.3) if S'0If only a single fault is contained, the fault is isolated, and the algorithm is ended; otherwise, will S'0And returning to the step (4.2) as a new fault set S 'until S'0Only contains a single fault, and the calculation is finished;
(4.4) if S'1If only a single fault is contained, the fault is isolated, and the algorithm is ended; otherwise, will S'1As a new fault set S', returning to the step (4.2) until S1' only a single fault is contained, and the algorithm ends;
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 CN110457776A (en) | 2019-11-15 |
CN110457776B true 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) |
Families Citing this family (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 |
CN113221496B (en) * | 2021-05-06 | 2022-06-14 | 电子科技大学 | Fault diagnosis method based on three-dimensional testability analysis model |
CN114528948B (en) * | 2022-03-10 | 2023-07-11 | 电子科技大学 | Sequential test sequence generation method of complex system |
Citations (1)
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 |
Family Cites Families (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US8745440B1 (en) * | 2010-09-21 | 2014-06-03 | F5 Networks, Inc. | Computer-implemented system and method for providing software fault tolerance |
US8577663B2 (en) * | 2011-05-23 | 2013-11-05 | GM Global Technology Operations LLC | System and methods for fault-isolation and fault-mitigation based on network modeling |
CN102520342B (en) * | 2011-12-07 | 2013-11-06 | 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 |
CN105699882B (en) * | 2016-01-22 | 2018-05-29 | 电子科技大学 | Analog-circuit fault diagnosis method based on vibration test technology |
CN105629156B (en) * | 2016-03-10 | 2018-04-13 | 电子科技大学 | Analog circuit fault based on genetic planning tests optimal sequential search method |
CN106095608B (en) * | 2016-06-17 | 2019-03-15 | 电子科技大学 | Sequential test dynamic adjusting method based on AO* algorithm |
FR3059432B1 (en) * | 2016-11-25 | 2020-02-28 | Commissariat A L'energie Atomique Et Aux Energies Alternatives | METHOD AND DEVICE FOR ANALYZING DEFECTS IN A NETWORK OF TRANSMISSION LINES |
CN109581190B (en) * | 2018-12-05 | 2020-08-11 | 电子科技大学 | Optimal diagnosis tree generation method for circuit fault diagnosis |
CN109581194B (en) * | 2018-12-18 | 2020-08-11 | 电子科技大学 | Dynamic generation method for electronic system fault test strategy |
-
2019
- 2019-07-22 CN CN201910661767.1A patent/CN110457776B/en active Active
Patent Citations (1)
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 |
Also Published As
Publication number | Publication date |
---|---|
CN110457776A (en) | 2019-11-15 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110457776B (en) | Test strategy rapid generation method based on fault decision network | |
CN109581190B (en) | Optimal diagnosis tree generation method for circuit fault diagnosis | |
CN111999657B (en) | Method for evaluating driving mileage of lithium ion battery of electric vehicle in residual life | |
CN111007399B (en) | Lithium battery state of charge prediction method based on improved generation countermeasure network | |
CN109060398B (en) | Multi-source information equipment fault diagnosis method | |
CN109617888B (en) | Abnormal flow detection method and system based on neural network | |
CN110348615B (en) | Cable line fault probability prediction method based on ant colony optimization support vector machine | |
CN110568360B (en) | Lithium battery aging diagnosis method based on fuzzy logic algorithm | |
CN111274540A (en) | Fault diagnosis tree generation method based on information entropy and dynamic programming | |
CN112132102B (en) | Intelligent fault diagnosis method combining deep neural network with artificial bee colony optimization | |
CN115051864B (en) | PCA-MF-WNN-based network security situation element extraction method and system | |
CN105228185A (en) | A kind of method for Fuzzy Redundancy node identities in identification communication network | |
CN109581194B (en) | Dynamic generation method for electronic system fault test strategy | |
CN113821452B (en) | Intelligent test method for dynamically generating test case according to test performance of tested system | |
CN115791174B (en) | Rolling bearing abnormality diagnosis method, system, electronic equipment and storage medium | |
CN112036079B (en) | Diesel engine multi-information fusion diagnosis method based on ANFIS | |
CN114818859A (en) | Method and device for diagnosing condition of heat distribution pipe network, terminal equipment and storage medium | |
CN115454473A (en) | Data processing method based on deep learning vulnerability decision and information security system | |
CN113887452A (en) | Fault diagnosis optimization method based on correlation matrix | |
CN112801367A (en) | Fault prediction method based on ARMret model considering rare variables | |
CN112685957A (en) | Method for predicting relay protection defects | |
CN113159640A (en) | Method, device, equipment and medium for determining evaluation index weight | |
CN113312722A (en) | Reliability prediction optimization method for key components of urban rail train | |
CN113657604A (en) | Device and method for operating an inspection table | |
CN111460456B (en) | Attack method for realizing clear decision tree and fuzzy decision tree based on sensitivity |
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 |