Avionics equipment fault diagnosis reasoning method and system based on graph neural network

Abstract

The invention discloses an avionics equipment fault diagnosis reasoning method and system based on a graph neural network, and belongs to the technical field of fault prediction. The method comprises the following steps: step 1, constructing an initial fault knowledge graph according to expert experience; 2, vectorizing relationships and edges in the initial fault knowledge graph by using a graph neural network to obtain a fault vector knowledge graph; 3, obtaining a fault phenomenon to be detected, and querying a vector value from the mapping table; and 4, according to the vector value of the to-be-detected fault phenomenon, calculating the similarity between the to-be-detected fault phenomenon and the entities in the fault vector knowledge graph, and regarding the entity which is directly connected with the entity in the fault vector knowledge graph through the relationship and has the highest similarity with the to-be-detected fault phenomenon as the entity which is connected with the to-be-detected fault phenomenon through the relationship. According to the invention, comprehensive fault reasons for fault phenomena can be diagnosed.

Description

Technical Field

[0001] The present invention relates to an avionics equipment fault diagnosis reasoning method and system based on a graph neural network, belonging to the technical field of fault prediction and health management. Background Art

[0002] In the field of aerospace, with the continuous improvement of equipment functions and effectiveness, the structure and function of avionics equipment have become more and more complex, and the difficulty of maintenance and repair of avionics equipment has also increased significantly. Therefore, in order to ensure the normal operation of aviation equipment and improve the reliability of aviation equipment, it has become one of the important research topics to locate and solve the faults in a timely and accurate manner and to predict the faults in time before the faults occur in order to ensure the normal operation of aviation equipment and improve the reliability of aviation equipment.

[0003] Combining faults with knowledge graph technology and creatively constructing fault knowledge graphs is actually using the advantages of artificial intelligence technology to overcome the limitations of traditional fault analysis. This integration is not only an innovation in fault analysis methods, but also an innovative attempt at knowledge management and intelligent decision-making. The fault knowledge graph integrates multiple data sources such as existing fault information, expert knowledge, and equipment information, and presents them visually in the form of a graph. Through the structured method of knowledge graphs, knowledge graphs can assist operators in quickly and accurately retrieving and obtaining relevant information, and can discover potential connections and common features between different fault cases. Because the existing information is incomplete and insufficient, the relationship between two entities may be missing or ignored in the construction of the knowledge graph. Therefore, the use of knowledge reasoning is crucial in the knowledge graph. Through knowledge reasoning, the existing knowledge graph relationship can be enriched, making the process of establishing the 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 (i.e., the "edges" shown in the graph are not rich enough). Summary of the invention

[0004] In order to overcome the shortcomings of the prior art, the present invention provides an avionics equipment fault diagnosis reasoning method and system based on graph neural network, which decomposes the fault mode of each fault phenomenon into multiple fault elements, and queries multiple fault causes for each fault element, so as to diagnose comprehensive fault causes for the fault phenomenon.

[0005] To achieve the above-mentioned purpose, the present invention provides an avionics equipment fault diagnosis reasoning method based on graph neural network, which comprises the following steps: Step 1: Based on expert experience, sort out multiple fault elements for avionics equipment fault phenomena, sort out the fault causes for each fault element, take fault phenomena, fault elements and fault causes as entities, and use the relationships between fault phenomena and fault elements, and between fault elements and fault causes as edges to construct an initial fault knowledge graph; Step 2: Use graph neural network to vectorize the entities and edges in the initial fault knowledge graph to obtain the fault vector knowledge graph; Step 3: Obtain the fault phenomenon to be detected and query the vector value from the mapping table; Step 4: According to the vector value of the fault phenomenon to be detected, the similarity between the fault phenomenon to be detected and the entities in the fault vector knowledge graph is calculated. The entity set directly connected to the entity in the fault vector knowledge graph with the highest similarity to the fault phenomenon to be detected through a relationship is regarded as the one-hop entity set connected to the fault phenomenon to be detected through a relationship, and is recorded as .

[0006] To achieve the above-mentioned purpose of the invention, the present invention also provides a system, which includes 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 graph neural network-based avionics equipment fault diagnosis reasoning method.

[0007] Compared with the prior art, the graph neural network-based avionics equipment fault diagnosis reasoning method and system provided by the present invention decomposes the fault mode of each fault phenomenon into multiple fault elements, and queries multiple fault causes for each fault element, thereby being able to diagnose comprehensive fault causes for the fault phenomenon. BRIEF DESCRIPTION OF THE DRAWINGS

[0008] Figure 1 It is a flow chart of the avionics equipment fault diagnosis reasoning method based on graph neural network provided by the present invention. DETAILED DESCRIPTION

[0009] 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.

[0010] Figure 1 is a flow chart of the avionics equipment fault diagnosis reasoning method based on graph neural network provided by the present invention, such as Figure 1 As shown, the avionics equipment fault diagnosis reasoning method based on graph neural network provided by the present invention comprises the following steps: Step 1: Sort out the avionics equipment failure phenomena based on expert experience Fault element , sort out the fault elements Cause of failure , the fault phenomenon , Fault element and cause of failure As an entity, the fault phenomenon and fault element relationship, fault element and cause of failure The relationships of are used as edges to construct the initial fault knowledge graph; Step 2: Use graph neural network to vectorize the entities and edges in the initial fault knowledge graph to obtain the fault vector knowledge graph; Step 3: Obtain the fault phenomenon to be detected and query the vector value from the mapping table; Step 4: According to the vector value of the fault phenomenon to be detected, the similarity between the fault phenomenon to be detected and the entities in the fault vector knowledge graph is calculated. The entity set directly connected to the entity in the fault vector knowledge graph with the highest similarity to the fault phenomenon to be detected through a relationship is regarded as the one-hop entity set connected to the fault phenomenon to be detected through a relationship, and is recorded as , I is a positive integer.

[0011] The avionics equipment fault diagnosis reasoning method based on graph neural network provided by the present invention also includes the following steps: Step 5: 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 used as the two-hop entity set of the fault phenomenon to be detected. , In the formula, Representation and Entity The entity set obtained by subtracting the backflow entities from the entities directly connected by the edges.

[0012] By analogy, query the fault vector knowledge graph with entity set E that is 1 hop away from a a Each entity in the is directly connected to the entities through the edge, and the entities in the reflux are cut as the a-hop entity set of the fault phenomenon to be detected. After multiple reasonings, the comprehensive fault causes for the fault phenomenon can be diagnosed through the quantified knowledge graph of the graph neural network.

[0013] In the present invention, according to the vector value of the fault phenomenon to be detected , calculating the similarity between the fault phenomenon to be detected and the entity in the fault vector knowledge graph specifically includes: S1-1: Calculate the vector of the fault phenomenon to be detected The embedding matrix after the k+1th layer diffusion ; S1-2: Obtain the entity with the highest similarity to the fault phenomenon to be detected in the fault vector knowledge graph through the following formula: , In the formula, is the two-norm; A vector representing any entity in the fault vector knowledge graph The k+1-layer diffusion embedding matrix of ; D is the set of real vector triplets.

[0014] In the fault reasoning method of the graph neural network provided by the present invention, the entities and edges in the initial fault knowledge graph are vectorized by using the graph neural network to obtain the initial fault vector knowledge graph, which specifically includes: S2-1: The two entities and relations in the initial fault knowledge graph constitute a fault triple, and its fault vector triple is , where h represents the head entity vector, r represents the relationship vector, and t represents the tail entity vector value; S2-2: Extract all head entities and tail entities of the initial fault knowledge graph, extract all relations of the initial fault knowledge graph, and the size of the entity set is , the size of the relationship set is ; S2-3: Randomly initialize the embedding vector of the entity to obtain the entity embedding matrix H; randomly initialize the embedding vector of the relationship to obtain the relationship embedding matrix R; at the same time, according to the fault vector triple Set, get the adjacency matrix A; for each relationship vector r, extract the corresponding subgraph adjacency matrix , so that Only include edges related to vector r; randomly initialize the change matrix of relationship vector r ; S2-4: For the relation vector r, calculate the message , further embedding the message and relation vector of the relation vector Combination ; Then aggregate all relationships: , and then update the entity embedding vector to obtain the k+1th layer embedding matrix of the relationship vector r: , is the activation function; at the same time, the degree matrix of each entity is obtained from the adjacency matrix A ; S2-5: Calculate the normalized diffusion matrix: , further diffusion is performed on the entity nodes to obtain the diffused embedding matrix: ; S2-6: Traverse the fault vector triples in the initial fault knowledge graph Set, calculate the forward loss function according to the following formula : , where represents the diffused embedding matrix of the head entity vector h at the k+1th layer, Represents the diffusion embedding matrix of the k+1th layer of the tail entity vector t.

[0015] In the present invention, the entities and edges in the initial fault knowledge graph are vectorized by using a graph neural network to obtain a fault vector knowledge graph including: S2-7: Construct negative samples by randomly replacing the fault vector triples Generate a false fault vector triplet from the head or tail entity vector in , , ; S2-8: Traverse the false fault vector triples in the initial fault knowledge graph Set, calculate the negative loss function according to the following formula : , where Representation vector The k+1th layer diffusion embedding matrix; Representation vector The embedding matrix after the k+1th layer diffusion; S2-9: Use the following formula to calculate the total loss L: , where represents the positive part; D is the set of real triples, is the set of negative triples; S2-10: Use gradient descent method to update the vector values ​​of head entity, tail entity and relationship.

[0016] In the present invention, using a graph neural network to vectorize entities and edges in an initial fault knowledge graph to obtain a fault vector knowledge graph also includes: 2-11: Determine whether the total loss L is the minimum. If the total loss L is the minimum, use the test fault vector triplet Verification is performed and the entities and relationships in the initial fault knowledge graph are assigned fixed vectors to obtain the optimized entity embedding matrix. , optimized relation embedding matrix And the optimized change matrix , and then obtain the initial fault vector knowledge graph; if the total loss L does not reach the minimum, the updated vector values ​​of the head entity h, the tail entity t and the relationship r are replaced by the updated vector values, and then return to step S2-4.

[0017] The present invention quantifies all entities and relationships in the initial fault knowledge graph through the above technical solution, and assigns a fixed vector to each entity and relationship in the initial fault knowledge graph, thereby laying a foundation for diagnosing comprehensive fault causes for fault phenomena.

[0018] Optionally, for the fault vector triplet Generate a false fault vector triplet from the head or tail entity vector in Perform disturbance and calculate the disturbance loss by the following formula: , In the formula, is the perturbation quantity, T represents the transpose; the gradient descent method is used to update the values ​​of the head entity vector h, the tail entity vector t and the relationship vector r, and the total loss is determined Is it the minimum? If the total loss is minimized, the test fault triples are used for verification. If the verification is qualified, the entities and relations in the initial fault knowledge graph are assigned fixed vectors to obtain the optimized entity embedding matrix. , optimized relation embedding matrix And the optimized change matrix , and then obtain the initial fault vector knowledge graph; if the total loss L does not reach the minimum, the updated vector values ​​of the head entity h, the tail entity t and the relationship r are replaced by the updated vector values, and then return to step S2-4.

[0019] The present invention can make the application scope of the fault vector knowledge graph wider through the above method.

[0020] The fault vector knowledge graph obtained by vectorizing the entities and edges in the initial fault knowledge graph using the graph neural network also includes: S2-12: Get the vector of another entity in the initial fault vector knowledge graph , the vector is calculated by the following formula and vector The second norm of the difference of the k+1th layer embedding vector: , In the formula, Representation vector The embedding matrix after the k+1th layer diffusion; Representation vector The embedding matrix after the k+1th layer diffusion; S2-13: Acquisition less than the set value, and compare the other entity with All entities smaller than the set value are connected, and the relationship vector between them is calculated; S2-14: Repeat steps S2-12 and S2-13 to traverse all entities in the initial fault vector knowledge graph to obtain the fault vector knowledge graph.

[0021] The present invention uses the above technical solution to make the connection of entities in the initial fault vector knowledge graph more comprehensive.

[0022] In the present invention, using a graph neural network to vectorize entities and edges in an initial fault knowledge graph to obtain a fault vector knowledge graph also includes:

[0023] S2-15: 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 Less than a threshold, based on expert experience, a new fault mode for the new fault phenomenon is sorted out, 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 the graph neural network 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.

[0024] In the present invention, vectorizing entities and edges in the initial fault knowledge graph using a graph neural network to obtain a fault vector knowledge graph also includes the following steps: S2-16: Derive the correspondence between entities, relations and vectors in the fault vector knowledge graph to obtain a mapping table.

[0025] 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 process: S2-17: Get any entity in the first fault vector knowledge graph , whose vector is , get any entity from the second fault vector knowledge graph , whose vector is The vector is calculated by Vectors and vectors The second norm of the difference of the embedding vector after the k+1th layer diffusion: , where Representation vector The embedding matrix after diffusion; Representation vector The embedding matrix after diffusion; S2-18: Acquisition All values ​​less than the set value , and and All entities smaller than the set value Connect them and calculate the relationship vector between them; S2-19: Repeat steps S2-17 and S2-18 to traverse all entities in the initial fault vector knowledge graph to obtain the fault vector knowledge graph.

[0026] The present invention can fuse multiple fault vector knowledge graphs greater than or equal to 2 through the above technical solution without having to re-quantize the spliced ​​fault knowledge graphs.

[0027] The present invention expands the fault-based knowledge graph through the above technical solution, making the fault phenomenon, fault elements and fault causes more comprehensive, which facilitates more comprehensive fault causes to be obtained during fault diagnosis.

[0028] To achieve the above-mentioned purpose of the invention, the present invention also provides a system, which includes 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 graph neural network-based avionics equipment fault diagnosis reasoning method.

[0029] In order to achieve the above-mentioned purpose of the invention, the present invention also provides a computer program product, which uses computer language to compile the above-mentioned avionics equipment fault diagnosis reasoning method based on graph neural network into a computer program called and executed by one or more processors.

[0030] The preferred embodiments of the present invention disclosed above are only used to help explain 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 technicians in the relevant technical field can well understand and use the present invention. The present invention is only limited by the claims and their full scope and equivalents.

Claims

1. A method for fault diagnosis and reasoning of avionics equipment based on graph neural network, characterized in that: The steps include: Step 1: Based on expert experience, sort out multiple fault elements for avionics equipment fault phenomena, sort out the fault causes for each fault element, take fault phenomena, fault elements and fault causes as entities, and use the relationships between fault phenomena and fault elements, and between fault elements and fault causes as edges to construct an initial fault knowledge graph; Step 2: Use graph neural network to vectorize the entities and edges in the initial fault knowledge graph to obtain the fault vector knowledge graph; Step 3: Obtain the fault phenomenon to be detected and query the vector value from the mapping table; Step 4: According to the vector value of the fault phenomenon to be detected, the similarity between the fault phenomenon to be detected and the entities in the fault vector knowledge graph is calculated. The entity set directly connected to the entity in the fault vector knowledge graph with the highest similarity to the fault phenomenon to be detected through a relationship is regarded as the one-hop entity set connected to the fault phenomenon to be detected through a relationship, and is recorded as .

2. The avionics equipment fault diagnosis reasoning method based on graph neural network according to claim 1 is characterized in that: The following steps are also included: Step 5: 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 used as the two-hop entity set of the fault phenomenon to be detected. , where Representation and Entity The entity set obtained by subtracting the backflow entities from the entities directly connected by the edges.

3. The avionics equipment fault diagnosis reasoning method based on graph neural network according to claim 2 is characterized in that: According to the vector value of the fault phenomenon to be detected, calculating the similarity between the fault phenomenon to be detected and the entity in the fault vector knowledge graph specifically includes: S1-1: Calculate the vector of the fault phenomenon to be detected The embedding matrix after the k+1th layer diffusion ; S1-2: Obtain the entity with the highest similarity to the fault phenomenon to be detected in the fault vector knowledge graph through the following formula: , In the formula, is the two-norm; A vector representing any entity in the fault vector knowledge graph The k+1-layer diffusion embedding matrix of ; D is the set of real vector triplets.

4. The avionics equipment fault diagnosis reasoning method based on graph neural network according to claim 1 is characterized in that: The fault vector knowledge graph obtained by vectorizing the entities and edges in the initial fault knowledge graph using graph neural network includes: S2-1: The two entities and relations in the initial fault knowledge graph constitute a fault triple, and its fault vector triple is , where h represents the head entity vector, r represents the relationship vector, and t represents the tail entity vector value; S2-2: Extract all head entities and tail entities of the initial fault knowledge graph, extract all relations of the initial fault knowledge graph, and the size of the entity set is , the size of the relationship set is ; S2-3: Randomly initialize the embedding vector of the entity to obtain the entity embedding matrix H; randomly initialize the embedding vector of the relationship to obtain the relationship embedding matrix R; at the same time, according to the fault vector triple Set, get the adjacency matrix A; according to the relationship vector r, extract the corresponding subgraph adjacency matrix , so that Only include edges related to vector r; randomly initialize the change matrix of relationship vector r ; S2-4: For the relation vector r, calculate the message , further embedding the message and relation vector of the relation vector Combination ; Then aggregate all relationships: , and then update the entity embedding vector to obtain the k+1th layer embedding matrix of the relationship vector r: , is the activation function; at the same time, the degree matrix of each entity is obtained from the adjacency matrix A ; S2-5: Calculate the normalized diffusion matrix: , further diffusion is performed on the entity nodes to obtain the diffused embedding matrix: ; S2-6: Traverse all fault vector triplets in the initial fault knowledge graph Set, calculate the forward loss function according to the following formula : , where represents the diffused embedding matrix of the head entity vector h at the k+1th layer, Represents the diffusion embedding matrix of the k+1th layer of the tail entity vector t.

5. The avionics equipment fault diagnosis reasoning method based on graph neural network according to claim 4 is characterized in that: The fault vector knowledge graph obtained by vectorizing the entities and edges in the initial fault knowledge graph using the graph neural network also includes: S2-7: Construct negative samples by randomly replacing the fault vector triples Generate a false fault vector triplet from the head or tail entity vector in , , ; S2-8: Traverse the fault vector triples in the initial fault knowledge graph Set, calculate the negative loss function according to the following formula : , where Representation vector The volume embedding matrix after the k+1th layer diffusion; Representation vector The entity embedding matrix after the k+1th layer diffusion S2-9: Use the following formula to calculate the total loss L: , where represents the positive part; D is the set of real triples, is the set of negative triples; S2-10: Use gradient descent method to update the vector values ​​of head entity, tail entity and relationship.

6. The avionics equipment fault diagnosis reasoning method based on graph neural network 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 the graph neural network also includes: 2-11: Determine whether the total loss L is the minimum. If the total loss L is the minimum, use the test fault vector triplet Verification is performed and the entities and relationships in the initial fault knowledge graph are assigned fixed vectors to obtain the optimized entity embedding matrix. , optimized relation embedding matrix And the optimized change matrix , and then obtain the initial fault vector knowledge graph.

7. The avionics equipment fault diagnosis reasoning method based on graph neural network according to claim 6 is characterized in that: The fault vector knowledge graph obtained by vectorizing the entities and edges in the initial fault knowledge graph using the graph neural network also includes: S2-12: Obtaining the vector of another entity in the initial fault vector knowledge graph , calculate the vector by the following formula and vector The second norm of the difference of the k+1th layer embedding vector: , In the formula, Representation vector The embedding matrix after the k+1th layer diffusion; Representation vector The embedding matrix after the k+1th layer diffusion; S2-13: Acquisition less than the set value, and compare the other entity with All entities smaller than the set value are connected, and the relationship vector between them is calculated; S2-14: Repeat steps S2-12 and S2-13 to traverse all entities in the initial fault vector knowledge graph to obtain the fault vector knowledge graph.

8. The avionics equipment fault diagnosis reasoning method based on graph neural network according to claim 7 is characterized in that: The fault vector knowledge graph obtained by vectorizing the entities and edges in the initial fault knowledge graph using the graph neural network also includes: S2-15: 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 Less than a threshold, based on expert experience, a new fault mode for the new fault phenomenon is sorted out, 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 the graph neural network 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.

9. The avionics equipment fault diagnosis reasoning method based on graph neural network according to claim 8 is characterized in that: Using the graph neural network to vectorize the entities and edges in the initial fault knowledge graph to obtain the fault vector knowledge graph also includes the following steps: S2-16: Derive the correspondence between entities, relations and vectors in the fault vector knowledge graph to obtain a mapping table.

10. An avionics equipment fault diagnosis reasoning system based on graph neural network, characterized in that: It comprises 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 avionics equipment fault diagnosis reasoning method based on graph neural network as described in any one of claims 1-9.

Images