CN116400662A - Fault deduction method and device combining forward reasoning and reverse reasoning - Google Patents
Fault deduction method and device combining forward reasoning and reverse reasoning Download PDFInfo
- Publication number
- CN116400662A CN116400662A CN202310085883.XA CN202310085883A CN116400662A CN 116400662 A CN116400662 A CN 116400662A CN 202310085883 A CN202310085883 A CN 202310085883A CN 116400662 A CN116400662 A CN 116400662A
- Authority
- CN
- China
- Prior art keywords
- fault
- entity
- probability
- relation
- performance
- 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
- 238000000034 method Methods 0.000 title claims abstract description 52
- 208000024891 symptom Diseases 0.000 claims abstract description 36
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 12
- 238000011058 failure modes and effects analysis Methods 0.000 claims abstract description 8
- 238000009826 distribution Methods 0.000 claims description 24
- 238000004590 computer program Methods 0.000 claims description 12
- 230000008569 process Effects 0.000 claims description 12
- 238000000926 separation method Methods 0.000 claims description 12
- 230000006870 function Effects 0.000 claims description 9
- 230000009466 transformation Effects 0.000 claims description 5
- 230000005540 biological transmission Effects 0.000 claims description 4
- 238000004364 calculation method Methods 0.000 claims description 4
- 238000010276 construction Methods 0.000 claims description 3
- 230000005856 abnormality Effects 0.000 claims description 2
- 230000001131 transforming effect Effects 0.000 claims description 2
- 230000009471 action Effects 0.000 description 4
- 230000001364 causal effect Effects 0.000 description 4
- 238000010586 diagram Methods 0.000 description 3
- 238000004891 communication Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 238000007619 statistical method Methods 0.000 description 2
- 238000012795 verification Methods 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 1
- 230000019771 cognition Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000005265 energy consumption Methods 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000007704 transition Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B23/00—Testing or monitoring of control systems or parts thereof
- G05B23/02—Electric testing or monitoring
- G05B23/0205—Electric testing or monitoring by means of a monitoring system capable of detecting and responding to faults
- G05B23/0218—Electric testing or monitoring by means of a monitoring system capable of detecting and responding to faults characterised by the fault detection method dealing with either existing or incipient faults
- G05B23/0243—Electric testing or monitoring by means of a monitoring system capable of detecting and responding to faults characterised by the fault detection method dealing with either existing or incipient faults model based detection method, e.g. first-principles knowledge model
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B2219/00—Program-control systems
- G05B2219/20—Pc systems
- G05B2219/24—Pc safety
- G05B2219/24065—Real time diagnostics
Abstract
The invention relates to a fault deduction method and device combining forward reasoning and reverse reasoning, wherein the method comprises the following steps: constructing a performance-fault relation map of the spacecraft control system according to the FMEA; each entity of the performance-fault relation map comprises two states, each entity has a corresponding entity probability attribute, the entity probability attribute is used for describing the occurrence probability of fault reasons, each relation of the performance-fault relation map has a corresponding relation probability attribute, and the relation probability attribute is used for describing the probability of states of a head entity and a tail entity; converting the performance-fault relationship map into a junction tree; calculating probability values of all nodes in the junction tree to obtain a most likely fault cause set of each fault symptom; and determining a final fault reason and a fault influence path in the current fault reason set by adopting an A-star algorithm aiming at each fault reason set. The method and the device can improve the accuracy of the fault deduction result of the spacecraft control system.
Description
Technical Field
The invention relates to the technical field of aerospace, in particular to a fault deduction method and device combining forward reasoning and reverse reasoning.
Background
The spacecraft control system has long working time, high precision requirement and special environment, is limited by conditions such as weight and energy consumption, and has the defects of multiple fault types, complex fault reasons and wide influence factors.
The fault deduction combining forward reasoning and reverse reasoning mainly refers to a process of determining a fault cause and a fault influence path according to fault symptoms reflected by telemetry parameters. Certain causal relation exists between the fault reasons and the fault symptoms, but the reasons such as complexity of space environment, limitation of world communication, incompleteness of knowledge description and the like cause the mapping relation between the fault reasons and the fault symptoms to have strong uncertainty, and the accuracy of a fault deduction result is directly influenced. Therefore, a complex fault is difficult to find an accurate fault cause or propagation path at a time, and multiple reasoning and gradual removal are required.
Disclosure of Invention
In order to improve accuracy of a fault deduction result of a spacecraft control system, the embodiment of the invention provides a fault deduction method and device combining forward reasoning and reverse reasoning.
In a first aspect, an embodiment of the present invention provides a fault deduction method combining forward reasoning with reverse reasoning, including:
constructing a performance-fault relation map of the spacecraft control system according to the FMEA; each entity of the performance-fault relation map comprises two states, each entity has a corresponding entity probability attribute, the entity probability attribute is used for describing the occurrence probability of a fault cause, each relation of the performance-fault relation map has a corresponding relation probability attribute, and the relation probability attribute is used for describing the probability of the states of a head entity and a tail entity;
converting said performance-fault relationship map into a junction tree;
calculating probability values of all nodes in the junction tree to obtain a most likely fault cause set of each fault symptom;
and determining the final fault reason and fault influence path in the current fault reason set by adopting an A-star algorithm according to each fault reason set.
In a second aspect, an embodiment of the present invention further provides a fault deduction device combining forward reasoning and reverse reasoning, including:
the construction module is used for constructing a performance-fault relation map of the spacecraft control system according to the FMEA; each entity of the performance-fault relation map comprises two states, each entity has a corresponding entity probability attribute, the entity probability attribute is used for describing the occurrence probability of a fault cause, each relation of the performance-fault relation map has a corresponding relation probability attribute, and the relation probability attribute is used for describing the probability of the states of a head entity and a tail entity;
a transformation module for transforming said performance-fault relationship map into a junction tree;
the calculation module is used for calculating the probability value of each node in the junction tree so as to obtain a fault cause set most likely to occur for each fault symptom;
and the determining module is used for determining the final fault reason and the fault influence path in the current fault reason set by adopting an A-star algorithm aiming at each fault reason set.
In a third aspect, an embodiment of the present invention further provides an electronic device, including a memory and a processor, where the memory stores a computer program, and when the processor executes the computer program, the processor implements the method according to any embodiment of the present invention.
In a fourth aspect, embodiments of the present invention further provide a computer readable storage medium having stored thereon a computer program which, when executed in a computer, causes the computer to perform the method according to any of the embodiments of the present invention.
The embodiment of the invention provides a fault deduction method and device combining forward reasoning with reverse reasoning, which adopts causal reasoning based on a junction tree to carry out reverse reasoning of fault deduction, can give a reasoning result with probability from incomplete, inaccurate or uncertain knowledge or information, and can realize accurate reasoning of a fault influence process; forward reasoning of fault deduction is carried out by adopting A-star heuristic search, an optimal fault influence path is obtained by identifying the maximum probability in a search space, and approximate reasoning of a fault influence process can be realized; the accuracy of spacecraft fault reasoning results is improved by combining accurate reasoning based on the junction tree with approximate reasoning based on search and utilizing repeated verification of different principles and different directions.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings that are required in the embodiments or the description of the prior art will be briefly described, and it is obvious that the drawings in the following description are some embodiments of the present invention, and other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flow chart of a fault deduction method combining forward reasoning with reverse reasoning according to an embodiment of the present invention;
FIG. 2 is a hardware architecture diagram of an electronic device according to an embodiment of the present invention;
fig. 3 is a block diagram of a fault deduction device combining forward reasoning with reverse reasoning according to an embodiment of the present invention.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the embodiments of the present invention more apparent, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention, and it is apparent that the described embodiments are some embodiments of the present invention, but not all embodiments, and all other embodiments obtained by those skilled in the art without making any inventive effort based on the embodiments of the present invention are within the scope of protection of the present invention.
Referring to fig. 1, an embodiment of the present invention provides a fault deduction method combining forward reasoning and reverse reasoning, where the method includes:
step 100: constructing a performance-fault relation map of the spacecraft control system according to the FMEA; each entity of the performance-fault relation map comprises two states, each entity has a corresponding entity probability attribute, the entity probability attribute is used for describing the occurrence probability of fault reasons, each relation of the performance-fault relation map has a corresponding relation probability attribute, and the relation probability attribute is used for describing the probability of states of a head entity and a tail entity;
step 102: converting the performance-fault relationship map into a junction tree;
step 104: calculating probability values of all nodes in the junction tree to obtain a most likely fault cause set of each fault symptom;
step 106: and determining a final fault reason and a fault influence path in the current fault reason set by adopting an A-star algorithm aiming at each fault reason set.
In the embodiment of the invention, the reverse reasoning of fault deduction is performed by adopting causal reasoning based on the junction tree, so that a reasoning result with probability can be given from incomplete, inaccurate or uncertain knowledge or information, and the accurate reasoning of the fault influence process can be realized; forward reasoning of fault deduction is carried out by adopting A-star heuristic search, an optimal fault influence path is obtained by identifying the maximum probability in a search space, and approximate reasoning of a fault influence process can be realized; the accuracy of spacecraft fault reasoning results is improved by combining accurate reasoning based on the junction tree with approximate reasoning based on search and utilizing repeated verification of different principles and different directions.
It can be known that the knowledge graph can provide a new means for acquiring, storing, organizing, managing, updating and displaying the spacecraft fault knowledge information with complex relations by means of the great advantages of the knowledge graph in the aspects of constructing a knowledge network and showing knowledge association, and provides a fault knowledge application and fault reasoning mode which is more in line with cognition habits, so that the efficiency and the accuracy of fault deduction are improved, therefore, the knowledge graph knowledge is utilized to construct a spacecraft performance-fault relation graph, and on the basis, the research of a fault deduction method is carried out, so that the accuracy of a spacecraft fault reasoning result can be improved.
The manner in which the individual steps shown in fig. 1 are performed is described below.
For step 100:
in one embodiment of the invention, the set of triples in the performance-fault relationship graph includes: < component-containing-functional module >, < functional module-occurrence-failure cause >, < failure cause-failure mode >, < failure mode-manifestation-failure symptom >;
when an entity is a part, the states are the part and not the part;
when the entity is a functional module, the state is the functional module and is not the functional module;
when the entity is the fault cause, the state is that the fault cause occurs and the fault cause does not occur;
when the entity is in the fault mode, the state is that the fault mode occurs and the fault mode does not occur;
when an entity is a fault symptom, the state is abnormal and normal.
In this embodiment, a spacecraft performance-failure relationship map is constructed manually or automatically according to FMEA, including triplets mainly of < part-containing-function >, < function-occurrence-failure cause >, < failure cause-failure mode >, < failure mode-manifestation-failure sign >, etc.
Each entity in the spacecraft performance-fault relationship map comprises two states, and the specific meaning is shown in table one. For the failure cause, the entity i has a probability attribute of w e,i ＝P(s i =1) describing the probability of occurrence of a cause of failure, typically obtained from expert experience or statistical methods, s i Representing the state of entity i. While for other entities, their probability attributes w e,k ＝1。
List one
Setting the probability attribute of the relation between the head entity i and the tail entity j as follows
Wherein w is r,i,j,1 Describing the probability of 0 for the head entity and 0 for the tail entity, i.e. w r,i,j,1 =p (tail entity is 0|head entity is 0), w r,i,j,2 =p (tail entity is 0|head entity is 1), w r,i,j,3 =p (tail entity is 1|head entity is 0), w r,i,j,4 P (tail entity is 1|head entity is 1). The values of the relational probability attributes are typically obtained from expert experience or statistical methods.
For steps 102 and 104:
the reverse reasoning of the spacecraft fault evolution process mainly aims at each fault reason m, P (m|g) is calculated, namely the probability that the current fault symptom g is caused by the fault reason m is calculated, the probabilities of all the fault reasons are ordered from high to low, and the first three fault reasons are selected to be the reverse reasoning result.
The invention adopts a causal reasoning method based on a junction tree algorithm to realize the reverse reasoning of the spacecraft fault evolution process, and the basic thinking is as follows: firstly, converting a performance-fault relation map into a junction tree, then transmitting information in the junction tree until the whole tree is consistent with the information, and finally calculating probability values of all nodes to obtain a reverse reasoning result of the fault. The method comprises the following specific steps:
in one embodiment of the present invention, step 102 may specifically include:
converting a directed edge in the performance-fault relation map into a non-directed edge, and connecting two head entities with the same tail entity to form a prop-meaning map;
triangularizing the obtained trace-meaning graph;
finding all clusters forming a junction tree for the triangulated trace-meaning graph; the clusters are the maximum full-connected subgraphs in the triangulated trace-meaning graph, and each pair of different entities in the clusters have a relation;
determining separation entities between different clusters based on all clusters obtained;
the junction tree is constructed based on the order of cluster-separating entity-clusters.
In one embodiment of the present invention, the step of determining the separation entity between different clusters based on all clusters obtained may specifically comprise:
constructing an array of n rows and n columns; wherein n is the number of clusters, each row and each column is marked by one cluster, and each element in the array is an entity corresponding to the row cluster and the column cluster;
the elements with two identical entities in the array are used as separation entities.
In one embodiment of the present invention, the step of "calculating probability values of nodes in the junction tree to obtain a set of failure causes most likely to occur for each failure symptom" may specifically include:
initializing a junction tree;
message transmission is carried out on the initialized junction tree;
based on probability distribution of each cluster node and each separated entity node, calculating probability values of each node in the junction tree to obtain a most likely fault cause set of each fault symptom.
Wherein, initializing the junction tree, namely utilizing entity probability attribute w of performance-fault relation map e,i Probability attribute w of relation r,i,j The probability functions of each cluster node and each separate entity node are calculated.
Specifically, in one embodiment of the present invention, the step of "initializing the junction tree" may specifically include:
probability function phi of each node x Initializing to 1;
the tail entity of either head entity V is designated Pa (V), for both V and VClustering Pa (V), let phi x ←φ x P (v|pa (V)), the value of P (v|pa (V)) is as follows:
w r,i,j,1 =p (tail entity 0|head entity 0)
w r,i,j,2 =p (tail entity is 0|head entity is 1)
w r,i,j,3 =p (tail entity is 1|head entity is 0)
w r,i,j,4 =p (tail entity 1|head entity 1)
Wherein s is i Representing the status of entity i.
Where messaging includes both message divergence and message reception processes.
Specifically, in one embodiment of the present invention, the step of "messaging over the initialized junction tree" may specifically include:
message divergence is carried out on the initialized junction tree; wherein message divergence refers to the probability of separating entity nodes joining two cluster nodes being noted as phi S,pre And recalculate the probability of separating the nodes using:
receiving the message on the initialized junction tree; wherein, the message receiving refers to the separation node probability distribution phi according to the recalculation S Updating the probability distribution of the cluster nodes using the following formula:
wherein C represents a cluster node, S represents a separate entity node, φ C Represent the probability distribution, phi, of cluster nodes S Representing probability distribution of separate entity nodes。
In one embodiment of the present invention, the step of "calculating probability values of nodes in the junction tree based on probability distributions of each cluster node and each separate entity node to obtain a set of failure causes most likely to occur for each failure symptom" may specifically include:
assuming m as the cause of the failure, X is a cluster node including m, φ X For a probability distribution of X, for a given failure symptom g, the probability distribution of failure cause m is as follows:
in Sigma X/m φ X Representing the sum of the pairs phi according to other elements in the cluster node X after m is removed X A summation operation is performed such that,
representing a summation operation from all values of m;
for all fault reasons, calculating the probability of occurrence of the current fault symptom g caused by each fault reason according to the above formula;
and sorting according to the probability of each fault cause from large to small, and selecting the first three fault causes to form a fault cause set most likely to occur.
For step 106:
and (3) aiming at three fault reasons contained in the fault positioning result candidate set obtained in the step (104), adopting an A-star algorithm, and finally determining the fault reason corresponding to the current fault symptom and the corresponding fault deepening path through forward reasoning.
The A-star algorithm is a heuristic search method, and is mainly characterized in that in a state space formed by each entity of a performance-fault relation graph, the state of each searched entity is evaluated, and after the optimal entity state is obtained, the search is performed from the state until a target is found.
S is set as an initial entity, one of fault reasons obtained in the second step is assumed to be OPEN is a table for storing an entity to be expanded, CLOSED is a table for storing an expanded entity, and forward reasoning is carried out by utilizing an A-star algorithm as follows:
a. the original entity S, i.e. the cause of the fault, is put in the CLOSED table.
b. For any tail entity k contained in a triplet with entity S as the head entity, the following operations are performed:
if entity k is neither in OPEN nor CLOSED table, it is added to OPEN table, f (k) of entity k is calculated, where f (k) =w r,S,k,4 。
If entity k is already in the OPEN table, using entity S as the parent node of entity k, recalculating f (k) of entity k, and if f (k) recalculated is greater than f (k) calculated previously, updating f (k).
If entity k is already in the CLOSED table, no action is performed.
c. Checking whether the OPEN table is empty, if so, indicating that the search fails, otherwise, executing the step d.
d. And (3) selecting an entity q corresponding to the maximum f (q) value from the OPEN table, if the entity is a target entity, directly transferring to the step e, otherwise, removing the entity q from the OPEN table, putting the entity q into the CLOSED table, and repeatedly executing the step b instead of the entity S.
e. According to the elements contained in the CLOSED table, starting from the end point, moving along each father node, returning to the start point, obtaining a fault influence path, and calculating the influence path weight of the fault reason m
Where t represents the number of entities on the path affected by the failure cause m.
And (3) respectively utilizing the A-star algorithm to obtain corresponding influence path weights for the three fault reasons obtained in the step (104) through the forward reasoning, wherein the fault reason corresponding to the maximum influence path weight is the final fault positioning result, and further obtaining the fault influence path of the fault reason.
As shown in fig. 2 and 3, the embodiment of the invention provides a fault deduction device combining forward reasoning and reverse reasoning. The apparatus embodiments may be implemented by software, or may be implemented by hardware or a combination of hardware and software. In terms of hardware, as shown in fig. 2, a hardware architecture diagram of an electronic device where a fault deduction device combining forward reasoning and reverse reasoning is provided in an embodiment of the present invention, besides a processor, a memory, a network interface, and a nonvolatile memory shown in fig. 2, the electronic device where the device is located in the embodiment may generally include other hardware, such as a forwarding chip responsible for processing a packet, and so on. Taking a software implementation as an example, as shown in fig. 3, the device in a logic sense is formed by reading a corresponding computer program in a nonvolatile memory into a memory by a CPU of an electronic device where the device is located and running the computer program.
As shown in fig. 3, the fault deduction device combining forward reasoning with reverse reasoning provided in this embodiment includes:
a building module 300 for building a performance-fault relationship map of the spacecraft control system according to the FMEA; each entity of the performance-fault relation map comprises two states, each entity has a corresponding entity probability attribute, the entity probability attribute is used for describing the occurrence probability of a fault cause, each relation of the performance-fault relation map has a corresponding relation probability attribute, and the relation probability attribute is used for describing the probability of the states of a head entity and a tail entity;
a transformation module 302, configured to transform the performance-fault relationship map into a junction tree;
the calculating module 304 is configured to calculate probability values of nodes in the junction tree to obtain a set of fault causes most likely to occur for each fault symptom;
and a determining module 306, configured to determine, for each of the failure cause sets, a final failure cause and a failure impact path in the current failure cause set by adopting an a-star algorithm.
In an embodiment of the present invention, the construction module 300 may be used to perform the step 100 in the above-described method embodiment, the transformation module 302 may be used to perform the step 102 in the above-described method embodiment, the calculation module 304 may be used to perform the step 104 in the above-described method embodiment, and the determination module 306 may be used to perform the step 106 in the above-described method embodiment.
In one embodiment of the invention, the set of triples in the performance-fault relationship graph includes: < component-containing-functional module >, < functional module-occurrence-failure cause >, < failure cause-failure mode >, < failure mode-manifestation-failure symptom >;
when the entity is a part, the status is that the part and not the part;
when the entity is a functional module, the state is the functional module and not the functional module;
when the entity is the fault cause, the state is that the fault cause occurs and the fault cause does not occur;
when the entity is in a fault mode, the state is that the fault mode occurs and the fault mode does not occur;
when the entity is a fault symptom, the status is symptom abnormality and symptom normal.
In one embodiment of the present invention, the transition module is configured to perform the following operations:
converting the directed edges in the performance-fault relation graph into undirected edges, and connecting two head entities with the same tail entity to form a prop graph;
triangularizing the obtained trace-meaning graph;
finding all clusters forming a junction tree for the triangulated trace-meaning graph; the clusters are the maximum full-connected subgraphs in the triangulated trace-meaning graph, and each pair of different entities in the clusters have a relation;
determining separation entities between different clusters based on all clusters obtained;
the junction tree is constructed based on the order of cluster-separating entity-clusters.
In one embodiment of the invention, the transformation module, when executing the determination of the separation entity between different clusters based on all clusters obtained, is configured to perform the following operations:
constructing an array of n rows and n columns; wherein n is the number of clusters, each row and each column is marked by one cluster, and each element in the array is an entity corresponding to the row cluster and the column cluster;
and taking the elements with two identical entities in the array as separation entities.
In one embodiment of the present invention, the computing module is configured to perform the following operations:
initializing a junction tree;
message transmission is carried out on the initialized junction tree;
and calculating probability values of all nodes in the junction tree based on probability distribution of all cluster nodes and all separated entity nodes so as to obtain a most likely fault cause set of each fault symptom.
In one embodiment of the present invention, the computing module, when executing the initializing the junction tree, is configured to perform the following operations:
probability function phi of each node x Initializing to 1;
the tail entity of either head entity V is designated Pa (V), and phi is given for clusters containing both V and Pa (V) x ←φ x P (v|pa (V)), the value of P (v|pa (V)) is as follows:
w r,i,j,1 =p (tail entity 0|head entity 0)
w r,i,j,2 =p (tail entity is 0|head entity is 1)
w r,i,j,3 =p (tail entity is 1|head entity is 0)
w r,i,j,4 =p (tail entity 1|head entity 1)
Wherein s is i Representing the status of entity i;
the computing module is used for executing the following operations when executing the message transmission on the initialized junction tree:
message divergence is carried out on the initialized junction tree; wherein message divergence refers to the probability of separating entity nodes joining two cluster nodes being noted as phi S,pre And recalculate the probability of separating the nodes using:
receiving the message on the initialized junction tree; wherein, the message receiving refers to the separation node probability distribution phi according to the recalculation S Updating the probability distribution of the cluster nodes using the following formula:
wherein C represents a cluster node, S represents a separate entity node, φ C Represent the probability distribution, phi, of cluster nodes S Representing the probability distribution of the separate entity nodes.
In one embodiment of the present invention, the calculation module is configured to, when executing the probability distribution based on each cluster node and each separate entity node, calculate a probability value of each node in the junction tree to obtain a set of fault causes that each fault symptom is most likely to occur, perform the following operations:
assuming m as the cause of the failure, X is a cluster node including m, φ X For a probability distribution of X, for a given failure symptom g, the probability distribution of failure cause m is as follows:
in Sigma X/m φ X Representing the sum of the pairs phi according to other elements in the cluster node X after m is removed X A summation operation is performed such that,
representing a summation operation from all values of m;
for all fault reasons, calculating the probability of occurrence of the current fault symptom g caused by each fault reason according to the above formula;
and sorting according to the probability of each fault cause from large to small, and selecting the first three fault causes to form a fault cause set most likely to occur.
It will be appreciated that the structure illustrated in the embodiments of the present invention does not constitute a specific limitation on a fault deduction device combining forward reasoning with reverse reasoning. In other embodiments of the invention, a fault inference means combining forward and reverse reasoning may include more or fewer components than shown, or may combine certain components, or split certain components, or a different arrangement of components. The illustrated components may be implemented in hardware, software, or a combination of software and hardware.
The content of information interaction and execution process between the modules in the device is based on the same conception as the embodiment of the method of the present invention, and specific content can be referred to the description in the embodiment of the method of the present invention, which is not repeated here.
The embodiment of the invention also provides electronic equipment, which comprises a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the processor realizes the fault deduction method combining forward reasoning and reverse reasoning in any embodiment of the invention.
The embodiment of the invention also provides a computer readable storage medium, and the computer readable storage medium stores a computer program, and when the computer program is executed by a processor, the processor is caused to execute the fault deduction method combining forward reasoning with reverse reasoning in any embodiment of the invention.
Specifically, a system or apparatus provided with a storage medium on which a software program code realizing the functions of any of the above embodiments is stored, and a computer (or CPU or MPU) of the system or apparatus may be caused to read out and execute the program code stored in the storage medium.
In this case, the program code itself read from the storage medium may realize the functions of any of the above-described embodiments, and thus the program code and the storage medium storing the program code form part of the present invention.
Examples of the storage medium for providing the program code include a floppy disk, a hard disk, a magneto-optical disk, an optical disk (e.g., CD-ROM, CD-R, CD-RW, DVD-ROM, DVD-RAM, DVD-RW, DVD+RW), a magnetic tape, a nonvolatile memory card, and a ROM. Alternatively, the program code may be downloaded from a server computer by a communication network.
Further, it should be apparent that the functions of any of the above-described embodiments may be implemented not only by executing the program code read out by the computer, but also by causing an operating system or the like operating on the computer to perform part or all of the actual operations based on the instructions of the program code.
Further, it is understood that the program code read out by the storage medium is written into a memory provided in an expansion board inserted into a computer or into a memory provided in an expansion module connected to the computer, and then a CPU or the like mounted on the expansion board or the expansion module is caused to perform part and all of actual operations based on instructions of the program code, thereby realizing the functions of any of the above embodiments.
It is noted that relational terms such as first and second, and the like, are used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Moreover, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus.
Those of ordinary skill in the art will appreciate that: all or part of the steps for implementing the above method embodiments may be implemented by hardware related to program instructions, and the foregoing program may be stored in a computer readable storage medium, where the program, when executed, performs steps including the above method embodiments; and the aforementioned storage medium includes: various media in which program code may be stored, such as ROM, RAM, magnetic or optical disks.
Finally, it should be noted that: the above embodiments are only for illustrating the technical solution of the present invention, and are not limiting; although the invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the present invention.
Claims (10)
1. The fault deduction method combining forward reasoning and reverse reasoning is characterized by comprising the following steps:
constructing a performance-fault relation map of the spacecraft control system according to the FMEA; each entity of the performance-fault relation map comprises two states, each entity has a corresponding entity probability attribute, the entity probability attribute is used for describing the occurrence probability of a fault cause, each relation of the performance-fault relation map has a corresponding relation probability attribute, and the relation probability attribute is used for describing the probability of the states of a head entity and a tail entity;
converting said performance-fault relationship map into a junction tree;
calculating probability values of all nodes in the junction tree to obtain a most likely fault cause set of each fault symptom;
and determining the final fault reason and fault influence path in the current fault reason set by adopting an A-star algorithm according to each fault reason set.
2. The method of claim 1, wherein the set of triples in the performance-fault relationship graph comprises: < component-containing-functional module >, < functional module-occurrence-failure cause >, < failure cause-failure mode >, < failure mode-manifestation-failure symptom >;
when the entity is a part, the status is that the part and not the part;
when the entity is a functional module, the state is the functional module and not the functional module;
when the entity is the fault cause, the state is that the fault cause occurs and the fault cause does not occur;
when the entity is in a fault mode, the state is that the fault mode occurs and the fault mode does not occur;
when the entity is a fault symptom, the status is symptom abnormality and symptom normal.
3. The method of claim 1, wherein said converting said performance-fault relationship map into a junction tree comprises:
converting the directed edges in the performance-fault relation graph into undirected edges, and connecting two head entities with the same tail entity to form a prop graph;
triangularizing the obtained trace-meaning graph;
finding all clusters forming a junction tree for the triangulated trace-meaning graph; the clusters are the maximum full-connected subgraphs in the triangulated trace-meaning graph, and each pair of different entities in the clusters have a relation;
determining separation entities between different clusters based on all clusters obtained;
the junction tree is constructed based on the order of cluster-separating entity-clusters.
4. A method according to claim 3, wherein said determining separation entities between different clusters based on all clusters obtained comprises:
constructing an array of n rows and n columns; wherein n is the number of clusters, each row and each column is marked by one cluster, and each element in the array is an entity corresponding to the row cluster and the column cluster;
and taking the elements with two identical entities in the array as separation entities.
5. A method according to claim 3, wherein said calculating probability values for nodes in the junction tree to derive a set of fault causes for which each fault symptom is most likely to occur comprises:
initializing a junction tree;
message transmission is carried out on the initialized junction tree;
and calculating probability values of all nodes in the junction tree based on probability distribution of all cluster nodes and all separated entity nodes so as to obtain a most likely fault cause set of each fault symptom.
6. The method of claim 5, wherein initializing the junction tree comprises:
probability function phi of each node x Initializing to 1;
the tail entity of either head entity V is designated Pa (V), and phi is given for clusters containing both V and Pa (V) x ←φ x P (VPa (V)), the value of P (v|pa (V)) is as follows:
w r,i,j,1 =p (tail entity 0|head entity 0)
w r,i,j,2 =p (tail entity is 0|head entity is 1)
w r,i,j,3 =p (tail entity is 1|head entity is 0)
w r,i,j,4 =p (tail entity 1 head entity 1)
In the method, in the process of the invention,s i representing the status of entity i;
the message passing on the initialized junction tree comprises the following steps:
message divergence is carried out on the initialized junction tree; wherein message divergence refers to the probability of separating entity nodes joining two cluster nodes being noted as phi S,pre And recalculate the probability of separating the nodes using:
φ S ＝∑ C/S φ C ；
receiving the message on the initialized junction tree; wherein, the message receiving refers to the separation node probability distribution phi according to the recalculation S Updating the probability distribution of the cluster nodes using the following formula:
wherein C represents a cluster node, S represents a separate entity node, φ C Represent the probability distribution, phi, of cluster nodes S Representing the probability distribution of the separate entity nodes.
7. The method of claim 6, wherein calculating probability values for nodes in the junction tree based on probability distributions for each cluster node and each separate entity node to obtain a set of most likely fault causes for each fault symptom comprises:
assuming m as the cause of the failure, X is a cluster node including m, φ X For a probability distribution of X, for a given failure symptom g, the probability distribution of failure cause m is as follows:
in Sigma X/m φ X Representing the sum of the pairs phi according to other elements in the cluster node X after m is removed X A summation operation is performed such that,
representing a summation operation from all values of m;
for all fault reasons, calculating the probability of occurrence of the current fault symptom g caused by each fault reason according to the above formula;
and sorting according to the probability of each fault cause from large to small, and selecting the first three fault causes to form a fault cause set most likely to occur.
8. A fault deduction device combining forward reasoning and reverse reasoning, comprising:
the construction module is used for constructing a performance-fault relation map of the spacecraft control system according to the FMEA; each entity of the performance-fault relation map comprises two states, each entity has a corresponding entity probability attribute, the entity probability attribute is used for describing the occurrence probability of a fault cause, each relation of the performance-fault relation map has a corresponding relation probability attribute, and the relation probability attribute is used for describing the probability of the states of a head entity and a tail entity;
a transformation module for transforming said performance-fault relationship map into a junction tree;
the calculation module is used for calculating the probability value of each node in the junction tree so as to obtain a fault cause set most likely to occur for each fault symptom;
and the determining module is used for determining the final fault reason and the fault influence path in the current fault reason set by adopting an A-star algorithm aiming at each fault reason set.
9. An electronic device comprising a memory and a processor, the memory having stored therein a computer program, the processor implementing the method of any of claims 1-7 when the computer program is executed.
10. A computer readable storage medium having stored thereon a computer program which, when executed in a computer, causes the computer to perform the method of any of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310085883.XA CN116400662B (en) | 2023-01-18 | 2023-01-18 | Fault deduction method and device combining forward reasoning and reverse reasoning |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310085883.XA CN116400662B (en) | 2023-01-18 | 2023-01-18 | Fault deduction method and device combining forward reasoning and reverse reasoning |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116400662A true CN116400662A (en) | 2023-07-07 |
| CN116400662B CN116400662B (en) | 2023-09-15 |
Family
ID=87012993
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310085883.XA Active CN116400662B (en) | 2023-01-18 | 2023-01-18 | Fault deduction method and device combining forward reasoning and reverse reasoning |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116400662B (en) |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108320040A (en) * | 2017-01-17 | 2018-07-24 | 国网重庆市电力公司 | Acquisition terminal failure prediction method and system based on Bayesian network optimization algorithm |
| CN111368888A (en) * | 2020-02-25 | 2020-07-03 | 重庆邮电大学 | Service function chain fault diagnosis method based on deep dynamic Bayesian network |
| CN113111242A (en) * | 2021-03-10 | 2021-07-13 | 西安理工大学 | Self-adaptive learning path recommendation method based on knowledge graph |
-
2023
- 2023-01-18 CN CN202310085883.XA patent/CN116400662B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108320040A (en) * | 2017-01-17 | 2018-07-24 | 国网重庆市电力公司 | Acquisition terminal failure prediction method and system based on Bayesian network optimization algorithm |
| CN111368888A (en) * | 2020-02-25 | 2020-07-03 | 重庆邮电大学 | Service function chain fault diagnosis method based on deep dynamic Bayesian network |
| CN113111242A (en) * | 2021-03-10 | 2021-07-13 | 西安理工大学 | Self-adaptive learning path recommendation method based on knowledge graph |
Non-Patent Citations (4)
| Title |
|---|
| 李彦柯等: "知识图谱引导的贝叶斯网概率推理", 《小型微型计算机系统》, vol. 43, no. 6 * |
| 樊忠: "矿井提升设备制动系统故障诊断系统关键技术与应用研究", 《中国优秀硕士学位论文全文数据库》 * |
| 胡小建等: "基于联结树的贝叶斯网的推理结构及构造算法", 《系统仿真学报》, vol. 16, no. 11 * |
| 邢晓宇等: "考虑语义和位置信息的航天器知识图谱关系预测方法", 《空间控制技术与应用》, vol. 48, no. 6 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116400662B (en) | 2023-09-15 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108038183B (en) | Structured entity recording method, device, server and storage medium | |
| US11438212B2 (en) | Fault root cause analysis method and apparatus | |
| Steck et al. | Bayesian belief networks for data mining | |
| US9372736B2 (en) | Leveraging path information to generate predictions for parallel business processes | |
| US20080034074A1 (en) | Determination of graph connectivity metrics using bit-vectors | |
| CN113098723A (en) | Fault root cause positioning method and device, storage medium and equipment | |
| US20180314951A1 (en) | Reasoning system, reasoning method, and recording medium | |
| CN114781688A (en) | Method, device, equipment and storage medium for identifying abnormal data of business expansion project | |
| CN116400662B (en) | Fault deduction method and device combining forward reasoning and reverse reasoning | |
| Gertsbakh et al. | Network reliability: a lecture course | |
| Gao et al. | Clustering algorithms for detecting functional modules in protein interaction networks | |
| CN116388864B (en) | Quantum network device performance prediction method and device, electronic device and storage medium | |
| US9195557B2 (en) | Fault tree analysis system, fault tree analysis method and programme | |
| Fahmi et al. | A Multi-Class Classification of Dengue Infection Cases with Feature Selection in Imbalanced Clinical Diagnosis Data. | |
| EP2213066A2 (en) | Acquisition and expansion of storage area network interoperation relationships | |
| Lê et al. | A novel variable ordering heuristic for BDD-based K-terminal reliability | |
| Adorada et al. | The comparison of feature selection methods in software defect prediction | |
| CN113704519B (en) | Data set determining method and device, computer equipment and storage medium | |
| WO2021072646A1 (en) | Method and system for using production data for rapid modeling, and storage medium | |
| US10965315B2 (en) | Data compression method | |
| CN116089611B (en) | Spacecraft fault diagnosis method and device based on performance-fault relation map | |
| CN116304083B (en) | Relation prediction method and device for performance-fault relation map | |
| CN116203926B (en) | Spacecraft fault grading diagnosis method based on performance-fault relation map | |
| US20120078943A1 (en) | High quantitative pattern searching using spatial indexing | |
| Streicher | Incremental inference on higher-order probabilistic graphical models applied to constraint satisfaction problems |
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 |