Electromagnetic compatibility fault prediction method based on knowledge graph

Abstract

The invention discloses an electromagnetic compatibility fault prediction method based on a knowledge graph, and relates to the technical field of electromagnetic compatibility fault diagnosis and artificial intelligence, the electromagnetic compatibility fault knowledge graph is constructed through multi-source heterogeneous data, the structured fusion of the data is realized, nodes and relationships with physical significance are provided for a Bayesian network, and the fault diagnosis accuracy is improved. The target Bayesian network has interpretability and can trace the fault source, ALS-PSO is adopted to optimize the target Bayesian network, and the training precision of the target Bayesian network can be effectively improved, so that the trained target Bayesian network can accurately realize prediction of the electromagnetic compatibility fault.

Description

Technical Field

[0001] This application relates to the fields of electromagnetic compatibility fault diagnosis and artificial intelligence technology, and more specifically, to an electromagnetic compatibility fault prediction method based on knowledge graphs. Background Technology

[0002] With the increasing complexity and high integration of electronic devices, electromagnetic compatibility (EMC) issues have become a key factor affecting equipment reliability. Traditional EMC fault prediction mainly relies on expert experience or a single physical model. However, EMC faults are often characterized by nonlinearity, strong coupling, and randomness, making them difficult to accurately describe using simple mathematical models.

[0003] In recent years, data-driven fault prediction methods have gradually emerged. Bayesian networks, as a probabilistic graphical model for handling uncertainties, have been widely used in the field of fault diagnosis. However, existing Bayesian network-based fault prediction methods still suffer from the following technical bottlenecks: Network structure construction is difficult and inaccurate: Traditional Bayesian network structure learning is often based on pure statistical methods (such as K2 algorithm and BIC score), ignoring domain knowledge. This results in the constructed network structure not conforming to the physical mechanism of electromagnetic compatibility fault propagation, and it is difficult to automatically extract effective nodes and edges when faced with multi-source heterogeneous data.

[0004] Parameter learning is prone to getting trapped in local optima: Training the conditional probability table (CPT) parameters of a Bayesian network is essentially a high-dimensional nonlinear optimization problem. Traditional gradient descent or standard particle swarm optimization (PSO) methods are prone to converging to local optima when dealing with complex objective functions, and suffer from slow convergence speed and low optimization accuracy.

[0005] Low utilization of multi-source data: EMC-related data typically includes test data, operation logs, and maintenance records, which are often semi-structured or unstructured. Existing technologies struggle to effectively integrate this heterogeneous multi-source information, resulting in incomplete input information for prediction models and impacting prediction accuracy. Summary of the Invention

[0006] This application aims to provide an electromagnetic compatibility fault prediction method based on knowledge graphs, which seeks to solve the problems of unreasonable network structure construction, low parameter optimization accuracy, and insufficient utilization of multi-source data in the prior art.

[0007] This application provides a knowledge graph-based electromagnetic compatibility fault prediction method, including: Collect multi-source heterogeneous data related to electromagnetic compatibility; the multi-source heterogeneous data includes electromagnetic compatibility test data, equipment operation logs, and fault repair records. Natural language processing algorithms are used to extract entities and relationships from the multi-source heterogeneous data and construct an electromagnetic compatibility fault knowledge graph. Based on the entity and relation mapping in the electromagnetic compatibility fault knowledge graph, the basic nodes and initial network structure of the Bayesian network are determined, and the target Bayesian network is obtained. The conditional probability parameters of the target Bayesian network are trained using ALS-PSO to determine the trained target Bayesian network. The real-time electromagnetic compatibility (EMC) status characteristics of the device under test are obtained, and the real-time EMC status characteristics are input into the trained target Bayesian network for probabilistic inference, and the EMC fault prediction results are output.

[0008] In one possible design approach, based on the entity-relation mapping in the knowledge graph, the basic nodes and initial network structure of the Bayesian network are determined to obtain the target Bayesian network, including: The entities in the knowledge graph are mapped to nodes of a Bayesian network; Map the relationships between entities in a knowledge graph to directed edges in a Bayesian network; For nodes in the knowledge graph that are not explicitly connected but co-occur in physical space, the connection relationships supplemented by human-computer interaction are obtained and mapped as directed edges to form a complete Bayesian network topology, thus obtaining the target Bayesian network.

[0009] In one possible design approach, ALS-PSO is used to train the conditional probability parameters of the target Bayesian network to determine the trained target Bayesian network, including: The conditional probability parameters of the target Bayesian network are encoded to initialize the particle swarm. For any particle in the particle swarm, the fitness of the particle is obtained according to the knowledge graph, and the particle with the highest fitness is determined as the optimal particle. Based on the optimal particle, the particle is adaptively updated using a cross-strategy of historical gene mutation and social information learning based on least squares, resulting in an adaptively updated particle. The known optimal solution space is developed by using the polar coordinate search strategy of Levy flight control to obtain the particle after the known optimal solution space is developed. A time-response-based boundary search strategy is used to perform a coordinated search on the particles after the known optimal solution space has been developed, to obtain the particles after the coordinated search. Determine the total number of training iterations, and determine the training phase based on the total number of training iterations; wherein the training phase includes a training completion phase or a training incomplete phase; If the training phase is incomplete, then return to the step of obtaining the optimal particle; If the training phase is the training completion phase, then the optimal particle is re-determined based on the particles after the coordinated search, and the parameters in the re-determined optimal particle are used as the final conditional probability parameters of the target Bayesian network to obtain the trained target Bayesian network.

[0010] In one possible design approach, the conditional probability parameters of the target Bayesian network are encoded, and the particle swarm is initialized, including: The conditional probability parameters of the target Bayesian network are randomly initialized between the upper and lower bounds and encoded into a vector to obtain particles; By repeatedly generating multiple different particles, a particle swarm is obtained.

[0011] In one possible design approach, based on the optimal particle, the particle is adaptively updated using a strategy combining historical gene mutation and social information learning based on least squares, resulting in an adaptively updated particle, including: When the total number of training iterations is less than the threshold, the optimal particle is adaptively updated using a social information learning strategy, resulting in the following adaptively updated particle: ; ; Wherein, the threshold number of training iterations is less than the preset maximum number of training iterations. Indicates the first t During the training process, the first m One particle, m =1,2,…,M, where M represents the total number of particles. Indicates the first m The particles after adaptive update express In the t Speed ​​during the training process express In the t Speed ​​during +1 training session Indicates the first learning factor. Indicates the second learning factor. Represents the first random number between (0,1). This represents the second random number between (0,1). Represents the optimal particle. express The historical best value; When the total number of training iterations exceeds the threshold, three historical values ​​of particles are randomly selected to obtain the first, second, and third historical values ​​of the particles. Based on the first historical value, the second historical value, and the third historical value, the first gene variation control factor and the second gene variation control factor are obtained using the least squares method: ; ; ; in, Indicates the first m The first gene mutation control factor corresponding to each particle. Indicates the first m The second gene mutation control factor corresponding to each particle. The first historical value represents the first historical value. d Dimensional parameters, d =1,2,…,D, where D represents the total dimension of the parameters in the particle. The second historical value represents the first d Dimensional parameters, The third historical value is represented by the first. d Dimensional parameters, This represents the first training interval coefficient. This represents the second training interval coefficient. This represents the third training interval coefficient. Indicates the first i Training interval coefficient, i=1,2,3 This represents the average fitness value of a particle during the t-th training iteration. This represents the average fitness value of a particle during training, corresponding to the i-th historical value, and T represents the preset maximum number of training iterations. The term is a positive number and is set to 0.01; The first gene mutation control factor and the second gene mutation control factor are obtained according to the least squares method, and the particle is mutated as follows: ; in, This represents the m-th mutation of the particle. d The dimension parameter, e, represents the natural constant; Employing a social information learning strategy, we obtain particles after social informatics. Adaptive selection and crossover are performed between the mutated particles and the social informatics-derived particles to obtain adaptively updated particles.

[0012] In one possible design approach, a polar coordinate search strategy based on Lévy flight control is used to develop the known optimal solution space for the adaptively updated particles, resulting in particles with the known optimal solution space developed, including: To obtain the Levi flight factor: ; ; in, Indicates the Levi flight factor. This represents the first Lévy control coefficient, which is randomized between (0,1). This represents the second Lévy control coefficient, which is randomized between (0,1). Indicates intermediate parameters. This represents a constant term, and is set to 1.5; The standard gamma function is represented by , and sin represents the sine function. Represents pi; To obtain the polar coordinate parameters: ; ; in, Indicates the polar radius. Represents polar coordinate angles. Represents a random number between (0, 1). This represents the total dimension of the parameters in the particle. This represents the angle control parameter, and is set to 0.005. Based on the polar coordinate parameters and the Levy flight factor, the known optimal solution space is expanded for the adaptively updated particles, resulting in the following particles after the known optimal solution space has been expanded: in, Indicates the first t During the training process, the first n The particles after adaptive update Indicates the first n Particles after the known optimal solution space has been developed. Represents the worst-case particle. This represents the optimal particle.

[0013] In one possible design approach, a time-response-based boundary search strategy is employed to perform a coordinated search on the particles after the known optimal solution space has been expanded, resulting in particles after the coordinated search, including: The time response factor is obtained as follows: in, Indicates the time response factor. Represents a random number that follows a Gaussian distribution. Represents the sine function. Represents pi (π). This indicates the preset maximum number of training iterations. Represents the total number of training iterations, and cos represents the cosine function. This represents the fourth random number between (0,1). Let represent the fifth random number between (0,1), and let log represent the logarithmic function. Indicates the peak response control coefficient; Based on the time response factor and combined with boundary information, a coordinated search is performed on the particles after the known optimal solution space has been expanded, resulting in the following particles after the coordinated search: in, Indicates the first t During the training process, the first j After the known optimal solution space is developed, the particle's first... d Dimensional parameters, Indicates the first j The particle after the first coordinated search d Dimensional parameters, Indicates the first d Dimensional boundary information acquisition factor, s represents the order of the coordination search, Indicates the overall coordination search order. The first particle represents the optimal particle. d Dimensional parameters, Indicates the first d The upper bound of the dimension parameter.

[0014] In one possible design approach, determining the training phase based on the total number of training iterations includes: If the total number of training iterations is greater than the preset maximum number of training iterations, the training phase is determined to be the training completion phase; otherwise, the training phase is determined to be the training incomplete phase.

[0015] In one possible design approach, the real-time electromagnetic compatibility (EMC) status characteristics of the device under test are acquired, and these characteristics are input into a trained target Bayesian network for probabilistic inference. The network then outputs an EMC fault prediction result, including: Acquire the real-time electromagnetic compatibility status characteristics of the device under test; The real-time electromagnetic compatibility (EMC) state features are input into the trained target Bayesian network, and the joint tree algorithm is used for inference to output the EMC fault prediction results.

[0016] In one possible design approach, the method further includes: generating an electromagnetic compatibility fault detection report based on the electromagnetic compatibility fault prediction results and according to a preset template.

[0017] Beneficial effects: This application provides a knowledge graph-based electromagnetic compatibility (EMC) fault prediction method. By constructing an EMC fault knowledge graph through multi-source heterogeneous data, it not only achieves structured data fusion but also provides physically meaningful nodes and relationships for the Bayesian network, making the target Bayesian network interpretable and able to trace the source of the fault. Furthermore, ALS-PSO is used to optimize the target Bayesian network, which can effectively improve the training accuracy of the target Bayesian network, thereby enabling the trained target Bayesian network to accurately predict EMC faults. Attached Figure Description

[0018] To more clearly illustrate the technical solutions of the embodiments of this application, the drawings used in the description of the embodiments of this application will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0019] Figure 1 This is a flowchart of an electromagnetic compatibility fault prediction method based on knowledge graphs proposed in an embodiment of this application; Figure 2 This is a flowchart of obtaining the trained target Bayesian network according to an embodiment of this application. Detailed Implementation

[0020] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0021] like Figure 1 As shown in the figure, this application provides an electromagnetic compatibility fault prediction method based on knowledge graphs, including: S101. Collect multi-source heterogeneous data related to electromagnetic compatibility; the multi-source heterogeneous data includes electromagnetic compatibility test data, equipment operation logs and fault repair records.

[0022] For example, this can be achieved through test data such as conducted emissions and radiated emissions collected by EMC testing equipment; operational log data such as voltage, current, and temperature uploaded by equipment sensors; and textual description data from historical maintenance records.

[0023] S102. Natural language processing algorithms are used to extract entities and relationships from the multi-source heterogeneous data, and an electromagnetic compatibility fault knowledge graph is constructed.

[0024] Natural language processing algorithms can be used to extract entities and relationships from electromagnetic compatibility (EMC) test data, equipment operation logs, and fault repair records, and to construct an EMC fault knowledge graph. For example, entities from multi-source heterogeneous data can include equipment entities, interference source entities, sensitive equipment entities, fault phenomenon entities, fault cause entities, and / or environmental parameter entities; relationships can include those such as causing, coupled to, belonging to, occurring at, and / or related to. However, it is worth noting that the above entities and relationships are merely illustrative examples in this application's embodiments; in actual applications, the actual data shall prevail.

[0025] S103. Based on the entity and relation mapping in the electromagnetic compatibility fault knowledge graph, determine the basic nodes and initial network structure of the Bayesian network to obtain the target Bayesian network. Entities in a knowledge graph (such as interference source entities and sensitive device entities) can be mapped to nodes in a Bayesian network; relationships between entities (such as causes) can be mapped to directed edges.

[0026] Considering the possibility of missing data, for nodes in the knowledge graph that are not explicitly connected but co-occur in physical space (such as two chips on the same circuit board), experts are consulted via a human-computer interaction interface to inquire whether a connection should be established. If the expert confirms, the connection is supplemented by a directed edge, thus forming a complete Bayesian network topology that conforms to physical logic, which is the prototype of the target Bayesian network.

[0027] S104. The conditional probability parameters of the target Bayesian network are trained using ALS-PSO to determine the trained target Bayesian network.

[0028] After the structure of a Bayesian network is determined, the conditional probability parameters (CPTs) between nodes need to be trained. Existing technologies typically employ particle swarm optimization (PSO) or gradient descent algorithms for training, which often leads to getting trapped in local optima and failing to find the optimal solution in the high-dimensional solution space. Consequently, the trained Target Bayesian network cannot accurately predict electromagnetic compatibility (EMC) faults. Therefore, this application provides an ALS-PSO (Adaptive Least Squares Particle Swarm Optimization) algorithm to train the Target Bayesian network more accurately, enabling it to perform fault reasoning.

[0029] S105. Obtain the real-time electromagnetic compatibility status characteristics of the device under test, and input the real-time electromagnetic compatibility status characteristics into the trained target Bayesian network for probabilistic inference, and output the electromagnetic compatibility fault prediction result.

[0030] For example, the real-time electromagnetic compatibility (EMC) status characteristics of the device under test (DUT) can be obtained (such as real-time spectrum data, operating voltage, etc.). These characteristics are then input into a trained target Bayesian network. A joint tree algorithm is used for efficient probabilistic inference to calculate the posterior probability of each fault node, and the fault type with the highest probability is output as the prediction result.

[0031] This application's embodiments collect electromagnetic compatibility test data, equipment operation logs, and fault repair records, and construct a knowledge graph using natural language processing algorithms. Compared to methods relying solely on single test data, this invention fully utilizes the implicit fault mechanisms and expert experience contained in unstructured text (such as logs and repair records). The construction of the knowledge graph not only achieves structured data fusion but also provides Bayesian networks with physically meaningful nodes and relationships, making the prediction model interpretable and enabling the tracing of fault sources.

[0032] In one possible design approach, based on the entity-relation mapping in the knowledge graph, the basic nodes and initial network structure of the Bayesian network are determined to obtain the target Bayesian network, including: The entities in the knowledge graph are mapped to nodes of a Bayesian network; Map the relationships between entities in a knowledge graph to directed edges in a Bayesian network; For nodes in the knowledge graph that are not explicitly connected but co-occur in physical space, the connection relationships supplemented by human-computer interaction are obtained and mapped as directed edges to form a complete Bayesian network topology, thus obtaining the target Bayesian network.

[0033] This application's embodiments construct the initial structure of the Bayesian network based on the entity-relation mapping in the knowledge graph, avoiding the inefficiency and structural inconsistencies caused by blind searching in traditional pure data-driven methods. In particular, for nodes in the graph that are not explicitly connected but co-occur in physical space, connections are supplemented through human-computer interaction, further improving the network topology. This ensures that the structure of the Bayesian network conforms to the physical laws of electromagnetic compatibility fault propagation, enhancing the fundamental rationality of the model.

[0034] like Figure 2 As shown, the conditional probability parameters of the target Bayesian network are trained using ALS-PSO to determine the trained target Bayesian network, including: S201. Encode the conditional probability parameters of the target Bayesian network and initialize the particle swarm; S202. For any particle in the particle swarm, obtain the fitness of the particle according to the knowledge graph, and determine the particle with the highest fitness as the optimal particle. For example, the log-likelihood value of the target Bayesian network can be calculated as the fitness, and the particle with the highest fitness can be determined as the optimal particle. Fitness calculation is a relatively conventional technique for training Bayesian networks, and existing technologies can be used; therefore, it will not be elaborated further in this application.

[0035] S203. Based on the optimal particle, the particle is adaptively updated using a cross-strategy of historical gene mutation and social information learning based on least squares, to obtain the adaptively updated particle. S204. Using the polar coordinate search strategy of Levy flight control, the known optimal solution space is developed for the adaptively updated particles to obtain the particles after the known optimal solution space has been developed. S205. A time-response-based boundary search strategy is used to perform a coordinated search on the particles after the known optimal solution space has been developed, so as to obtain the particles after the coordinated search. S206. Determine the total number of training iterations, and determine the training phase based on the total number of training iterations; wherein the training phase includes a training completion phase or a training incomplete phase; S207. If the training phase is incomplete, then return to the step of obtaining the optimal particle. S208. If the training phase is the training completion phase, then the optimal particle is re-determined based on the particles after the coordinated search, and the parameters in the re-determined optimal particle are used as the final conditional probability parameters of the target Bayesian network to obtain the trained target Bayesian network.

[0036] In one possible design approach, the conditional probability parameters of the target Bayesian network are encoded, and the particle swarm is initialized, including: The conditional probability parameters of the target Bayesian network are randomly initialized between the upper and lower bounds and encoded into a vector to obtain particles; By repeatedly generating multiple different particles, a particle swarm is obtained.

[0037] In one possible design approach, based on the optimal particle, the particle is adaptively updated using a strategy combining historical gene mutation and social information learning based on least squares, resulting in an adaptively updated particle, including: When the total number of training iterations is less than the threshold (which can be set to T / 4, where T can be a multiple of 100), the optimal particle is adaptively updated using a social information learning strategy, resulting in the following adaptively updated particle: ; ; Wherein, the threshold number of training iterations is less than the preset maximum number of training iterations. Indicates the first t During the training process, the first m One particle, m =1,2,…,M, where M represents the total number of particles. Indicates the first m The particles after adaptive update express In the t Speed ​​during the training process express In the t Speed ​​during +1 training session This represents the first learning factor, which can be set to 0.75; This represents the second learning factor, which can be set to 1.5; Represents the first random number between (0,1). This represents the second random number between (0,1). Represents the optimal particle. express The historical best value; When the total number of training iterations exceeds the threshold, three historical values ​​of particles are randomly selected to obtain the first, second, and third historical values ​​of the particles. Based on the first historical value, the second historical value, and the third historical value, the first gene variation control factor and the second gene variation control factor are obtained using the least squares method: ; ; ; in, Indicates the first m The first gene mutation control factor corresponding to each particle. Indicates the first m The second gene mutation control factor corresponding to each particle. The first historical value represents the first historical value. d Dimensional parameters, d =1,2,…,D, where D represents the total dimension of the parameters in the particle. The second historical value represents the first d Dimensional parameters, The third historical value is represented by the first. d Dimensional parameters, This represents the first training interval coefficient. This represents the second training interval coefficient. This represents the third training interval coefficient. Indicates the first i Training interval coefficient, i =1,2,3 This represents the average fitness value of a particle during the t-th training iteration. This represents the average fitness value of a particle during training, corresponding to the i-th historical value, and T represents the preset maximum number of training iterations. The term is a positive number and is set to 0.01; The first gene mutation control factor and the second gene mutation control factor are obtained according to the least squares method, and the particle is mutated as follows: ; in, This represents the m-th mutation of the particle. d The dimension parameter, e, represents the natural constant; Employing a social information learning strategy, we obtain particles after social informatics. Adaptive selection and crossover are performed between the mutated particles and the social informatics-derived particles to obtain adaptively updated particles.

[0038] Starting with the first-dimensional parameter of the particle, the corresponding parameters from the mutated particle and the social informatics-adapted particle are replaced. The parameter that increases the fitness of the replaced particle is selected as the parameter for the adaptively updated particle. After traversing all dimensions of the particle, the adaptively updated particle is obtained. For example, replacing the first-dimensional parameter of the mutated particle with the first-dimensional parameter yields the first-replaced particle; replacing the first-dimensional parameter of the social informatics-adapted particle with the first-dimensional parameter yields the second-replaced particle. If the fitness of the first-replaced particle is greater than that of the second-replaced particle, then the first-dimensional parameter of the mutated particle is used to replace the first-dimensional parameter of the second-replaced particle. This process is repeated for each dimension of the particle, and after traversing all dimensions, the adaptively updated particle is obtained.

[0039] In the early stages of training, a social information learning strategy is employed to accelerate particle convergence. In the later stages, a least-squares-based historical gene mutation strategy is introduced, utilizing the position information and fitness differences of historical particles to calculate mutation control factors, effectively maintaining population diversity and preventing the algorithm from getting trapped in local optima. The introduction of adaptive selection crossover effectively improves the training speed of the algorithm, balancing training speed and training quality.

[0040] In one possible design approach, a polar coordinate search strategy based on Lévy flight control is used to develop the known optimal solution space for the adaptively updated particles, resulting in particles with the known optimal solution space developed, including: To obtain the Levi flight factor: ; ; in, Indicates the Levi flight factor. This represents the first Lévy control coefficient, which is randomized between (0,1). This represents the second Lévy control coefficient, which is randomized between (0,1). Indicates intermediate parameters. This represents a constant term, and is set to 1.5; The standard gamma function is represented by , and sin represents the sine function. Represents pi; To obtain the polar coordinate parameters: ; ; in, Indicates the polar radius. Represents polar coordinate angles. Represents a random number between (0, 1). This represents the total dimension of the parameters in the particle. This represents the angle control parameter, and is set to 0.005. Based on the polar coordinate parameters and the Levy flight factor, the known optimal solution space is expanded for the adaptively updated particles, resulting in the following particles after the known optimal solution space has been expanded: in, Indicates the first t During the training process, the first n The particles after adaptive update Indicates the first n Particles after the known optimal solution space has been developed. Represents the worst-case particle. This represents the optimal particle.

[0041] The polar coordinate search strategy of the Levy flight control described above allows the adaptively updated particles to search around the optimal particle. This allows for some positional transformation in the early stages of the algorithm, completely avoiding getting trapped in local optima. While moving towards the optimal particle, it moves away from the worst particle (i.e., the particle with the lowest fitness). Utilizing the long jump characteristic of Levy flight combined with polar coordinate transformation, it performs in-depth exploration within the known optimal solution space. This non-linear search method can escape local limitations and enhance global optimization capabilities. In the later stages of the algorithm, it gradually refines the local search around the optimal particle, ensuring training accuracy.

[0042] In one possible design approach, a time-response-based boundary search strategy is employed to perform a coordinated search on the particles after the known optimal solution space has been expanded, resulting in particles after the coordinated search, including: The time response factor is obtained as follows: in, Indicates the time response factor. Represents a random number that follows a Gaussian distribution. Represents the sine function. Represents pi (π). This indicates the preset maximum number of training iterations. Represents the total number of training iterations, and cos represents the cosine function. This represents the fourth random number between (0,1). Let represent the fifth random number between (0,1), and let log represent the logarithmic function. This represents the peak response control coefficient, which can be set to a constant between 0.75 and 0.9. Based on the time response factor and combined with boundary information, a coordinated search is performed on the particles after the known optimal solution space has been expanded, resulting in the following particles after the coordinated search: in, Indicates the first t During the training process, the first j After the known optimal solution space is developed, the particle's first... d Dimensional parameters, Indicates the first j The particle after the first coordinated search d Dimensional parameters, Indicates the first d Dimensional boundary information acquisition factor, s represents the order of the coordination search, This indicates the overall coordination search order, which can be set to 4; The first particle represents the optimal particle. dDimensional parameters, Indicates the first d The upper bound of the dimension parameter, i.e., the upper limit.

[0043] The aforementioned time-response-based boundary search strategy introduces a dynamic response factor that changes over time. It adjusts the search step size and direction based on the current training progress and boundary information, enabling the algorithm to have a greater global search capability in the early and mid-stages. This effectively avoids the algorithm getting stuck in local optima. At the same time, the algorithm will gradually explore the neighborhood in the later stages to ensure convergence accuracy.

[0044] Optionally, to accelerate training, simulated annealing can be used to control the time-response-based boundary search strategy.

[0045] In one possible design approach, determining the training phase based on the total number of training iterations includes: If the total number of training iterations is greater than the preset maximum number of training iterations, the training phase is determined to be the training completion phase; otherwise, the training phase is determined to be the training incomplete phase.

[0046] In one possible design approach, the real-time electromagnetic compatibility (EMC) status characteristics of the device under test are acquired, and these characteristics are input into a trained target Bayesian network for probabilistic inference. The network then outputs an EMC fault prediction result, including: Acquire the real-time electromagnetic compatibility status characteristics of the device under test; The real-time electromagnetic compatibility (EMC) state features are input into the trained target Bayesian network, and the joint tree algorithm is used for inference to output the EMC fault prediction results.

[0047] For example, a trained target Bayesian network can be used for real-time prediction.

[0048] Collect real-time electromagnetic compatibility status characteristics of the device under test, such as the current interference voltage value of the power port and the current operating temperature.

[0049] These real-time electromagnetic compatibility status features are used as evidence input into the corresponding nodes of the Bayesian network, and the joint tree algorithm is used for inference to calculate the posterior probability of faulty nodes (such as CPU reset, communication packet loss).

[0050] Output prediction results: For example, the probability of CPU reset is 85% and the probability of communication packet loss is 60%, which can be used to issue early warnings.

[0051] In one possible design approach, the method further includes: generating an electromagnetic compatibility fault detection report based on the electromagnetic compatibility fault prediction results and according to a preset template.

[0052] The various embodiments in this specification are described in a progressive manner, with each embodiment focusing on the differences from other embodiments. The same or similar parts between the various embodiments can be referred to each other.

[0053] This application describes embodiments with reference to flowchart illustrations and / or block diagrams of methods, apparatuses, electronic devices, and computer program products according to embodiments of this application. It should be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing terminal device to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing terminal device, generate instructions for implementing the flowchart... Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0054] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing terminal device to operate in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0055] These computer program instructions can also be loaded onto a computer or other programmable data processing terminal equipment, causing a series of operational steps to be performed on the computer or other programmable terminal equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable terminal equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0056] Although preferred embodiments of the present application have been described, those skilled in the art, upon learning the basic inventive concept, can make other changes and modifications to these embodiments. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments as well as all changes and modifications falling within the scope of the embodiments of the present application.

[0057] Finally, it should be noted that in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or terminal device that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or terminal device. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or terminal device that includes said element.

[0058] This document uses specific examples to illustrate the principles and implementation methods of this application. The descriptions of the above embodiments are only for the purpose of helping to understand the methods and core ideas of this application. At the same time, for those skilled in the art, there will be changes in the specific implementation methods and application scope based on the ideas of this application. Therefore, the content of this specification should not be construed as a limitation of this application.

Claims

1. A knowledge graph-based electromagnetic compatibility failure prediction method, characterized in that, The method comprises the following steps: Collecting electromagnetic compatibility related multi-source heterogeneous data; the multi-source heterogeneous data includes electromagnetic compatibility test data, equipment operation log and fault maintenance record; Using natural language processing algorithm to extract entities and relationships from the multi-source heterogeneous data, and constructing electromagnetic compatibility fault knowledge graph; Based on the entity and relationship mapping in the electromagnetic compatibility fault knowledge graph, the basic nodes and initial network structure of the Bayesian network are determined, and the target Bayesian network is obtained; Using ALS-PSO to train the conditional probability parameters of the target Bayesian network, and determining the target Bayesian network after training; Obtaining the real-time electromagnetic compatibility state characteristics of the equipment to be tested, and inputting the real-time electromagnetic compatibility state characteristics into the target Bayesian network after training for probability reasoning, and outputting the electromagnetic compatibility fault prediction result. 2.The knowledge graph-based electromagnetic compatibility failure prediction method according to claim 1, characterized in that, Based on the entity and relationship mapping in the knowledge graph, the basic nodes and initial network structure of the Bayesian network are determined, and the target Bayesian network is obtained, which comprises: Mapping the entities in the knowledge graph to the nodes of the Bayesian network; Mapping the relationships between entities in the knowledge graph to the directed edges of the Bayesian network; For the nodes in the knowledge graph that are not explicitly connected but coexist in the physical space, the connection relationship supplemented by human-computer interaction is obtained, and is mapped to the directed edge to form the topological structure of the complete Bayesian network, and the target Bayesian network is obtained. 3.The knowledge graph based electromagnetic compatibility failure prediction method according to claim 1, characterized in that, Using ALS-PSO to train the conditional probability parameters of the target Bayesian network, and determining the target Bayesian network after training, which comprises: Encoding the conditional probability parameters of the target Bayesian network, and initializing the particle swarm; For any particle in the particle swarm, the fitness corresponding to the particle is obtained according to the knowledge graph, and the particle with the maximum fitness is determined as the optimal particle; Based on the optimal particle, the adaptive update of the particle is carried out by using the least square based historical gene mutation and social information learning cross strategy, and the particle after adaptive update is obtained; Using the polar coordinate search strategy of Levy flight control to develop the known optimal solution space of the particle after adaptive update, and obtaining the particle after known optimal solution space development; Using the boundary search strategy based on time response to carry out coordinated search on the particle after known optimal solution space development, and obtaining the particle after coordinated search; Determine the total training times, and determine the training stage according to the total training times; wherein the training stage includes training completion stage or training incomplete stage; If the training stage is training incomplete stage, return to the step of obtaining the optimal particle; If the training stage is training completion stage, the optimal particle is re-determined according to the particle after coordinated search, and the parameters in the re-determined optimal particle are used as the final conditional probability parameters of the target Bayesian network, and the target Bayesian network after training is obtained. 4.The knowledge graph-based electromagnetic compatibility failure prediction method according to claim 3, characterized in that, Encoding the conditional probability parameters of the target Bayesian network, and initializing the particle swarm, which comprises: Randomly initializing between the upper limit and the lower limit of the conditional probability parameters of the target Bayesian network, and encoding into a vector to obtain a particle; The plurality of different particles are repeatedly generated to obtain a particle group. 5.The knowledge graph based electromagnetic compatibility failure prediction method according to claim 3, characterized in that, Based on the optimal particle, the particle is adaptively updated by using a history gene mutation and social information learning cross strategy based on least squares to obtain a particle after adaptive update, including: When the total training number is less than the number threshold, the particle is adaptively updated according to the optimal particle by using a social information learning strategy to obtain a particle after adaptive update, including: ； ； wherein the number threshold is less than a preset maximum training number, denotes the i-th particle in the j-th training process, t denotes the i-th particle in the j-th training process, m denotes the i-th particle in the j-th training process, m = 1, 2, …, M, M denotes a total number of particles, denotes the i-th particle after the j-th adaptive update, m denotes the i-th particle after the j-th adaptive update, denotes the i-th particle after the j-th adaptive update, denotes the i-th velocity in the j-th training process, t denotes the i-th velocity in the j-th training process, denotes the i-th velocity in the j-th training process, denotes the i-th velocity in the j-th training process, t denotes the i-th velocity in the j-th training process, denotes a first learning factor, denotes a second learning factor, denotes a first random number between (0, 1), denotes a second random number between (0, 1), denotes an optimal particle, denotes a historical optimal value of the i-th particle, denotes a historical optimal value of the i-th particle. When the total training number is greater than the number threshold, three particle history values are randomly selected to obtain a first history value, a second history value and a third history value corresponding to the particle; According to the first history value, the second history value and the third history value, a first gene mutation control factor and a second gene mutation control factor are obtained by using a least squares method, including: ； ； ； in, Indicates the first m The first gene mutation control factor corresponding to each particle. Indicates the first m The second gene mutation control factor corresponding to each particle. The first historical value represents the first historical value. d Dimensional parameters, d =1,2,…,D, where D represents the total dimension of the parameters in the particle. The second historical value represents the first d Dimensional parameters, The third historical value is represented by the first. d Dimensional parameters, This represents the first training interval coefficient. This represents the second training interval coefficient. This represents the third training interval coefficient. Indicates the first i Training interval coefficient, i=1,2,3 This represents the average fitness value of a particle during the t-th training iteration. This represents the average fitness value of a particle during training, corresponding to the i-th historical value, and T represents the preset maximum number of training iterations. The term is a positive number and is set to 0.01; According to the first gene mutation control factor and the second gene mutation control factor obtained by the least squares method, the particle is mutated, including: ； wherein, represents the mth variation of the particle d dimensional parameter, e represents the natural constant; The particle after social information learning is obtained by using a social information learning strategy. The particle after mutation and the particle after social information learning are adaptively selected and crossed to obtain a particle after adaptive update. 6.The knowledge graph based electromagnetic compatibility failure prediction method according to claim 3, characterized in that, The particle after adaptive update is developed in a known optimal solution space by using a polar coordinate search strategy of Levy flight control to obtain a particle after known optimal solution space development, including: A Levy flight factor is obtained, including: ； ； wherein, denotes the Levy flight factor, denotes a first Levy control coefficient random between (0,1), denotes a second Levy control coefficient random between (0,1), denotes an intermediate parameter, denotes a constant term and is set to 1.5; denotes the standard gamma function, sin denotes the sine function, denotes the constant pi; A polar coordinate parameter is obtained, including: ； ； wherein, denotes the polar radius, denotes the polar angle, denotes a random number between (0,1), denotes the total dimension of parameters in the particle, denotes the angle control parameter, and is set to 0.005; According to the polar coordinate parameter and the Levy flight factor, the particle after adaptive update is developed in a known optimal solution space to obtain a particle after known optimal solution space development, including: in, Indicates the first t During the training process, the first n The particles after adaptive update Indicates the first n Particles after the known optimal solution space has been developed. Represents the worst-case particle. This represents the optimal particle. 7.The knowledge graph based electromagnetic compatibility failure prediction method according to claim 3, characterized in that, The particle after known optimal solution space development is coordinately searched by using a boundary search strategy based on time response to obtain a particle after coordination search, including: A time response factor is obtained, including: wherein, represents a time response factor, represents a random number subject to a Gaussian distribution, represents a sine function, represents a circular constant, represents a preset maximum training number, represents a total training number, cos represents a cosine function, represents a fourth random number between (0, 1), represents a fifth random number between (0, 1), log represents a logarithmic function, represents a response peak control coefficient; According to the time response factor and in combination with boundary information, the particle after known optimal solution space development is coordinately searched to obtain a particle after coordination search, including: in, Indicates the first t During the training process, the first j After the known optimal solution space is developed, the particle's first... d Dimensional parameters, Indicates the first j The particle after the first coordinated search d Dimensional parameters, Indicates the first d Dimensional boundary information acquisition factor, s represents the order of the coordination search, Indicates the overall coordination search order. The first particle represents the optimal particle. d Dimensional parameters, Indicates the first d The upper bound of the dimension parameter. 8.The knowledge graph based electromagnetic compatibility failure prediction method according to claim 3, characterized in that, The training phase is determined according to the total training number, including: When the total training number is greater than a preset maximum training number, the training phase is determined as a training completion phase, otherwise the training phase is determined as a training incomplete phase. 9.The knowledge graph based electromagnetic compatibility failure prediction method according to claim 1, wherein, The real-time electromagnetic compatibility state feature of the to-be-tested equipment is obtained, and the real-time electromagnetic compatibility state feature is input into the target Bayesian network after training for probability inference to output an electromagnetic compatibility fault prediction result, including: The real-time electromagnetic compatibility state feature of the to-be-tested equipment is obtained; The real-time electromagnetic compatibility state feature is input into the target Bayesian network after training, and a joint tree algorithm is used for inference to output an electromagnetic compatibility fault prediction result. 10.The knowledge graph based electromagnetic compatibility failure prediction method according to claim 1, characterized in that, Further including: Based on the electromagnetic compatibility fault prediction result, an electromagnetic compatibility fault detection report is generated according to a preset template.

Images