Fault multiple diagnosis reasoning method and system based on tensor decomposition

Abstract

A method and system for multi-stage fault diagnosis and reasoning based on tensor decomposition, belonging to the field of fault prediction and health management technology, includes the following steps: Step 1: constructing an initial fault knowledge graph based on expert experience; Step 2: vectorizing the entities and edges in the initial fault knowledge graph using tensor decomposition to obtain a fault vector knowledge graph; Step 3: obtaining the fault phenomenon #imgabs0# to be detected, calculating the similarity of all entities in the fault vector knowledge graph of the fault phenomenon to be detected, and treating all entities in the fault vector knowledge graph that are directly connected to the entity #imgabs2# with the highest similarity to the fault phenomenon #imgabs1# to be detected via edges as a one-hop entity set connected to the fault phenomenon to be detected. This method can diagnose the comprehensive fault causes of a specific fault phenomenon.

Description

Technical Field

[0001] The present invention relates to a fault multiple diagnosis reasoning method and system based on tensor decomposition, belonging to the technical field of fault prediction and health management. Background Art

[0002] The aerospace sector has always been a key area of development for every country and a reflection of a country's scientific and technological innovation capabilities. Driven by the continuous growth and improvement of my country's economic strength, the aerospace industry is booming. However, as the functionality and efficiency of equipment continue to improve, the structure and functions of avionics equipment are becoming increasingly complex, significantly increasing the difficulty of maintenance and repair. Therefore, to ensure the normal operation and reliability of aviation equipment, the ability to accurately locate and resolve faults when they occur, as well as the ability to predict faults before they occur, has become a key research topic.

[0003] Combining fault analysis with knowledge graph technology to creatively construct a fault knowledge graph leverages the advantages of artificial intelligence to overcome the limitations of traditional fault analysis. This integration not only revolutionizes fault analysis methods but also represents an innovative approach to knowledge management and intelligent decision-making. The fault knowledge graph integrates multiple data sources, including existing fault data, expert knowledge, and equipment information, and presents them visually in the form of a graph. Through this structured approach, the knowledge graph can assist operators in quickly and accurately retrieving and acquiring relevant information, and can also identify potential connections and common features between different fault cases. Because existing information is incomplete and insufficient, relationships between two entities may be missing or omitted during knowledge graph construction. Therefore, the use of knowledge reasoning is crucial in knowledge graphs. It can enrich existing knowledge graph relationships, making the process of building a fault knowledge graph more intelligent and efficient. However, due to the difficulty and high cost of acquiring knowledge about avionics equipment, some electronic equipment can only acquire a small amount of knowledge. The knowledge graph constructed based on the existing information will always have less information and weaker correlations (that is, the "edges" shown in the graph are not rich enough). Summary of the Invention

[0004] In order to overcome the shortcomings of the existing technology, the present invention provides a multi-fault diagnostic reasoning method and system based on tensor decomposition. It decomposes the fault mode of each fault phenomenon into multiple fault elements, queries multiple fault causes for each fault element, and vectorizes the entities in the fault knowledge graph through tensor decomposition to obtain a fault vectorized knowledge graph. The fault vectorized knowledge graph can diagnose comprehensive fault causes for the fault phenomenon.

[0005] To achieve the above-mentioned object, the present invention provides a method for multiple fault diagnosis based on tensor decomposition, which comprises the following steps:

[0006] Step 1: Based on expert experience, we sort out the fault modes of system fault phenomena, decompose the fault modes into multiple fault elements, and sort out multiple fault causes based on the fault elements. We construct an initial fault knowledge graph using the fault phenomena, fault elements, and fault causes as entities, and the relationships between the fault phenomena and fault elements, and between the fault elements and fault causes as edges.

[0007] Step 2: Use tensor decomposition to vectorize the entities and edges in the initial fault knowledge graph to obtain a fault vector knowledge graph;

[0008] Step 3: Obtain the fault phenomenon to be detected , calculate the similarity of all entities in the fault vector knowledge graph of the fault phenomenon to be detected, and the similarity of all entities in the vector knowledge graph with the fault phenomenon to be detected The most similar entity All entities directly connected by edges are regarded as a set of one-hop entities connected to the fault phenomenon to be detected, denoted as .

[0009] To achieve the above-mentioned purpose, the present invention also provides a system comprising a storage medium and one or more processors, wherein the storage medium stores a computer program, and the computer program is called by one or more processors to implement the above-mentioned tensor decomposition-based multiple fault diagnosis method.

[0010] Compared with the existing technology, the present invention provides a multi-fault diagnostic reasoning method and system based on tensor decomposition, which has the following beneficial effects: by decomposing the fault mode of each fault phenomenon into multiple fault elements, multiple fault causes are queried for each fault element, and the entities in the fault knowledge graph are vectorized through tensor decomposition to obtain a fault vectorized knowledge graph. The fault vectorized knowledge graph can diagnose comprehensive fault causes for the fault phenomenon. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] Figure 1 This is a flow chart of the tensor decomposition-based fault multiple diagnosis and inference method provided by the present invention. DETAILED DESCRIPTION

[0012] The technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0013] Figure 1 This is a flow chart of the fault multiple diagnosis and deduction method based on tensor decomposition provided by the present invention, as shown in FIG. Figure 1 As shown, the tensor decomposition-based fault multiple diagnosis method provided by the present invention includes the following steps:

[0014] Step 1: Based on expert experience, we sort out the fault modes of system fault phenomena, decompose the fault modes into multiple fault elements, and sort out multiple fault causes based on the fault elements. We construct an initial fault knowledge graph using the fault phenomena, fault elements, and fault causes as entities, and the relationships between the fault phenomena and fault elements, and between the fault elements and fault causes as edges.

[0015] Step 2: Use tensor decomposition to vectorize the entities and edges in the initial fault knowledge graph to obtain a fault vector knowledge graph;

[0016] Step 3: Obtain the fault phenomenon to be detected , calculate the similarity of all entities in the fault vector knowledge graph of the fault phenomenon to be detected, and the similarity of all entities in the vector knowledge graph with the fault phenomenon to be detected The most similar entity The entities directly connected by the edge are regarded as the one-hop entity set connected to the fault phenomenon to be detected, which is recorded as , M is a positive integer.

[0017] The tensor decomposition-based fault multiple diagnosis and inference method provided by the present invention further includes the following steps:

[0018] Step 4: Query the fault vector knowledge graph for the one-hop entity set Each entity in The entities directly connected by the edge minus the return flow entity is the two-hop entity set of the fault phenomenon to be detected. ,

[0019] Where, Representation and Entity The entity set obtained by subtracting the backflow entities from the entities directly connected by the edges.

[0020] By analogy, query the fault vector knowledge graph with n-1 hop entity set E n Each entity in the ensemble is directly connected to the entities in the backflow by edges, and the entities in the backflow are reduced to form the n-hop entity set of the fault phenomenon to be detected. After multiple inferences, the fault vectorization knowledge graph can diagnose the comprehensive fault cause for the fault phenomenon.

[0021] In the present invention, vectorizing entities and edges in the initial fault knowledge graph using tensor decomposition to obtain a fault vector knowledge graph further includes:

[0022] S1-1: The two entities and relations in the initial fault knowledge graph constitute a fault triple, and their vector triples are , where h represents the vector of the head entity and r represents the vector of the relationship. A vector representing the tail entity;

[0023] S1-2: Extract all entities to form entity codes, extract all relationships in a relationship to form relationship codes, the size of the entity set is , the relationship set size is ;

[0024] S1-3: Constructing tensors ,if If true, set Otherwise it is 0; then the tensor To break it down: , where is the embedding matrix of all entities, mapping the vectors of all entities to the entity space ; is the embedding matrix of all relations, mapping the vector of relations to the relation space ; represents tensor modular product;

[0025] S1-4: From the embedding matrix Take any two rows as the head entity embedding vector and tail entity embedding vector ; From the relation embedding matrix Take a row as the relation embedding vector ;

[0026] S1-5: Traverse the vector triples of fault triples in the initial fault knowledge graph Set D, calculate the vector triple according to the following formula The forward loss function :

[0027] ;

[0028] S1-6: Construct negative samples by randomly replacing vector triplets Generate a fake triple vector from the vector of the head entity or tail entity in , , ;

[0029] S1-7: Traverse the false triple vectors in the initial fault knowledge graph gather , calculate the pseudo triplet vector according to the following formula Negative loss function :

[0030] ,

[0031] In the formula, in the formula, Embedding vector for the head entity of the fake triple; is the tail body embedding vector of the false triple;

[0032] S1-8: Use the following formula to calculate the total loss L:

[0033] ,

[0034] Where, Indicates taking the positive part; D is the set of real triples, is the set of negative triples, is a hyperparameter;

[0035] S1-9: Determine whether the total loss L is the minimum. If the total loss L is the minimum, use the vector value of the test fault triplet Verification is performed and qualified. The entities and relationships in the initial fault knowledge graph are assigned fixed vectors to obtain the optimized core tensor. , entity embedding matrix and the relation embedding matrix , and then obtain the initial fault vector knowledge graph; if the total loss L does not reach the minimum, the gradient descent method is used to update the vector h of the head entity, the vector t of the tail entity, and the vector value r of the relationship, and the updated vector values of the head entity, tail entity, and relationship replace the vector values before the update, and then return to step S1-4.

[0036] Optionally, the vectors of fault triples and false triples in the initial fault knowledge graph are perturbed, and the perturbation loss is calculated using the following formula: ,

[0037] Where, is the disturbance amount, and judge the total loss Is it the minimum? If the total loss reaches the minimum, the test fault triple is used for verification. If the verification is qualified, the entities and relationships in the initial fault knowledge graph are assigned fixed vectors, and the optimized entity embedding matrix, relationship embedding matrix and normal vector matrix are obtained, and then the initial fault vector knowledge graph is obtained; if the total loss L does not reach the minimum, the updated values of the head entity vector h, tail entity vector t and relationship vector r are replaced with the updated values before the update, and then return to step S1-4.

[0038] Through the above technical solution, the present invention quantifies all entities and relationships in the initial fault knowledge graph, and assigns a fixed vector to each entity and relationship in the initial fault knowledge graph, thereby laying the foundation for diagnosing comprehensive fault causes for fault phenomena and enhancing the applicability of the quantified knowledge graph.

[0039] In the present invention, vectorizing entities and edges in the initial fault knowledge graph using tensor decomposition to obtain a fault vector knowledge graph further includes:

[0040] S1-10: Pick any two entities in the initial fault vector knowledge graph and , ; Calculate their embedding vectors respectively as and ; Choose any relationship among the relationships , calculate its embedding vector , which forms a fault embedding vector triplet , calculate the fault embedding vector triplet according to the following formula: Tensor:

[0041] ,

[0042] Where, , represents tensor modular product;

[0043] S1-11: Determine the tensor Is it close to 1? If the tensor , For the minimum setting value, the entity and entities Connected, the connected edges are ; If the tensor ,entity and entities Not connected;

[0044] S1-12: Repeat steps S1-10 and S1-11 to traverse all entities in the initial fault vector knowledge graph to obtain a first fault vector knowledge graph.

[0045] The present invention uses the above technical solution to make the connection of entities in the initial fault vector knowledge graph more comprehensive.

[0046] In the present invention, vectorizing entities and edges in the initial fault knowledge graph using tensor decomposition to obtain a fault vector knowledge graph further includes the following steps:

[0047] S1-13: Get new fault symptoms , calculate the new fault phenomenon Similarity with all entities e in the knowledge graph of the first fault vector , if the similarity If it is greater than or equal to the threshold, the fault phenomenon As an entity, and connected to the entity connected to entity e through an edge, the vector of entity e is adjusted according to the similarity as the fault phenomenon The vector of the edge connecting entity e and its connected entities is adjusted according to the similarity as the connection failure phenomenon and the edge vector of the entity connected to entity e; if the similarity If the fault frequency is less than a threshold, a new fault mode for the new fault phenomenon is sorted out based on expert experience, the new fault mode is decomposed into multiple new fault elements, and multiple new fault causes are sorted out for the new fault elements; the new fault phenomenon, the new fault element and the new fault cause are taken as entities, and the relationship between the new fault phenomenon and the new fault element, and the relationship between the new fault element and the new fault cause are taken as edges to construct a new initial fault knowledge graph, and then tensor decomposition is used to vectorize the entities and edges of the new initial fault knowledge graph to obtain a second fault vector knowledge graph, and the first fault vector knowledge graph and the second fault vector knowledge graph are fused to obtain a fault vector knowledge graph.

[0048] In the present invention, vectorizing entities and edges in the initial fault knowledge graph using tensor decomposition to obtain a fault vector knowledge graph further includes the following steps:

[0049] Step 1-14: Generate a mapping table by deriving the correspondence between entities and vectors, and relations and vectors from the fault vector knowledge graph.

[0050] In the present invention, fusing the first fault vector knowledge graph and the second fault vector knowledge graph to obtain the fault vector knowledge graph includes the following steps:

[0051] S1-15: embedding matrix of all entities in the knowledge graph of the first fault vector And the embedding matrix of all entities in the second fault vector knowledge graph Splice them together and embed the matrix of all relations of the first fault vector knowledge graph Embedding matrix of all relations with the first fault vector knowledge graph Phase splicing;

[0052] S1-16: Select any entity from the first fault vector knowledge graph , select any entity from the second fault vector knowledge graph ; Calculate their embedding vectors respectively as and ,in, , ;

[0053] from Pick a relationship , calculate its embedding vector , which forms a fault embedding vector triplet , calculate the fault embedding vector triplet according to the following formula: Tensor:

[0054] ,

[0055] Where, , represents tensor modular product;

[0056] S1-17: Judging tensors Is it close to 1? If the tensor , For the minimum setting value, the entity and entities Connected, the connected edges are ; If the tensor ,entity and entities Not connected;

[0057] S1-18: Repeat steps S1-16 and S1-17 to traverse all entities in the initial fault vector knowledge graph to obtain a fault vector knowledge graph.

[0058] Through the above technical solution, the present invention can fuse multiple fault vector knowledge graphs greater than or equal to 2 without having to re-quantize the spliced fault knowledge graphs.

[0059] The present invention expands the fault-based knowledge graph through the above technical solution, making the fault phenomena, fault elements and fault causes more comprehensive, and facilitating more accurate fault diagnosis.

[0060] In the present invention, the mapping table records the correspondence between entities and vectors, and relations and vectors in the fault vector knowledge graph.

[0061] To achieve the above-mentioned purpose, the present invention also provides a system comprising a storage medium and one or more processors, wherein the storage medium stores a computer program, and the computer program is called by one or more processors to implement the above-mentioned tensor decomposition-based multiple fault diagnosis method.

[0062] To achieve the above-mentioned object of the invention, the present invention also provides a computer program product, which uses computer language to compile the above-mentioned tensor decomposition-based fault multiple diagnosis and inference method into a computer program called and executed by one or more processors.

[0063] The preferred embodiments of the present invention disclosed above are only used to help illustrate the present invention. The preferred embodiments do not describe all the details in detail, nor do they limit the invention to only specific implementation methods. Obviously, many modifications and changes can be made according to the contents of this specification. This specification selects and specifically describes these embodiments in order to better explain the principles and practical applications of the present invention, so that those skilled in the art can better understand and utilize the present invention. The present invention is only limited by the claims and their full scope and equivalents.

Claims

1. A fault multiple diagnosis reasoning method based on tensor decomposition, characterized in that: The steps include: Step 1: Based on expert experience, we sort out the fault modes for system fault phenomena, decompose the fault modes into multiple fault elements, and sort out multiple fault causes for each fault element. We construct an initial fault knowledge graph using the fault phenomena, fault elements, and fault causes as entities, and the relationships between the fault phenomena and fault elements, and between the fault elements and fault causes as edges. Step 2: Use tensor decomposition to vectorize the entities and edges in the initial fault knowledge graph to obtain a fault vector knowledge graph, including: and random replacement vector triplets The pseudo triplet vector generated by the vector of the head entity or tail entity in Perform the perturbation and calculate the perturbation loss by the following formula: , where h represents the vector of the head entity, r represents the vector of the relationship, and t represents the vector of the tail entity; D is the set of real triples, is the set of negative triples, is the first hyperparameter, and determine the total loss Is it the smallest? If so, use the vector in the test fault triple to verify. If qualified, the entities and relationships in the initial fault knowledge graph are assigned fixed vectors, where L is: , where Triplet vector The forward loss function of is a false triple vector Negative loss function; It means taking the positive part; is the second hyperparameter; Step 3: Obtain the fault phenomenon to be detected , calculate the similarity of all entities in the fault vector knowledge graph of the fault phenomenon to be detected, and the similarity of all entities in the vector knowledge graph with the fault phenomenon to be detected The most similar entity All entities directly connected by edges are regarded as a set of one-hop entities connected to the fault phenomenon to be detected, denoted as .

2. The fault multiple diagnosis reasoning method based on tensor decomposition according to claim 1 is characterized in that: Also includes step 4: Query the fault vector knowledge graph and the one-hop entity set Each entity in The entities directly connected by edges minus the return flow entities are the two-hop entity set of the fault phenomenon to be detected: ， Where, Representation and Entity The set of entities obtained by subtracting the backflow entities from the entities directly connected by the edge.

3. The fault multiple diagnosis reasoning method based on tensor decomposition according to claim 1 is characterized in that: The fault vector knowledge graph is obtained by vectorizing the entities and edges in the initial fault knowledge graph using tensor decomposition, including: S1-1: The two entities and relations in the initial fault knowledge graph constitute a fault triple, and their vector triples are ; S1-2: Extract all entities to form entity codes, extract all relationships in a relationship to form relationship codes, the size of the entity set is , the relationship set size is ; S1-3: Constructing tensors ,if If true, set Otherwise it is 0; then the tensor To break it down: , where is the embedding matrix of all entities, mapping the vectors of all entities to the entity space ; is the embedding matrix of all relations, mapping the vector of relations to the relation space ; represents tensor modular product; represents the kernel tensor; S1-4: From the embedding matrix Take any two rows as the head entity embedding vector and tail entity embedding vector ; From the relation embedding matrix Take a row as the relation embedding vector ; S1-5: Traverse the vector triples of fault triples in the initial fault knowledge graph Set D, calculate the vector triple according to the following formula The forward loss function : 。 4. The fault multiple diagnosis reasoning method based on tensor decomposition according to claim 3 is characterized in that: The fault vector knowledge graph obtained by vectorizing the entities and edges in the initial fault knowledge graph using tensor decomposition also includes: S1-6: Construct negative samples by randomly replacing vector triplets Generate a fake triple vector from the vector of the head entity or tail entity in , , ; S1-7: Traverse the false triple vectors in the initial fault knowledge graph gather , calculate the pseudo triplet vector according to the following formula Negative loss function : ， Where, Embedding vector for fake triplet head entity; Embedding vector for the fake triple tail entity; S1-8: Calculate the total loss .

5. The fault multiple diagnosis reasoning method based on tensor decomposition according to claim 4 is characterized in that: The fault vector knowledge graph is obtained by vectorizing the entities and edges in the initial fault knowledge graph using tensor decomposition. Specifically, it includes: S1-9: Determine the total loss Is it the smallest, if the total loss To achieve the minimum, use the vector value of the test fault triple Verification is performed and qualified. The entities and relationships in the initial fault knowledge graph are assigned fixed vectors to obtain the optimized core tensor. , entity embedding matrix and the relation embedding matrix , and then obtain the initial fault vector knowledge graph.

6. The fault multiple diagnosis reasoning method based on tensor decomposition according to claim 5 is characterized in that: The fault vector knowledge graph obtained by vectorizing the entities and edges in the initial fault knowledge graph using tensor decomposition also includes: S1-10: Pick any two entities in the initial fault vector knowledge graph and , ; Calculate their embedding vectors respectively as and ; Choose any relationship among the relationships , calculate its embedding vector , which forms a fault embedding vector triplet , calculate the fault embedding vector triplet according to the following formula Tensor: ， Where, , represents tensor modular product; S1-11: Determine the tensor Is it close to 1? If the tensor , For the minimum setting value, the entity and entities Connected, the connected edges are ; If the tensor ,entity and entities Not connected; S1-12: Repeat steps S1-10 and S1-11 to traverse all entities in the initial fault vector knowledge graph to obtain a first fault vector knowledge graph.

7. The fault multiple diagnosis reasoning method based on tensor decomposition according to claim 6 is characterized in that: Using tensor decomposition to vectorize the entities and edges in the initial fault knowledge graph to obtain a fault vector knowledge graph also includes the following steps: S1-13: Get new fault symptoms , calculate the new fault phenomenon Similarity with all entities e in the knowledge graph of the first fault vector , if the similarity If it is greater than or equal to the threshold, the new fault phenomenon As an entity, and connected to the entity connected to entity e through an edge, the vector of entity e is adjusted according to the similarity as a new fault phenomenon The vector of the edge connecting entity e and its connected entities is adjusted according to the similarity as the new fault phenomenon of the connection and the edge vector of the entity connected to entity e; if the similarity Less than the threshold, based on expert experience to sort out the new fault phenomenon The new fault mode is decomposed into multiple new fault elements, and multiple new fault causes are sorted out for the new fault elements; the new fault phenomenon is decomposed into multiple new fault elements. , new fault elements and new fault causes as entities, new fault phenomena A new initial fault knowledge graph is constructed with the relationship between the new fault element and the new fault cause as edges, and then the entities and edges of the new initial fault knowledge graph are vectorized by tensor decomposition to obtain a second fault vector knowledge graph. The first fault vector knowledge graph and the second fault vector knowledge graph are fused to obtain a fault vector knowledge graph.

8. The fault multiple diagnosis reasoning method based on tensor decomposition according to claim 7 is characterized in that: The following steps are also included: Step 1-14: Generate a mapping table by deriving the correspondence between entities and vectors, and relations and vectors from the fault vector knowledge graph.

9. A system, characterized in that: The method comprises a storage medium and one or more processors, wherein the storage medium stores a computer program, and the computer program is called by the one or more processors to implement the tensor decomposition-based fault multiple diagnosis reasoning method according to any one of claims 1 to 8.

Images