Method and system for analyzing failure of aviation equipment based on ontology semantic retrieval

Abstract

The application provides an aviation equipment fault analysis method and system based on ontology semantic retrieval, relates to the technical field of aviation equipment maintenance support, and comprises the following steps: S1, establishing an aviation equipment fault ontology model, setting a retrieval condition, and determining fault ontology characteristic parameters; S2, performing semantic data matching of aviation equipment fault ontology concept characteristic parameters; S3, performing aviation equipment fault ontology data characteristic parameter matching; S4, calculating the weighted semantic similarity of aviation equipment fault ontology concept characteristic parameters; and S5, judging the aviation equipment fault type and assisting in processing aviation equipment faults. The application changes actual fault data retrieval into matching of concepts and their semantics in the fault ontology library, utilizes standardized concepts for retrieval, effectively improves the recall rate and precision rate of fault data retrieval, proposes a concept matching similarity method in combination with the depth and density factors of the ontology model, realizes aviation equipment fault ontology semantic retrieval, and provides accurate fault auxiliary diagnosis.

Description

Technical Field

[0001] This invention relates to the field of aviation equipment fault evaluation technology, and specifically to an aviation equipment fault analysis method and system based on ontology semantic retrieval. Background Technology

[0002] Aviation equipment is a large, complex, technologically advanced, and quality-critical product system. Due to its massive system structure, numerous complex functions, and intricate subsystems, the probability of failure is relatively high. Localized failures can sometimes trigger major accidents, causing significant losses and even casualties. Therefore, improving reliability to reduce the probability of failure and preventing and eliminating failures through maintenance and support are essential. Failure is an inherent characteristic of products; products can malfunction during use, preventing them from performing their tasks or functions as required, and even affecting safety. As a complex equipment system, aviation equipment failures are characterized by complexity, hierarchy, correlation, delay, and uncertainty. The most direct method to solve failure problems is to reuse similar failure data. The main way to apply failure data is through knowledge retrieval. Traditional information retrieval technologies generally use simple word matching rules, which can only retrieve information if the search terms appear in the search object. This has limited ability to represent relevant information and cannot describe or reflect semantic information. However, the search terms entered are related to knowledge background, search ability, and search experience. They may only be one of several synonyms, near-synonyms, or related terms for a certain concept. As a result, concepts similar to the user's search request often cannot be retrieved due to different wording, resulting in low search efficiency and a lack of accuracy and comprehensiveness in the search results.

[0003] Semantics refers to concepts that computers can recognize; it is the relationship between symbols and expressions built on a certain grammar and the objects they describe. Semantic retrieval is a retrieval mechanism that provides machine-readable and understandable information through semantic descriptions, and performs retrieval and reasoning according to certain logical rules. Semantic retrieval uses a standardized concept set to map search terms to their synonyms, near-synonyms, and related semantic terms. Using a standardized set of concepts for retrieval effectively improves the recall and precision of information retrieval. The key to achieving semantic retrieval lies in the expression of knowledge and reasoning based on knowledge. Knowledge retrieval is the reverse process of knowledge organization; achieving concept-based semantic knowledge retrieval relies on the support of a knowledge organization system.

[0004] An ontology is an explicit formal specification of a shared conceptual model, containing modeling meta-terms such as concepts, relations, functions, axioms, and instances. As a way of organizing knowledge, it can explicitly describe the setting of domain concepts, reflect the semantic information of concepts through the relationships between them, and endow simple terms with explicit background knowledge, thereby clarifying implicit relationships and ensuring semantic consistency. The concept of ontology originated in the field of philosophy to study the nature of the objective world. In the field of science and technology, the generally accepted setting is: an ontology is an explicit formal specification of a shared conceptual model. This setting has four layers of meaning: shared refers to the idea that the ontology captures shared knowledge, reflecting a set of recognized concepts in the relevant domain, and it is aimed at groups rather than individuals; conceptualization refers to the model obtained by abstracting related concepts of some phenomena in the objective world, and its meaning is independent of specific environmental states; explicit means that the types of all concepts and the constraints between concepts should be clearly defined; and formal means that the ontology should be computer-understandable, that is, it should be able to be processed by computers. The goal of ontology is to capture fault data in a relevant domain, provide a shared understanding of this data, identify commonly accepted vocabulary within the domain, and explicitly define these vocabulary terms and their relationships at different levels of formalization. The language used in ontology can be categorized into informal, semi-formal, and formal ontology languages ​​based on the degree of formalization in representation and description. A higher degree of formalization in an ontology facilitates automated computer processing. Ontologies can explicitly describe the definition of domain concepts, reflect semantic information through relationships between concepts, and assign explicit background fault data to simple terms, thereby clarifying implicit relationships and ensuring semantic consistency. Because ontology enables communication between humans and computers, or between computers, to be based on a consensus of the domain being communicated, it is suitable for representing aviation equipment fault data. Ontology-based representations of aviation equipment fault data model the real world itself, making them task-independent. Ontology-based topological representations of various types of aviation equipment fault data establish explicit relationships between them, achieving unification and providing explicit semantics for the data.

[0005] Fault data comprises all conceptualized, valuable experience and information related to product failures, encompassing multiple dimensions such as faulty products, failure modes, failure causes, failure impacts, failure handling, failure cases, and failure diagnosis. Organizing aerospace equipment fault data using ontology technology can provide computer-understandable domain concepts and their relationships, and also supports semantic retrieval. Summary of the Invention

[0006] To address the shortcomings of existing technologies, this invention aims to provide a method and system for fault analysis of aviation equipment based on ontology semantic retrieval. By standardizing retrieval conditions and transforming them into concepts within ontology rule constraints, the actual fault data retrieval is converted into a matching process of concepts and their semantics within a fault ontology database. The search and reasoning process at the semantic layer of fault data effectively improves recall and precision by utilizing a set of standardized concepts. An ontology-based semantic retrieval model is established from aspects such as semantic expansion and semantic matching. A concept matching similarity method based on semantic distance is proposed, incorporating the depth and density factors of the ontology model. Furthermore, a semantic retrieval method and its implementation process are presented based on this method. The fault analysis system provides user-oriented support for fault data semantic retrieval applications, enabling comprehensive and accurate retrieval of fault data and providing strong support for solving fault problems.

[0007] Specifically, on the one hand, the present invention provides a method for analyzing aircraft equipment faults based on ontology semantic retrieval, which includes the following steps: S1: Establish an aviation equipment fault ontology model, set search conditions, and determine fault ontology feature parameters; if the search items of aviation equipment fault data correspond to the conceptual feature parameters of the fault ontology, then proceed to step S2; if the search items of aviation equipment fault data correspond to the data feature parameters of the fault ontology, then proceed to step S3. S2: Expand the semantic data of the feature parameters of the aviation equipment fault ontology concept, calculate the depth factor and density factor of the feature parameters of the aviation equipment fault ontology concept, determine the semantic distance between the feature parameters of the fault ontology concept, calculate the semantic similarity between the feature parameters of the aviation equipment fault ontology concept, and perform semantic matching of the feature parameters of the aviation equipment fault ontology concept. S3: Perform fault body data feature parameter matching for aviation equipment, specifically including: corresponding matching of data feature parameters, fuzzy matching of data feature parameters, and matching of text data feature parameters; S4: Perform steps S2 and S3 respectively on the conceptual feature parameters and data feature parameters of the aviation equipment fault ontology. After summing the similarity of the obtained feature parameters, normalize the weights of all search feature parameters and calculate the weighted semantic similarity of the conceptual feature parameters of the aviation equipment fault ontology. Specifically: ; in, Examples of failures in aviation equipment and examples Weighted semantic similarity between them; For the first The weights of each feature parameter; For the first A semantic similarity function for each feature parameter value; This is an example of a fault in the first type of aviation equipment. This is an example of a faulty component in the second type of aviation equipment. For the retrieval feature parameter number; To retrieve the total number of feature parameters; S5: Based on the semantic search results of aviation equipment failures in step S4, determine the type of aviation equipment failure.

[0008] Preferably, step S2 specifically includes: S21: Semantic data for the feature parameters of the concept of fault ontology of aviation equipment, specifically including: data synonym expansion, feature parameter expansion, hierarchical expansion, axiom expansion and rule expansion; S22: Calculate the depth factor and density factor of the feature parameters of the fault ontology concept of aviation equipment, and determine the semantic distance between the feature parameters of the fault ontology concept. S23: Calculate the semantic similarity between the feature parameters of the aviation equipment fault ontology concept, and perform semantic matching of the feature parameters of the aviation equipment fault ontology concept.

[0009] Preferably, step S22 specifically includes: S221: Determine the conceptual characteristic parameters of the aircraft equipment fault ontology The depth is ; Depth factor for setting the concept level depth factor Calculate the depth factor of the conceptual characteristic parameters of the fault ontology of aviation equipment; S222: Determine the conceptual characteristic parameters of the aircraft equipment fault ontology The density is ; Set the density factor β of the concept density factor, and calculate the density factor of the conceptual characteristic parameters of the aircraft equipment fault ontology; S223: Calculate the fault ontology concept feature parameters of aviation equipment within the fault concept tree of the aviation equipment fault ontology concept feature parameters. Node-to-concept feature parameters The semantic distance of nodes yields the comprehensive semantic distance between the feature parameters of two concepts in the aviation equipment fault ontology. .

[0010] Preferably, the depth factors of the aviation equipment fault ontology concept feature parameters in step S221 specifically include: a higher-level semantic relationship depth factor and a lower-level semantic relationship depth factor; the higher-level semantic relationship depth factor is determined through the root node of the aviation equipment fault concept tree, and the lower-level semantic relationship depth factor is determined through the bottom-level leaf nodes of the aviation equipment fault concept tree, specifically as follows: ; ; in, Conceptual feature parameters The depth factor of the higher-level semantic relation; For the conceptual characteristic parameters of the fault body of aviation equipment; Conceptual feature parameters The depth; Conceptual feature parameters The depth factor of the subordinate semantic relation; Fault concept tree for aviation equipment The depth; A concept tree for aircraft equipment failures.

[0011] Preferably, the density factors of the feature parameters of the aviation equipment fault ontology concept in step S222 include: a higher-level semantic relation density factor and a lower-level semantic relation density factor; the higher-level semantic relation density factor is determined by the root node of the aviation equipment fault concept tree, and the lower-level semantic relation density factor is determined by the bottom-level leaf nodes of the aviation equipment fault concept tree, specifically: ; ; in, The hyperordinate semantic relation density factor of the concept feature parameter C; This is the parent node of the concept feature parameter C; Let C be the out-degree of the parent node of the concept feature parameter C; Conceptual feature parameters The hyponym semantic relation density factor; Conceptual feature parameters The degree of departure.

[0012] Preferably, step S223 uses the baseline value of the semantic distance between the hierarchical relationship. Multiplying by a combined adjustment coefficient that combines the depth factor and the density factor, we obtain the actual semantic distance of the hierarchical semantic relationship. The combined adjustment coefficient of depth factor and density factor is used as a conceptual feature parameter. Depth factor of hierarchical semantic relationship Add density factor Multiply by adjustment coefficient Specifically: ; in, This represents the actual semantic distance between the hierarchical semantic relationships. This serves as the baseline value for the semantic distance between hierarchical relationships; Conceptual feature parameters The depth factor of the hierarchical semantic relationship; Conceptual feature parameters Density factor of hierarchical semantic relationship; This is the adjustment coefficient.

[0013] Preferably, step S23 specifically includes: Calculate the comprehensive semantic distance between concept feature parameters in the fault ontology. The comprehensive semantic distance is the sum of the semantic distances of all directed edges of the shortest path between concept feature parameters. Calculate the semantic similarity between concept feature parameters in the fault ontology. The specific steps are as follows: ; ; ; in, Conceptual feature parameters in the fault ontology arrive The comprehensive semantic distance; Conceptual feature parameters arrive semantic distance; Conceptual feature parameters arrive The shortest path is a directed edge; Number the directed edges of the shortest path; This represents the total number of directed edges in the shortest path. These are the first concept feature parameters; These are the characteristic parameters of the second concept; Conceptual feature parameters To concept feature parameters The maximum semantic distance; This is the root node of the aviation equipment fault concept tree; Conceptual feature parameters in the fault ontology to the root node semantic distance; The root node in the faulty entity To concept feature parameters semantic distance; Conceptual feature parameters in the fault ontology With concept feature parameters Semantic similarity between them; As a regulating factor; Conceptual feature parameters in the fault ontology To concept feature parameters Semantic distance.

[0014] Preferably, step S3 specifically includes: S31: The correspondence matching of the feature parameters of the fault body data of aviation equipment is to perform data correspondence matching on Boolean type, enumeration type, numerical type and date and time type data feature parameters to obtain the similarity function of the data feature parameter correspondence matching; S32: To perform fuzzy matching of the feature parameters of the fault body data of aviation equipment, it is necessary to divide the limited interval of the set domain and obtain the similarity between the two data feature parameters through the similarity function of fuzzy matching of data feature parameters. S33: Use word matching to quantify and calculate the similarity of text data feature parameters; perform real word matching of text data feature parameters; and obtain the similarity of text data feature parameters.

[0015] Preferably, step S5 specifically involves: setting the weights of each concept feature parameter and the semantic similarity threshold of the search results to filter the search results and improve the accuracy of semantic retrieval; removing the result instances in step S4 whose semantic similarity is less than the similarity threshold to obtain the final set of semantic retrieval result instances; sorting the similarity from largest to smallest and outputting the semantic retrieval results of the aviation equipment fault ontology; and determining the type of aviation equipment fault based on the semantic retrieval results of the aviation equipment fault.

[0016] On the other hand, the present invention provides a fault analysis system for an aviation equipment fault analysis method based on ontology semantic retrieval, which includes: a fault ontology module, an attribute weight and similarity threshold setting module, a fault data semantic retrieval module, and an aviation equipment fault judgment output module. The Fault Ontology module is used to manipulate and view aviation equipment fault ontology data, including the structural construction of concepts, relationships, attributes, and instances of aviation equipment fault ontology; The attribute weight and similarity threshold setting module is used to set the weight of the aviation equipment fault ontology concept attribute corresponding to the aviation equipment fault data retrieval item and the semantic similarity threshold of the retrieval results, so as to perform semantic similarity calculation between aviation equipment fault data and retrieval conditions and filter retrieval results. The fault data semantic retrieval module is an interactive module between the fault analysis system and semantic retrieval. By combining the aviation equipment fault ontology model with semantic retrieval, it realizes a similarity method based on semantic distance for matching concept feature parameters. It inputs search conditions, calls the fault ontology module, attribute weight and similarity threshold setting module to perform semantic similarity calculation, and outputs the aviation equipment fault ontology semantic retrieval results. The aviation equipment fault diagnosis output module compares the aviation equipment fault ontology semantic retrieval results output by the fault data semantic retrieval module with the aviation equipment fault conditions to determine the type of aviation equipment fault.

[0017] Compared with the prior art, the beneficial effects of the present invention are as follows: (1) This invention can solve the problem of comprehensive and accurate retrieval of aviation equipment fault data. In view of the problems of low retrieval efficiency and lack of accuracy and comprehensiveness of retrieval results in traditional information retrieval technology, this invention introduces a set of standardized concepts of fault data ontology to standardize the retrieval conditions and transform them into concepts in ontology rule constraints. This transforms the actual fault data retrieval into the matching of concepts and their semantics in the fault ontology library. It is a search and reasoning process at the semantic layer of fault data. By using a set of standardized concepts for retrieval, the recall and precision of fault data retrieval can be effectively improved.

[0018] (2) This invention establishes an ontology-based semantic retrieval model from the aspects of semantic expansion and semantic matching. It proposes a concept matching similarity method based on semantic distance by combining the depth and density factors of the ontology model, as well as a semantic retrieval method and its implementation process based on this. Through the fault analysis system function, it provides user-oriented fault data semantic retrieval application support, realizes comprehensive and accurate retrieval of fault data, and provides strong support for solving fault problems. Attached Figure Description

[0019] Figure 1 This is a flowchart illustrating the aviation equipment fault analysis method based on ontology semantic retrieval of the present invention. Figure 2 This is a structural diagram of the aircraft equipment fault model of the present invention; Figure 3 This is a schematic diagram of the basic semantic relationships of the aviation equipment fault entity in this invention; Figure 4 This is a schematic diagram illustrating the domain-specific semantic relationships of the aviation equipment fault ontology in this invention; Figure 5 This is a schematic diagram illustrating the actual semantic distance of the hierarchical relationship involving depth and density factors in this invention. Detailed Implementation

[0020] Hereinafter, embodiments of the present invention will be described with reference to the accompanying drawings.

[0021] This invention proposes a method for analyzing aviation equipment faults based on ontology semantic retrieval, such as... Figure 1 As shown, an aviation equipment fault ontology model is established, search conditions are set, and fault ontology feature parameters are determined; semantic data matching of aviation equipment fault ontology conceptual feature parameters is performed; aviation equipment fault ontology data feature parameter matching is performed; weighted semantic similarity of aviation equipment fault ontology conceptual feature parameters is calculated; aviation equipment fault type is determined, and aviation equipment fault processing is assisted; the process includes the following steps: Step S1: Establish an aircraft equipment fault ontology model, set search conditions, and determine fault ontology characteristic parameters.

[0022] Based on ontology modeling and semantic analysis, the knowledge sources of the aviation equipment fault ontology are analyzed. The ontology consists of five elements: concepts, relations, functions, axioms, and instances. Concepts form a classification hierarchy, and relations, functions, and axioms express the relationships and constraints between concepts. According to the constituent elements of the ontology, the sources of aviation equipment fault knowledge include: fault-related standards and specifications, comprehensive and professional thesaurus, fault-related engineering design and information management systems, fault-related expert experience and knowledge, literature such as books, papers, and reports, and online information resources; and fault-related engineering design and information management systems such as PDM, CAX, ERP, MES, and other fault-related information systems.

[0023] like Figure 2 The diagram shows an aviation equipment fault ontology model. This model uses ontology methods to express and organize knowledge about aviation equipment faults. The aviation equipment fault ontology model constructed in this invention consists of a product domain ontology, a case domain ontology, a diagnostic domain ontology, and a fault core ontology reflecting the essential characteristics of faults. In the aviation equipment fault ontology model, the fault core sub-ontology reflects the essential characteristics of faults and consists of five core concepts: faulty product, fault mode, fault cause, fault impact, and fault handling. The product domain sub-ontology describes the concepts and relationships related to faults, such as aviation products and equipment structures, mainly including core concepts and relationships related to aviation products and equipment structures. The case domain sub-ontology describes the concepts and relationships related to actual faults, mainly including core concepts and relationships related to fault scenarios, support resources, and fault operations. The diagnostic domain sub-ontology describes the concepts and relationships of aircraft fault diagnosis models, mainly including core concepts and relationships related to system models, fault detection models, and fault propagation models. There are overlapping concepts and relationships among the sub-ontologies, expressing complete and consistent knowledge of the aviation equipment fault domain.

[0024] The retrieval items of aviation equipment fault data are converted into feature parameter items of the aviation equipment fault ontology model; the retrieval values ​​of aviation equipment fault data are converted into feature parameter values ​​of the fault ontology. In the aviation equipment fault ontology model, the feature parameters of aviation equipment fault data are divided into conceptual feature parameters and data feature parameters. If the retrieval items of aviation equipment fault data correspond to the conceptual feature parameters of the fault ontology, then step S2 is executed. If the retrieval items of aviation equipment fault data correspond to the data feature parameters of the fault ontology, then step S3 is executed.

[0025] Step S2: Expand the semantic data and matching of the feature parameters of the aviation equipment fault ontology concept, such as... Figure 3 The diagram illustrates the semantic data expansion and matching implementation steps for the conceptual feature parameters of aviation equipment fault ontology in this embodiment of the invention, specifically including the following sub-steps: Step S21: Expand the semantic data of the conceptual feature parameters of the aviation equipment fault ontology. This includes types such as data synonym expansion, feature parameter expansion, hierarchical expansion, axiom expansion, and rule expansion, resulting in a fault concept tree or fault network diagram in the aviation equipment fault data space. The complex semantic data relationships between the conceptual feature parameters of various aviation equipment fault ontology concepts are organized into a semantic data network diagram. Conceptual feature parameters are represented as nodes, and the connections between nodes represent the relationships between these conceptual feature parameters. Semantic data retrieval enables retrieval of a single point based on search criteria. The semantic data relationship network, through semantic data expansion, transforms into the retrieval of a semantic feature surface of aviation equipment faults.

[0026] Step S22: Calculate the depth factor and density factor of the conceptual feature parameters of the aviation equipment fault ontology to determine the semantic distance between the conceptual feature parameters. The semantic distance of the conceptual feature parameters of the aviation equipment fault ontology refers to the path length connecting two conceptual feature parameters in the directed weighted conceptual feature parameter network graph, i.e., the sum of the weights of all edges on the path connecting these two conceptual feature parameters. It is used to quantitatively describe the strength of the correlation between conceptual feature parameters. The semantic distance is related to the number, type, and direction of edges in the path connecting the nodes of the conceptual feature parameters, as well as the depth and density of the nodes. In the aviation equipment fault ontology model, different semantic relationships correspond to different semantic distances, including basic relationships such as synonymy, superordinate, subordinate, and related relationships, as well as special semantic relationships in areas such as fault causality, product structure, problem-solving, product replacement, and case reference. The complex semantic relationships between the various conceptual feature parameters of the aviation equipment fault ontology form a semantic data network graph, in which the conceptual feature parameters are represented as nodes, and the directed edges between nodes represent the aforementioned relationships. The weights on the edges are the semantic distances. A semantic distance baseline value is first set for superordinate and subordinate relationships.

[0027] This embodiment of the invention determines that the fault data object to be retrieved is aircraft fault data, such as... Figure 4 The diagram shown illustrates the basic semantic relationships of a fault ontology model. Aircraft fault data consists of a product domain ontology, a case domain ontology, a diagnostic domain ontology, and a core fault ontology reflecting the essential characteristics of the fault. These sub-domains overlap, representing a complete and consistent aircraft fault domain. Figure 3 The diagram illustrates the domain-specific semantic relationships of the fault ontology model. It shows the setting of semantic distances between concepts in the aircraft fault ontology, addressing basic relationships such as synonymy, superordinate, subordinate, and related relationships within the aircraft fault ontology. Figure 4The schematic diagram illustrates the special semantic relationships in the aircraft fault ontology, including fault causal relationships, product structure relationships, problem-solving relationships, product replacement relationships, and case reference relationships. The semantic distance values ​​of various conceptual feature parameter relationships are set as shown in Table 1. The semantic distance of the superior and subordinate relationships in the table is the baseline value. When considering depth factors and density factors, depth factors and density factors need to be added for comprehensive calculation to obtain the actual value.

[0028] Table 1. Semantic distance table of various conceptual relationships in the aircraft fault ontology. Synonyms 0 Superior position subclass Superclass 3* lower position Superclass subclass 5* Related kind Feature parameter class 7 Case Reference Fault Cases Fault Cases 1 Product Structure aviation products Aircraft Structure 2 Product replacement aviation products aviation products 1 Causes and effects of failure Cause of the fault Failure Mode 6 Problem solved Failure Mode Troubleshooting 6 Step S221: Calculate the depth factor of the conceptual feature parameters of the aviation equipment fault ontology. In the hierarchical fault concept tree of the aviation equipment fault ontology conceptual feature parameters, the deeper the nodes of two conceptual feature parameters are in the classification hierarchy, the closer their relationship and the smaller their semantic distance; conversely, the deeper the nodes, the larger their semantic distance. The node depth of the conceptual feature parameters of the aviation equipment fault ontology refers to the level of the node of the conceptual feature parameter in the hierarchical fault concept tree. The depth of the root node is 1, the depth of its child nodes is 2, and so on. Conceptual feature parameters The depth is root node The depth is ,and =1. Fault concept tree depth of the aircraft equipment fault entity. This refers to the maximum number of levels of nodes in the fault concept tree, i.e. As the node depth of concept feature parameters increases, the semantic distance between concept feature parameters decreases; a depth factor reflecting the depth of concept hierarchy is set. The depth factor for calculating the conceptual characteristic parameters of the aircraft equipment fault ontology is as follows: For concept feature parameters The depth of the superordinate semantic relation concept features -1 is taken as the square root and then the reciprocal is taken to obtain the concept feature parameters. Hyper-semantic relation depth factor Since the root node of the aviation equipment fault concept tree has a depth of 1, and the root node does not have a superior relationship, the conceptual feature parameters... It cannot be the root node, that is... >1; The higher-level semantic relation depth factor of the concept feature parameter C is obtained as: ; in, Conceptual feature parameters The depth factor of the higher-level semantic relation; For the conceptual characteristic parameters of the fault body of aviation equipment; Conceptual feature parameters The depth.

[0029] For concept feature parameters depth To obtain the concept feature parameters, take the square root and then the reciprocal. Hypo-semantic relation depth factor Due to the concept tree of aircraft equipment failure The depth of the bottom leaf nodes is Furthermore, they do not have a subordinate relationship, therefore the conceptual characteristic parameters It cannot be a bottom-level leaf node, i.e. < ; Obtain concept feature parameters The depth factor of the subordinate semantic relation is: ; in, Conceptual feature parameters The depth factor of the subordinate semantic relation; Fault concept tree for aviation equipment The depth; A concept tree for aircraft equipment failures.

[0030] In the concept tree of aviation equipment faults, the root node does not have a higher-level semantic relationship, and the bottom-level nodes do not have a lower-level semantic relationship.

[0031] Step S222: Calculate the density factor of the conceptual feature parameters of the aviation equipment fault ontology; In the fault concept tree of the conceptual feature parameters of the aviation equipment fault ontology, the region density is generally different, that is, the coarseness of the description of the conceptual feature parameters is uneven; When the density of a certain conceptual feature parameter node is larger, it indicates that the concept feature parameter is more refined, the similarity between its subdivided nodes is greater, and the semantic distance is smaller.

[0032] The density of conceptual feature parameter nodes in the aircraft equipment fault ontology refers to the out-degree of the parent node of that conceptual feature parameter node, i.e., the number of sibling nodes of that node that contain conceptual feature parameter nodes. Conceptual feature parameters The density is Its superior node is The out-degree of the parent node is Then the concept feature parameters The density is ,and It cannot be the root node. Correspondingly, the density of the fault concept tree... The out-degree of the node with the most child nodes, i.e. As the node density of concept feature parameters increases, the semantic distance between concept feature parameters decreases. A density factor β, reflecting the concept density factor, is set, and the density factor of the concept feature parameters of the aviation equipment fault ontology is calculated, specifically as follows: For concept feature parameters The parent node out of degree Take the reciprocal to obtain the concept feature parameters. Hyperordinate semantic relation density factor Since the root node of the aviation equipment fault concept tree has a depth of 1 and no hierarchical relationship, the conceptual characteristic parameters... It cannot be the root node, that is... >1; Obtain conceptual feature parameters The hyperordinate semantic relation density factor is: ; in, The hyperordinate semantic relation density factor of the concept feature parameter C; This is the parent node of the concept feature parameter C; Let C be the out-degree of the parent node of the concept feature parameter C.

[0033] For concept feature parameters out of degree Taking the reciprocal, we obtain the lower semantic relation density factor of the concept feature parameter C. Due to the concept tree of aircraft equipment failure The depth of the bottom leaf nodes is Furthermore, they do not have a subordinate relationship, therefore the conceptual characteristic parameters It cannot be a bottom-level leaf node, i.e. < The subordinate semantic relation density factor of the concept feature parameter C is: ; in, Conceptual feature parameters The hyponym semantic relation density factor; The depth of the concept tree for aircraft equipment failures; Conceptual feature parameters The degree of departure.

[0034] Step S223: Calculate the semantic distance between the conceptual feature parameters of the aviation equipment fault ontology; in the fault concept tree of the aviation equipment fault ontology conceptual feature parameters, calculate the conceptual feature parameters. Node-to-concept feature parameters The semantic distance of a node is as follows: The benchmark value of semantic distance between hierarchical relationships Multiplying by a combined adjustment coefficient that combines the depth factor and the density factor, we obtain the actual semantic distance of the hierarchical semantic relationship. The combined adjustment coefficient of depth factor and density factor is used as a conceptual feature parameter. Depth factor of hierarchical semantic relationship Add density factor Multiply by adjustment coefficient Adjustment coefficient The density factor is used to adjust the relative importance of the depth factor, and its value range is [0,1]. Based on the baseline values ​​of the superordinate and subordinate semantic relations, the depth factor, and the density factor, the actual semantic distance between the superordinate and subordinate semantic relations of each level of concepts is calculated as follows: ; in, This represents the actual semantic distance between the hierarchical semantic relationships. The baseline value for semantic distance in hierarchical relationships should be consistent with the fixed values ​​for semantic distance in other relationships. Conceptual feature parameters The depth factor of the hypernym semantic relationship is used to substitute the hypernym semantic relationship. Substitute the subordinate semantic relation ; Conceptual feature parameters The density factor of the hypernym semantic relationship is used to substitute the hypernym semantic relationship. Substitute the subordinate semantic relation ; The adjustment coefficient modifies the relative importance of density factors compared to depth factors. Density factors have a smaller impact on semantic distance than depth factors. The value range is [0,1].

[0035] like Figure 4 The illustration shows the application of the method proposed in this invention in an embodiment, calculating the concept depth factor and concept density factor between concepts in the aircraft fault ontology, and then calculating the actual semantic distance of the hierarchical relationship. It also calculates the comprehensive semantic distance between the concept feature parameters of the aviation equipment fault ontology; concept feature parameters... To concept feature parameters The semantic distance is the concept feature parameter. Node-to-concept feature parameters The shortest path to the node is obtained from the ontology concept feature parameter graph using the Floyd-Warshall method. Node to The shortest path to a node, the sum of the weights of that shortest path, is the concept feature parameter graph. arrive The semantic distance. The Floyd method, also known as the interpolation method, is a method that uses dynamic programming to find the shortest path between multiple source points in a given weighted graph. Conceptual feature parameters in the fault ontology. arrive Comprehensive semantic distance for arrive The shortest path is the sum of the semantic distances of all directed edges. After determining the weights of all directed edges in the aviation equipment fault ontology network graph, the semantic distance between two concept feature parameter nodes is the shortest weighted path length; the comprehensive semantic distance between two concept feature parameters in the aviation equipment fault ontology is obtained as follows: ; in, Conceptual feature parameters in the fault ontology arrive The comprehensive semantic distance; Conceptual feature parameters Node to The sum of weighted distances of all edges in the shortest path of a node; Conceptual feature parameters arrive semantic distance; Conceptual feature parameters arrive The shortest path is a directed edge; Number the directed edges of the shortest path; This represents the total number of directed edges in the shortest path. These are the first concept feature parameters; These are the characteristic parameters of the second concept.

[0036] like Figure 5 The figure shows the calculation of the comprehensive semantic distance between two concepts using the comprehensive semantic distance calculation function proposed in this invention. In the example, the shortest path value of the semantic distance from "aviation product" to "support resource" is 7; the semantic distance from "avionics product" to "mechanical product" is 2.42+4.04=6.46, and the semantic distance from "support resource" to "failure cause" is 3.13+5.21=8.34. It can be seen that the semantic distance between co-occurring concepts with deeper levels is small; the semantic distance between the synonyms "engine" and "engine engine" is 0.

[0037] Step S23: Calculate the semantic data similarity between the conceptual feature parameters of the aviation equipment fault ontology, and perform semantic data matching of the conceptual feature parameters of the aviation equipment fault ontology. The core of semantic data matching lies in correctly and objectively setting and quantifying the degree of semantic data similarity between conceptual feature parameters. Semantic data similarity is the substitutability and semantic conformity of the vocabulary of conceptual feature parameters. It reflects the similarity of two conceptual feature parameters in semantic data. The higher the semantic similarity, the higher the matching degree. The semantic similarity between two conceptual feature parameters can be measured by the semantic distance between them. That is, the smaller the semantic distance between two conceptual feature parameters, the greater their semantic similarity. The purpose of calculating the semantic distance between the conceptual feature parameters of the aviation equipment fault ontology is to calculate the semantic similarity between them. The semantic similarity function is used to convert the semantic distance between the conceptual feature parameters of the aviation equipment fault ontology into the semantic similarity between them.

[0038] Calculate the maximum semantic distance between conceptual feature parameters in the aviation equipment fault ontology. In the aviation equipment fault ontology, all conceptual feature parameters share a common root node. When the semantic distance between two conceptual feature parameters is equal to the sum of their semantic distances to the root node, it indicates that the two conceptual feature parameters have little similarity other than being conceptual feature parameters. This situation is defined as having a similarity of 0, i.e., the maximum semantic distance. The maximum semantic distance between conceptual feature parameters in the aviation equipment fault ontology is the sum of the semantic distance from one conceptual feature parameter node to the root node through its superior relation and the semantic distance from the root node to another conceptual feature parameter node through its subordinate relation. To concept feature parameters maximum semantic distance These are conceptual feature parameters in the fault ontology. to the root node semantic distance With the root node To concept feature parameters semantic distance The summation of the features. Conceptual characteristic parameters. Node-to-concept feature parameters The maximum semantic distance between nodes is specifically: ; in, Conceptual feature parameters To concept feature parameters The maximum semantic distance; This is the root node of the aviation equipment fault concept tree; Conceptual feature parameters in the fault ontology to the root node semantic distance; The root node in the faulty entity To concept feature parameters Semantic distance.

[0039] Since a subclass in the aircraft equipment body can inherit multiple superclasses, when calculating the maximum semantic distance, it is necessary to first determine the fault concept tree to which the two concept feature parameters belong, and take the fault concept tree with the smallest node depth of the concept feature parameters as the standard.

[0040] Calculate the semantic data similarity of conceptual feature parameters of the fault ontology of aviation equipment. The semantic similarity calculation function must satisfy several characteristics: the function output range is [0, 1]; the semantic similarity is 1 when the semantic distance is 0; the semantic similarity is 0 when the semantic distance is the maximum semantic distance Dmax; semantic similarity decreases with semantic distance, that is, semantic similarity decreases as the semantic distance increases. Conceptual feature parameters in the fault ontology. With concept feature parameters semantic similarity between It is 1 minus the conceptual feature parameters in the fault entity. To concept feature parameters Comprehensive semantic distance and arrive The opening of the maximum semantic distance ratio Power; Regulatory factor This is used to adjust the rate at which semantic similarity decreases as semantic distance increases, and its value range is positive integers; the semantic similarity calculation function proposed in this invention is: ; in, Conceptual feature parameters in the fault ontology With concept feature parameters Semantic similarity between them; It is a moderating factor used to adjust the rate at which semantic similarity decreases as semantic distance increases; The root node in the faulty entity To concept feature parameters Semantic distance.

[0041] By applying the computational function proposed in this invention, the maximum semantic distance between concept feature parameters is calculated, thereby obtaining the semantic similarity between concept feature parameters. (Refer to...) Figure 5 If we take the parameter θ=1 in the semantic similarity calculation function, the following is an example of similarity calculation between some conceptual feature parameter classes of the aircraft fault ontology.

[0042] The semantic distance, i.e. the shortest path value, between the concept feature parameters of "aviation products" and "support resources" is 7, and the maximum semantic distance is 3.13 + 5.21 = 8.34. Therefore, the semantic similarity between the concept feature parameters of "aviation products" and "support resources" is 1 - (7 / 8.34) = 0.16.

[0043] The semantic distance between the conceptual feature parameters of “avionics products” and “mechanical products” is 2.42 + 4.04 = 6.46, and the maximum semantic distance is 2.42 + 3.13 + 5.21 + 4.04 = 14.8. Therefore, the semantic similarity between the conceptual feature parameters of “avionics products” and “mechanical products” is 1 - (6.46 / 14.8) = 0.56.

[0044] The semantic distance between the conceptual feature parameters of “resource protection” and “failure cause” is 8.34. The maximum semantic distance is 8.34. Therefore, the semantic similarity between the conceptual feature parameters of “resource protection” and “failure cause” is 1-(8.34 / 8.34)=0, which means they are completely dissimilar.

[0045] The semantic distance between the feature parameters of the concepts “engine” and “engine” is 0, and the maximum semantic distance is 19.86. The semantic similarity between the feature parameters of the concepts “engine” and “engine” is 1-(0 / 19.86)=1, which means they are completely similar.

[0046] Step S3: Perform feature parameter matching of the aircraft equipment fault data; such as... Figure 4 The diagram illustrates the steps for matching feature parameters in the fault ontology data. The value range of these feature parameters encompasses various data types. Data types in the aviation equipment fault ontology include Boolean, enumerated, numeric, date / time, and string types. Semantic similarity matching methods for the feature parameters include correspondence matching, fuzzy matching, and text matching. A suitable matching method is selected based on the specific application. The steps include the following sub-steps: Step S31: Perform correspondence matching of the data feature parameters of the aircraft equipment fault ontology. Since quantifiable data feature parameters are themselves a precise description of the state of things, they can be directly mathematically calculated. In principle, each data value is dissimilar to other unequal data values. Therefore, for quantifiable data feature parameters, a correspondence matching method is used to calculate the similarity. In the fault ontology, data feature parameters of Boolean, enumeration, numeric, and date / time types are matched. The similarity function for the data feature parameter correspondence matching is as follows: ; in, Data feature parameters With data feature parameters The corresponding semantic similarity between them; This is the first characteristic parameter of aviation equipment fault data; This is the second characteristic parameter for aviation equipment fault data.

[0047] Step S32: Perform fuzzy matching of the feature parameters of the aviation equipment fault ontology data. Boolean and enumerated data feature parameters have discrete value ranges, while numerical and date / time data feature parameters can be both discrete and continuous. For quantifiable continuous data value ranges, intervals are divided. Data feature parameters within a given interval have a certain similarity, while those outside the same interval are dissimilar—this is fuzzy matching of data feature parameters. Fuzzy matching avoids the loss of semantic similarity in corresponding matches within a certain range, achieving better semantic matching results. In the field of aviation equipment faults, due to numerous uncertainties, statistical data is often described using fuzzy interval values ​​or fuzzy semantics. For example, the mean time between failures (MTBF) of a product is described as "approximately 400 to 500 hours," or fuzzily described as "low failure rate." A finite interval is defined within a given domain, and the similarity between two data feature parameters is calculated. The similarity between two data feature parameters in different intervals is 0. The specific similarity function for fuzzy matching of data feature parameters is as follows: ; in, Data feature parameters With data feature parameters Fuzzy matching semantic similarity between them; For fuzzy finite intervals; The length of the fuzzy finite interval.

[0048] This invention embodiment matches data feature parameters in the aircraft fault body. An example of fuzzy data matching is as follows: the feature parameter values ​​of a certain duct's fluid pressure feature parameter are divided into three intervals: small, medium, and large, respectively [0,20), [20,60), and [60,+∞), with units of MPa. Then, if the data feature parameter... =30, data feature parameters =50, because , If all values ​​are within the interval [20, 60), then the similarity is 1 - |30 - 50| / |60 - 20| = 1 - 20 / 40 = 0.5. If the data feature parameters... =30, data feature parameters =80, due to , If they are not in the same defined range, the similarity is 0.

[0049] Step S33: Perform feature parameter matching for the text data of the aircraft equipment fault entity. Since string text data feature parameters are difficult to match directly, a word-based matching method is used to quantify and calculate the similarity of the text data feature parameters. The text data feature parameters are first segmented and replaced, and then the content words contained in two text data feature parameters are compared to calculate the matching degree between the two text data. Specifically: The text data feature parameters are decomposed into words and function words are removed. The segmented words are replaced with entries from a thesaurus to ensure that words with the same meaning have the same expression. The thesaurus is obtained from comprehensive or specialized thesauruses, such as the *NASA Thesaurus*, *National Defense Science and Technology Thesaurus*, *Aerospace Science and Technology Data Thesaurus*, and *Military Logistics Thesaurus*. Content word matching of the text data feature parameters is performed. The similarity of the text data feature parameters is calculated, defined as the number of identical or synonymous content words in two text data feature parameters divided by the average number of content words in the two text data feature parameters. Specifically, the text data feature parameter similarity is: ; in, Text data feature parameters Text data feature parameters Semantic similarity of textual data between them; These are the feature parameters of the first aircraft equipment fault text data. These are the feature parameters of the first aircraft equipment fault text data. Text data feature parameters The number of content words in the text; Text data feature parameters The number of content words in the text; Text data feature parameters and text data feature parameters The number of content words that are substantially the same in the example means identical or synonymous.

[0050] An example of matching feature parameters for aviation equipment fault text data in this embodiment of the invention is as follows: For instance, the faults described in "the thrust cable of engine number 2 is worn and broken" and "the thrust cable of the right engine is broken" are semantically identical, but their expressions are not exactly the same. Directly matching the text data will not lead to the conclusion that they are the same. Therefore, it is necessary to first perform word segmentation and replacement processing on the text data, and then calculate the matching degree between the two text data by comparing the content words contained in the two text data. Word segmentation processing involves decomposing the text data into words and removing function words. For example, =“The thrust cable of engine No. 2 wore out and broke”, after word segmentation, is =“Engine No. 2 ~ Thrust Cable ~ Wear ~ Breakage”; Replacement processing: Replace the segmented words with entries from the thesaurus, such as replacing “Engine No. 2” with “Right Engine”, and “Thrust Cable” with “Thrust Cable”, the purpose being to ensure that words with the same meaning have the same expression; Content word matching: Calculate the similarity of text data feature parameters, apply the text matching similarity function proposed in this invention, after word segmentation and replacement processing. =“Right engine ~ thrust cable ~ wear ~ breakage” =“Right engine ~ thrust cable ~ broken”, then Count( )=4,Count( )=3, Count(S)=3, calculate to obtain text data and The match score is 0.86.

[0051] Step S4: After performing the processing steps S2 and S3 on the ontology concept feature parameters and data feature parameters corresponding to all search conditions, sum up the similarity of all feature parameters of each result instance, and then normalize the weights of all search feature parameters to obtain the semantic similarity of the search result instance to all search conditions. Calculate the weighted semantic similarity of the ontology concept feature parameters of aviation equipment faults.

[0052] Semantic retrieval of the aviation equipment fault ontology involves instance retrieval of the conceptual feature parameters corresponding to the search criteria in the aviation equipment fault domain. Specifically, it calculates the similarity between different instances of the same conceptual feature parameter, representing a comprehensive calculation of the similarity between feature parameters of instances. The weighted semantic similarity of the conceptual feature parameters of the aviation equipment fault ontology is as follows: ; in, Examples of failures in aviation equipment and examples The similarity between them; For the first The weights of each feature parameter; For the first The semantic similarity function of each feature parameter value corresponds to the conceptual similarity of the concept feature parameters or the semantic similarity of the data feature parameters; This is an example of a fault in the first type of aviation equipment. This is an example of a faulty component in the second type of aviation equipment. For the retrieval feature parameter number; To retrieve the total number of feature parameters.

[0053] This invention, after calculating the similarity of conceptual feature parameters and data feature parameters for all search conditions, calculates the weighted semantic similarity of the ontological feature parameters of aviation equipment faults, and then outputs a set of semantic search result instances sorted by similarity. For example, in aircraft fault data retrieval, taking the faulty component as "landing gear lifting actuator hydraulic conduit," the corresponding ontological concept depth is 5 and density is 6; the fault mode as "leakage," corresponding to an ontological concept depth of 6 and density of 3; and the occurrence timing as "static maintenance," an enumerated data feature parameter, and using corresponding matching as the search condition, a semantic search is performed on the database of real aviation equipment fault cases handled by the enterprise within a certain time period. Six semantically similar fault cases are obtained, with similarities of 1.0, 0.87, 0.76, 0.76, 0.69, and 0.63, respectively. The feature parameter values ​​of the result fault case with a similarity of 1.0 are exactly the same as the search conditions, while the feature parameter values ​​of the other result cases differ from the search conditions. When dealing with fault problems, considering the actual situation of aviation equipment fault problems, appropriate cases are selected from the set of similar cases obtained through semantic search as troubleshooting references.

[0054] Step S5: Based on the semantic retrieval results of aviation equipment failures, determine the type of aviation equipment failure. Remove the result instances from Step S4 whose semantic similarity is less than the similarity threshold, and obtain the final semantic retrieval result instance set. Sort the results by similarity from largest to smallest and output the semantic retrieval results of the aviation equipment failure ontology.

[0055] Before performing semantic retrieval for ontology matching of aviation equipment faults, it is necessary to determine the search terms, i.e., concept feature parameters, and set the weights of each concept feature parameter and the semantic similarity threshold of the search results. Here, concept feature parameters represent a certain aspect of a concept's properties, the weights of concept feature parameters reflect the importance of each feature of the concept, and the semantic similarity threshold is used to filter search results to improve the accuracy of semantic retrieval.

[0056] The second aspect of this invention provides a fault analysis system for an aviation equipment fault analysis method based on ontology semantic retrieval, which includes: a fault ontology module, an attribute weight and similarity threshold setting module, a fault data semantic retrieval module, and an aviation equipment fault judgment output module.

[0057] The Fault Ontology module is used to operate and view aviation equipment fault ontology data, including the construction, graphical display, consistency verification, and inference rule setting of the structure and content of aviation equipment fault ontology such as concepts, relationships, attributes, and instances, providing a foundation for semantic retrieval of aviation equipment faults.

[0058] The attribute weight and similarity threshold setting module is used to set the weight of the aviation equipment fault ontology concept attribute corresponding to the aviation equipment fault data retrieval item and the semantic similarity threshold of the retrieval results. This supports the semantic similarity calculation of aviation equipment fault data and retrieval conditions, as well as the filtering of retrieval results, in order to improve the accuracy of semantic retrieval.

[0059] The fault data semantic retrieval module is an interactive module between the fault analysis system and semantic retrieval. By combining the aviation equipment fault ontology model with semantic retrieval, it realizes a similarity method based on semantic distance for matching concept feature parameters. This module inputs search conditions, calls the fault ontology module, attribute weight and similarity threshold setting module to calculate semantic similarity, and outputs the aviation equipment fault ontology semantic retrieval results.

[0060] The aviation equipment fault diagnosis output module compares the aviation equipment fault ontology semantic retrieval results output by the fault data semantic retrieval module with the aviation equipment fault conditions to determine the specific fault type of the aviation equipment.

[0061] The beneficial effects of the embodiments of this invention are as follows: Addressing the problems of low retrieval efficiency and lack of accuracy and comprehensiveness in traditional information retrieval technologies, this invention introduces a standardized concept set for fault data ontology to standardize retrieval conditions, transforming them into concepts within ontology rule constraints. This transforms actual fault data retrieval into matching concepts and their semantics within the fault ontology database, representing a search and reasoning process at the semantic layer of fault data. The embodiments demonstrate that this method can solve the problem of comprehensive and accurate retrieval of aviation equipment fault data, effectively improving the recall and precision of fault data retrieval. This invention establishes an ontology-based semantic retrieval model from aspects such as semantic expansion and semantic matching. It also proposes a concept matching similarity method based on semantic distance, combined with the depth and density factors of the ontology model, and a semantic retrieval method and its implementation process based on this. Through the functions of the fault analysis system, it provides user-oriented fault data semantic retrieval application support, achieving comprehensive and accurate retrieval of fault data and providing strong support for solving fault problems. The implementation process of the embodiments demonstrates that this method can effectively achieve aviation equipment fault retrieval and meet practical engineering needs.

[0062] The embodiments described above are merely preferred embodiments of the present invention and are not intended to limit the scope of the present invention. Various modifications and improvements made by those skilled in the art to the technical solutions of the present invention without departing from the spirit of the present invention should fall within the protection scope defined by the claims of the present invention.

Claims

1. An aviation equipment fault analysis method based on ontology semantic retrieval, characterized in that: It includes the following steps: S1: Establish a fault ontology model for aviation equipment, set search conditions, and determine the fault ontology characteristic parameters; If the retrieval item of the aviation equipment fault data corresponds to the conceptual feature parameters of the fault entity, then proceed to step S2; if the retrieval item of the aviation equipment fault data corresponds to the data feature parameters of the fault entity, then proceed to step S3. S2: Expand the semantic data of the feature parameters of the aviation equipment fault ontology concept, calculate the depth factor and density factor of the feature parameters of the aviation equipment fault ontology concept, determine the semantic distance between the feature parameters of the fault ontology concept, calculate the semantic similarity between the feature parameters of the aviation equipment fault ontology concept, and perform semantic matching of the feature parameters of the aviation equipment fault ontology concept. In step S2, the depth factors of the conceptual feature parameters of the aviation equipment fault ontology specifically include: a higher-level semantic relationship depth factor and a lower-level semantic relationship depth factor; the higher-level semantic relationship depth factor is determined through the root node of the aviation equipment fault concept tree, and the lower-level semantic relationship depth factor is determined through the bottom-level leaf nodes of the aviation equipment fault concept tree, specifically as follows: ； ； in, Conceptual feature parameters The depth factor of the higher-level semantic relation; For the conceptual characteristic parameters of the fault body of aviation equipment; Conceptual feature parameters The depth; Conceptual feature parameters The depth factor of the subordinate semantic relation; Fault concept tree for aviation equipment The depth; A concept tree for aircraft equipment failures; In step S2, the density factors of the feature parameters of the aviation equipment fault ontology concept include: a higher-level semantic relation density factor and a lower-level semantic relation density factor. The higher-level semantic relation density factor is determined through the root node of the aviation equipment fault concept tree, and the lower-level semantic relation density factor is determined through the bottom-level leaf nodes of the aviation equipment fault concept tree, specifically: ； ； in, The hyperordinate semantic relation density factor of the concept feature parameter C; This is the parent node of the concept feature parameter C; Let C be the out-degree of the parent node of the concept feature parameter C; Conceptual feature parameters The hyponym semantic relation density factor; Conceptual feature parameters The degree of departure; S3: Perform fault body data feature parameter matching for aviation equipment, specifically including: corresponding matching of data feature parameters, fuzzy matching of data feature parameters, and matching of text data feature parameters; S4: Perform steps S2 and S3 respectively on the conceptual feature parameters and data feature parameters of the aviation equipment fault ontology. After summing the similarity of the obtained feature parameters, normalize the weights of all search feature parameters and calculate the weighted semantic similarity of the conceptual feature parameters of the aviation equipment fault ontology. Specifically: ； in, Examples of failures in aviation equipment and examples Weighted semantic similarity between them; For the first The weights of each feature parameter; For the first A semantic similarity function for each feature parameter; This is an example of a fault in the first type of aviation equipment. This is an example of a faulty component in the second type of aviation equipment. For the retrieval feature parameter number; To retrieve the total number of feature parameters; S5: Based on the semantic search results of aviation equipment failures in step S4, determine the type of aviation equipment failure.

2. The ontology-based semantic retrieval based aviation equipment failure analysis method according to claim 1, characterized in that: Step S2 is as follows: S21: Semantic data for the feature parameters of the concept of fault ontology of aviation equipment, specifically including: data synonym expansion, feature parameter expansion, hierarchical expansion, axiom expansion and rule expansion; S22: Calculate the depth factor and density factor of the feature parameters of the fault ontology concept of aviation equipment, and determine the semantic distance between the feature parameters of the fault ontology concept. S23: Calculate the semantic similarity between the feature parameters of the aviation equipment fault ontology concept, and perform semantic matching of the feature parameters of the aviation equipment fault ontology concept.

3. The ontology-based semantic retrieval based aviation equipment failure analysis method according to claim 2, characterized in that: Step S22 is as follows: S221: Determine the conceptual characteristic parameters of the aircraft equipment fault ontology The depth is ; Depth factor for setting the concept level depth factor Calculate the depth factor of the conceptual characteristic parameters of the fault ontology of aviation equipment; S222: Determine the conceptual characteristic parameters of the aircraft equipment fault ontology The density is ; Set the density factor β of the concept density factor, and calculate the density factor of the conceptual characteristic parameters of the aircraft equipment fault ontology; S223: Calculate the fault ontology concept feature parameters of aviation equipment within the fault concept tree of the aviation equipment fault ontology concept feature parameters. Node-to-concept feature parameters The semantic distance of nodes yields the comprehensive semantic distance between the feature parameters of two concepts in the aviation equipment fault ontology. .

4. The ontology-based semantic retrieval based aviation equipment failure analysis method according to claim 3, characterized in that: Step S223 sets the baseline value of the semantic distance between the hierarchical relationship. Multiplying by a combined adjustment coefficient that combines the depth factor and the density factor, we obtain the actual semantic distance of the hierarchical semantic relationship. The combined adjustment coefficient of depth factor and density factor is used as a conceptual feature parameter. Depth factor of hierarchical semantic relationship Add density factor Multiply by adjustment coefficient Specifically: ； in, This represents the actual semantic distance between the hierarchical semantic relationships. This serves as the baseline value for the semantic distance between hierarchical relationships.

5. The ontology-based semantic retrieval based aviation equipment failure analysis method according to claim 2, characterized in that: Step S23 is as follows: Calculate the comprehensive semantic distance between concept feature parameters in the fault ontology. The comprehensive semantic distance is the sum of the semantic distances of all directed edges of the shortest path between concept feature parameters. Calculate the semantic similarity between concept feature parameters in the fault ontology. The specific steps are as follows: ； ； ； in, Conceptual feature parameters in the fault ontology arrive The comprehensive semantic distance; Conceptual feature parameters arrive semantic distance; Conceptual feature parameters arrive The shortest path is a directed edge; Number the directed edges of the shortest path; This represents the total number of directed edges in the shortest path. These are the first concept feature parameters; These are the characteristic parameters of the second concept; Conceptual feature parameters To concept feature parameters The maximum semantic distance; This is the root node of the aviation equipment fault concept tree; Conceptual feature parameters in the fault ontology to the root node semantic distance; The root node in the faulty entity To concept feature parameters semantic distance; Conceptual feature parameters in the fault ontology With concept feature parameters Semantic similarity between them; It is a regulating factor.

6. The ontology-based semantic retrieval based aviation equipment failure analysis method according to claim 1, characterized in that: Step S3 is as follows: S31: The correspondence matching of the feature parameters of the fault body data of aviation equipment is to perform data correspondence matching on Boolean type, enumeration type, numerical type and date and time type data feature parameters to obtain the similarity function of the data feature parameter correspondence matching; S32: To perform fuzzy matching of the feature parameters of the fault body data of aviation equipment, it is necessary to divide the limited interval of the set domain and obtain the similarity between the two data feature parameters through the similarity function of fuzzy matching of data feature parameters. S33: Use word matching to quantify and calculate the similarity of text data feature parameters; perform real word matching of text data feature parameters; and obtain the similarity of text data feature parameters.

7. The ontology-based semantic retrieval based aviation equipment failure analysis method according to claim 1, characterized in that: Step S5 specifically involves: setting the weights of each concept feature parameter and the semantic similarity threshold of the search results to filter the search results and improve the accuracy of semantic retrieval; removing the result instances in step S4 whose semantic similarity is less than the similarity threshold to obtain the final set of semantic retrieval result instances; sorting the similarity from largest to smallest and outputting the semantic retrieval results of the aviation equipment fault ontology; and determining the type of aviation equipment fault based on the semantic retrieval results of the aviation equipment fault.

8. A failure analysis system for the ontology-based semantic retrieval based failure analysis method of one of claims 1 to 7, characterized in that It includes: The system includes a fault ontology module, an attribute weight and similarity threshold setting module, a fault data semantic retrieval module, and an aviation equipment fault judgment output module. The Fault Ontology module is used to manipulate and view aviation equipment fault ontology data, including the structural construction of concepts, relationships, attributes, and instances of aviation equipment fault ontology; The attribute weight and similarity threshold setting module is used to set the weight of the aviation equipment fault ontology concept attribute corresponding to the aviation equipment fault data retrieval item and the semantic similarity threshold of the retrieval results, so as to perform semantic similarity calculation between aviation equipment fault data and retrieval conditions and filter retrieval results. The fault data semantic retrieval module is an interactive module between the fault analysis system and semantic retrieval. By combining the aviation equipment fault ontology model with semantic retrieval, it realizes a similarity method based on semantic distance for matching concept feature parameters. It inputs search conditions, calls the fault ontology module, attribute weight and similarity threshold setting module to perform semantic similarity calculation, and outputs the aviation equipment fault ontology semantic retrieval results. The aviation equipment fault diagnosis output module compares the aviation equipment fault ontology semantic retrieval results output by the fault data semantic retrieval module with the aviation equipment fault conditions to determine the type of aviation equipment fault.

Images