Multi-scene fine-grained avionics fault characterization model dynamic generation method, medium, device and product

Abstract

The invention provides a multi-scene fine-grained avionics fault characterization model dynamic generation method, a medium, a device and a product. The method aims at universal and fine-grained modeling requirements, basic elements are analyzed and extracted, the incidence relation between the elements is determined, and an avionics fault characterization model is constructed; based on a fault analysis result, constructing a preliminary model by adopting a mode of combining forward and reverse analysis; updating and perfecting the avionics fault characterization model by adopting a mode of combining automatic recommendation and expert auditing based on continuously accumulated fault cases in the use stage; and displaying the avionics fault characterization model for different analysis scenes and user roles based on the multi-view fault map. According to the method, the avionics fault characterization model construction process is standard and modeled, construction of an avionics fault knowledge model is supported, the fault mechanism and the cross-linking relation embodied by the model can be applied to a fault diagnosis system, the fault isolation rate is increased, the troubleshooting time is shortened, and the maintenance efficiency is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of avionics equipment, and in particular to a method, medium, device and program product for dynamically generating a multi-scenario fine-grained avionics fault characterization model. Background Art

[0002] The product structure of avionics information equipment is complex, and the equipment is highly integrated. Due to the rapid iteration of avionics technology, there are many systems and products in different projects, and the failure mechanisms are different. The relationship between the underlying failure causes and the failure characterization is complex, which greatly increases the difficulty of fault analysis and fault diagnosis. At the same time, the application of avionics information equipment fault knowledge includes multiple scenarios such as user on-site whole machine troubleshooting, maintenance production line module fault location, and component failure analysis. Relevant personnel include field support personnel or users, maintenance production line engineers, fault location process personnel, etc. The description of the fault phenomenon has the characteristics of subjectivity, ambiguity, and incompleteness. The traditional fault case reporting form cannot meet the requirements. Therefore, it is urgent to build a multi-scenario fine-grained avionics fault characterization model. Summary of the invention

[0003] The present invention aims to provide a method, medium, device and product for dynamically generating a multi-scenario fine-grained avionics fault characterization model, so as to solve the problem that the fault characterization relationship in avionics equipment is complex and difficult to construct a model.

[0004] The present invention provides a method for dynamically generating a multi-scenario fine-grained avionics fault characterization model, comprising the following steps:

[0005] S1, in view of the subjectivity, ambiguity and incompleteness of user fault description, the concept of fault element is proposed to describe the fault phenomenon in a fine-grained manner, and the basic elements of the avionics fault characterization model are analyzed and extracted;

[0006] S2, defines the complex relationships between different fault factors at multiple levels of avionics complete machines, modules, and components, and builds an avionics fault characterization model;

[0007] S3, based on the results of fault impact relationship analysis, a preliminary avionics fault characterization model is constructed; on this basis, based on the accumulated fault cases during the use phase, the avionics fault characterization model is dynamically updated and improved by combining automatic recommendation with expert review;

[0008] S4, for different avionics fault characterization model analysis scenarios, proposes different analysis perspectives of cluster centers, and displays avionics fault characterization models for different analysis scenarios and user roles based on multi-analysis perspective fault maps.

[0009] Further, step S1 includes:

[0010] The avionics equipment fault knowledge files and specific fault cases are analyzed. Based on the characteristics of user fault descriptions, the avionics fault characterization model is characterized with the fine-grained fault element to ensure the standardization and generalization of the fault characterization model, and the following fault elements are proposed:

[0011] Failure mode: A standardized description of the failure phenomenon that occurs in a product and can be observed and measured;

[0012] Failure mode object: a product that experiences a certain failure mode;

[0013] Failure cause: the reason that caused the failure mode to occur;

[0014] Fault cause object: the component that causes the failure mode to occur;

[0015] Failure cases: specific failure events and handling processes that occurred during actual application;

[0016] Case fault phenomenon: description of the phenomenon of the specific fault case;

[0017] Standard fault cases: Classify specific fault cases by fault phenomenon to form standardized fault phenomenon description and handling methods;

[0018] Standard fault phenomenon: description of the phenomenon of standard fault cases;

[0019] Fault confirmation method: a method to determine whether the specific fault phenomenon of the product belongs to a certain type of standard fault case;

[0020] Fault location method: A method to determine the exact location or component where a product failure occurs;

[0021] Fault element: the smallest element describing a standard fault phenomenon;

[0022] Fault Element Alias: A non-standard name or alias for a fault element.

[0023] Further, step S2 includes:

[0024] The possible cross-linking and transmission relationships among fault elements, fault causes, fault phenomena and fault modes at multiple levels of avionics complete machines, modules and components are analyzed, and the relationships among the main fault elements are defined as follows:

[0025] Standard fault phenomenon - fault element: In the fault analysis stage, the smallest element that forms the standard fault phenomenon is the fault element. The fault element includes component units, functional signals, fault modes and fault conditions. Among them, the fault conditions include working parameters, occurrence timing, power supply type and fault status;

[0026] Failure case - Failure mode - Failure cause: By sorting out and analyzing the failure cases that have occurred, the corresponding failure mode and failure cause can be summarized;

[0027] Failure mode - standard failure phenomenon - failure cause: Through failure impact and cause analysis, confirm the relationship between the product's failure mode, failure phenomenon and failure cause from both positive and negative directions, that is, the product fault tree;

[0028] Fault case - fault element alias - fault element: In a specific fault case, the fault phenomenon is decomposed into several types of fault elements. The relationship between the fault element alias and the fault element is established by combining manual labeling and intelligent recognition, thereby establishing the relationship between the fault phenomenon and the fault element.

[0029] Further, step S3 includes:

[0030] Initially build an avionics fault characterization model: starting from the functions and signals of avionics products, analyze the product fault tree, and comprehensively consider the impact of fault mode, working parameters and fault conditions on fault phenomena, confirm the underlying cause of a certain type of fault mode under the corresponding working parameters and fault conditions; at the same time, store the smallest elements of these types of elements as fault elements, that is, group different types of fault elements into standard fault phenomena, and form a fault mode-standard fault phenomenon-fault cause relationship, such as Figure 2 As shown;

[0031] Dynamically update the avionics fault characterization model: First, based on the newly added cases of the project, identify the fault elements in the fault phenomenon through a combination of manual labeling and intelligent recognition, and build a fault case-fault element alias-fault element relationship; then, intelligently identify the fault causes of the newly added cases and whether the fault elements are incremental knowledge of the fault characterization model, and complete the dynamic update of the fault knowledge characterization model.

[0032] Further, the identifying of the fault element in the fault phenomenon includes:

[0033] On the construction side, based on the specific phenomena of the fault case, the fault element intelligent labeling software is used to manually establish the relationship between the fault element and the fault element alias, and then a fault element-fault element alias library is constructed by combining manual labeling and intelligent recognition.

[0034] On the user side, a prefix dictionary is jointly constructed based on the constructed fault element-fault element alias library and the open source Chinese natural language dictionary library; the input fault phenomenon is vectorized and converted into a directed acyclic graph; then, a path with the highest probability is found on the directed acyclic graph based on dynamic programming, and word segmentation is performed based on this path to identify all word sequences that may be fault element aliases; then, the longest common subsequence method is used to calculate the textual similarity between the word sequences of all possible fault element aliases extracted and all fault elements and their fault element aliases in the fault element-fault element alias library, and based on the set similarity measurement threshold, fault element-fault element alias similar pairs that are greater than the similarity measurement threshold are recommended to achieve intelligent matching of fault elements.

[0035] Furthermore, the dynamic update of the fault knowledge characterization model includes:

[0036] In the constructed avionics fault characterization model, let the standard fault phenomenon library be FP = {fp1, fp2, ..., fp n}, where fp i Represents a standard fault phenomenon in the standard fault phenomenon library. i It is composed of multiple fault elements, which constitute the standard fault phenomenon fp i The set of fault elements is Fe i ={fe 1 ,fe 2 ,...,fe m}, fe k It is the standard fault phenomenon fp i One of the faulty elements, and ΣFe i =fp i Denotes the fault element set Fe i Arrange and add according to a certain rule to form the standard fault phenomenon fp i ; Let FE be the large set of fault element sets that constitute the standard fault phenomenon in the entire avionics fault characterization model, then FE={fe1,fe2,...,fe n Let the fault cause library FR in the avionics fault characterization model be FR = {fr1, fr2, ..., fr s}, resulting in the standard failure phenomenon fp i There may be one or more reasons for the failure, which can be expressed mathematically as fp i ←{fr o ,fr p ,...,fr q}, where the fault cause {fr o ,fr p ,...,fr q}∈FR;

[0037] Let the failure reason of the newly added case be fr c , the identified fault element set is Fe c ={fe 1 ,fe 2 ,...,fe n}, the standard fault phenomenon composed of the fault element set is fp c , make the following judgment:

[0038] If fr c ∈FR, find fp in the library j ←fr c , fp j The corresponding fault element set is Fe j , and the fault element set Fe corresponding to the new case c ∈Fe j , then the avionics fault characterization model remains unchanged;

[0039] If fr c ∈FR, but This means that the newly added case adds a new fault element to the fault element set associated with the standard fault phenomenon in the library, and c With the result fp j Phase separation can increase fault isolation. The specific method is: let Fe s =Fe c ∪Fe j , if Fe s ∈FE, then first according to fp s =ΣFe s 、fp s ∈FP query fp s , add another fp s ←fr c relationship, and enter the sequence for expert review; if Then build fp first s =ΣFe s , and then construct fp s ←fr c Relationship, enter the sequence for expert review;

[0040] like But Fe c ∈Fe j , then first according to fp c =∑Fe c 、fp c ∈FP query fp c , add another fp c ←fr c relationship, and enter the sequence for expert review;

[0041] like but Then first add a new fault cause fr to the fault cause set FR c , then add fp to the fault phenomenon set FP c =∑Fe c , and finally construct fp c ←fr c Relationship, enter the sequence for expert review.

[0042] Further, step S4 includes:

[0043] On-site whole machine troubleshooting scenario: centered on specific fault cases, it displays the integration of single fault cases, including fault cases, fault modes, fault causes, fault cause objects, fault elements and their fault element aliases;

[0044] Failure analysis scenario of a certain category: Based on the standard failure phenomenon, multiple cases are clustered to display the standard failure phenomenon, failure mode, failure cause, failure case and failure element;

[0045] Fault tree-based analysis scenario: Centered on the fault mode, it displays the results of the entire fault tree, including the fault mode, standard fault phenomenon, fault cause and fault case.

[0046] The present invention also provides a computer terminal storage medium storing computer terminal executable instructions, wherein the computer terminal executable instructions are used to execute the above-mentioned multi-scenario fine-grained avionics fault characterization model dynamic generation method.

[0047] The present invention also provides a computing device, comprising:

[0048] At least one processor; and a memory in communication with the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the above-mentioned multi-scenario fine-grained avionics fault characterization model dynamic generation method.

[0049] The present invention also provides a computer program product, which implements the above-mentioned multi-scenario fine-grained avionics fault characterization model dynamic generation method when the computer program is executed by a processor.

[0050] In summary, due to the adoption of the above technical solution, the beneficial effects of the present invention are:

[0051] The present invention can realize the rapid construction of the avionics fault characterization model, and then continuously update and expand the model through actual cases, and continuously form and verify the cross-linking relationship between the fault characterization and the fault cause in the iterative process, so as to ensure the correctness and effectiveness of the model. Through the present invention, the construction process of the avionics fault characterization model can be standardized and patterned, supporting the construction of the avionics fault knowledge model, and the fault mechanism and cross-linking relationship embodied in the avionics fault characterization model can be applied to the fault diagnosis system, thereby improving the fault isolation rate, reducing the troubleshooting time, and improving the maintenance efficiency, which has important significance and value. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings in the embodiments will be briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present invention and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without creative work.

[0053] Figure 1 This is a basic flow chart of the method for dynamically generating a multi-scenario fine-grained avionics fault characterization model in an embodiment of the present invention.

[0054] Figure 2 Schematic diagram of an avionics fault characterization model in an embodiment of the present invention. DETAILED DESCRIPTION

[0055] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Generally, the components of the embodiments of the present invention described and shown in the drawings here can be arranged and designed in various different configurations.

[0056] Therefore, the following detailed description of the embodiments of the present invention provided in the accompanying drawings is not intended to limit the scope of the invention claimed for protection, but merely represents selected embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0057] Example

[0058] like Figure 1 As shown, this embodiment proposes a method for dynamically generating a multi-scenario fine-grained avionics fault characterization model, comprising the following steps:

[0059] S1, in view of the subjectivity, ambiguity and incompleteness of user fault description, the concept of fault element is proposed to describe the fault phenomenon in a fine-grained manner, and the basic elements of the avionics fault characterization model are analyzed and extracted.

[0060] Specifically, through expert experience, the fault knowledge documents such as FMEA, FTA and maintenance manual of avionics equipment and specific fault cases are analyzed. Based on the subjectivity, fuzziness and incompleteness of user fault description, in order to ensure the standardization and generalization of avionics fault characterization model, the avionics fault characterization model is characterized with the fine granularity of fault elements, and the following main fault elements are proposed:

[0061] Failure mode: A standardized description of the failure phenomenon that occurs in a product and can be observed and measured;

[0062] Failure mode object: a product that experiences a certain failure mode;

[0063] Failure cause: the reason that caused the failure mode to occur;

[0064] Fault cause object: the component that causes the failure mode to occur;

[0065] Failure cases: specific failure events and handling processes that occurred during actual application;

[0066] Case fault phenomenon: description of the phenomenon of the specific fault case;

[0067] Standard fault cases: Classify specific fault cases by fault phenomenon to form standardized fault phenomenon description and handling methods;

[0068] Standard fault phenomenon: description of the phenomenon of standard fault cases;

[0069] Fault confirmation method: a method to determine whether the specific fault phenomenon of the product belongs to a certain type of standard fault case;

[0070] Fault location method: A method to determine the exact location or component where a product failure occurs;

[0071] Fault element: the smallest element describing a standard fault phenomenon;

[0072] Fault Element Alias: A non-standard name or alias for a fault element.

[0073] S2, defines the complex relationships between different fault factors at multiple levels of avionics systems, modules, and components, and builds an avionics fault characterization model.

[0074] Specifically, the possible cross-linking and transmission relationships among fault elements, fault causes, fault phenomena and fault modes at multiple levels of avionics complete machines, modules and components are analyzed, and the relationships among the main fault elements are defined as follows:

[0075] Standard fault phenomenon - fault element: In the fault analysis stage, the smallest element that forms the standard fault phenomenon is the fault element. The fault element includes component units, functional signals, fault modes and fault conditions. Among them, the fault conditions include working parameters, occurrence timing, power supply type and fault status;

[0076] Failure case - Failure mode - Failure cause: By sorting out and analyzing the failure cases that have occurred, the corresponding failure modes and failure causes are summarized;

[0077] Failure mode - standard failure phenomenon - failure cause: Through failure impact and cause analysis, confirm the relationship between the product's failure mode, failure phenomenon and failure cause from both positive and negative directions, that is, the product fault tree;

[0078] Fault case (fault phenomenon) - fault element alias - fault element: In a specific fault case, its fault phenomenon is decomposed into several types of fault elements. Due to human subjectivity, there are differences in the description of the same fault element. The relationship between the fault element alias and the fault element is established by combining manual labeling and intelligent recognition, thereby establishing the relationship between the fault phenomenon and the fault element.

[0079] S3, based on the results of fault impact relationship analysis, preliminarily build an avionics fault characterization model; on this basis, based on the fault cases accumulated during the use phase, the avionics fault characterization model is dynamically updated and improved by combining automatic recommendation with expert review.

[0080] Initially build an avionics fault characterization model: starting from the functions and signals of avionics products, analyze the product fault tree, and comprehensively consider the impact of fault mode, working parameters and fault conditions on fault phenomena, confirm the underlying cause of a certain type of fault mode under the corresponding working parameters and fault conditions; at the same time, store the smallest elements of these types of elements as fault elements, that is, group different types of fault elements into standard fault phenomena, and form a fault mode-standard fault phenomenon-fault cause relationship;

[0081] Dynamically update the avionics fault characterization model: First, based on the newly added cases of the project, the fault element in the fault phenomenon is identified through a combination of manual labeling and intelligent recognition, and the fault case (fault phenomenon) - fault element alias - fault element relationship is constructed. Then, the fault cause of the newly added case and whether the fault element is the incremental knowledge of the fault characterization model are intelligently identified to complete the dynamic update of the fault knowledge characterization model.

[0082] Specifically, the method of identifying the fault element from the fault case phenomenon includes:

[0083] On the construction side, based on the specific phenomena of the fault case, the fault element intelligent labeling software is used to manually establish the relationship between the fault element and the fault element alias, and then a fault element-fault element alias library is constructed by combining manual labeling and intelligent recognition.

[0084] On the user side, a prefix dictionary is jointly constructed based on the constructed fault element-fault element alias library and the open source Chinese natural language dictionary library; the input fault phenomenon is vectorized and converted into a directed acyclic graph; then, a path with the highest probability is found on the directed acyclic graph based on dynamic programming, and word segmentation is performed based on this path to identify all word sequences that may be fault element aliases; then, the longest common subsequence method is used to calculate the textual similarity between the word sequences of all possible fault element aliases extracted and all fault elements and their fault element aliases in the fault element-fault element alias library, and based on the set similarity measurement threshold, fault element-fault element alias similar pairs that are greater than the similarity measurement threshold are recommended to achieve intelligent matching of fault elements.

[0085] Specifically, the method for dynamically updating the avionics fault characterization model includes:

[0086] In the constructed avionics fault characterization model, let the standard fault phenomenon library be FP = {fp1, fp2, ..., fp n}, where fp i Represents a standard fault phenomenon in the standard fault phenomenon library. i It is composed of multiple fault elements, which constitute the standard fault phenomenon fp i The set of fault elements is Fe i ={fe 1 ,fe 2 ,...,fe m}, fe k It is the standard fault phenomenon fp i One of the fault elements, and ∑Fe i =fp i Denotes the fault element set Fe i Arrange and add according to a certain rule to form the standard fault phenomenon fp i ; Let FE be the large set of fault element sets that constitute the standard fault phenomenon in the entire avionics fault characterization model, then FE={fe1,fe2,...,fe n Let the fault cause library FR in the avionics fault characterization model be FR = {fr1, fr2, ..., fr s}, resulting in the standard failure phenomenon fp iThere may be one or more reasons for the failure, which can be expressed mathematically as fp i ←{fr o ,fr p ,...,fr q}, where the fault cause {fr o ,fr p ,...,fr q}∈FR.

[0087] Let the failure reason of the newly added case be fr c , the identified fault element set is Fe c ={fe 1 ,fe 2 ,...,fe n}, the standard fault phenomenon composed of the fault element set is fp c , make the following judgment:

[0088] If fr c ∈FR, find fp in the library j ←fr c , fp j The corresponding fault element set is Fe j , and the fault element set Fe corresponding to the new case c ∈Fe j , then the avionics fault characterization model remains unchanged;

[0089] If fr c ∈FR, but This means that the newly added case adds a new fault element to the fault element set associated with the standard fault phenomenon in the library, and c With the result fp j Phase separation can increase fault isolation. The specific method is: let Fe s =Fe c ∪Fe j , if Fe s ∈FE, then first according to fp s =∑Fe s 、fp s ∈FP query fp s , add another fp s ←fr c relationship, and enter the sequence for expert review; if Then build fp first s =∑Fe s , and then construct fp s ←fr c Relationship, enter the sequence for expert review;

[0090] like But Fec ∈Fe j , then first according to fp c =∑Fe c 、fp c ∈FP query fp c , add another fp c ←fr c relationship, and enter the sequence for expert review;

[0091] like but Then first add a new fault cause fr to the fault cause set FR c , then add fp to the fault phenomenon set FP c =ΣFe c , and finally construct fp c ←fr c Relationship, enter the sequence for expert review.

[0092] S4, for different avionics fault characterization model analysis scenarios such as on-site whole machine troubleshooting, maintenance production line module fault location, component failure analysis, etc., proposes analysis perspectives with three different clustering centers: fault case, fault phenomenon, and fault mode. Based on the multi-analysis perspective fault map, the avionics fault characterization model is presented for different analysis scenarios and user roles.

[0093] Specifically, in different analysis scenarios, the avionics fault characterization model is displayed from multiple angles based on the multi-analysis perspective fault map:

[0094] On-site whole machine troubleshooting scenario: centered on specific fault cases, it displays the integration of single fault cases, including fault cases, fault modes, fault causes, fault cause objects, fault elements and their fault element aliases;

[0095] Failure analysis scenario of a certain category: Based on the standard failure phenomenon, multiple cases are clustered to display the standard failure phenomenon, failure mode, failure cause, failure case and failure element;

[0096] Fault tree-based analysis scenario: Centered on the fault mode, it displays the results of the entire fault tree, including the fault mode, standard fault phenomenon, fault cause and fault case.

[0097] The above-mentioned multi-scenario fine-grained avionics fault characterization model dynamic generation method can be applied to multiple fields. First, facing the generalization and fine-grained modeling requirements of avionics fault characterization models, the basic elements of avionics fault characterization models are analyzed and extracted; based on the analysis and application scenarios of fault knowledge, the correlation between the elements is clarified to construct an avionics fault characterization model; based on the fault analysis results, a preliminary avionics fault characterization model is constructed by combining forward analysis and reverse analysis; based on the fault cases accumulated during the use phase, the avionics fault characterization model is updated and improved by combining automatic recommendation with expert review; based on multi-perspective fault maps, the avionics fault characterization model is presented for different analysis scenarios and user roles. Through the present invention, the construction process of avionics fault characterization models can be standardized and patterned, supporting the construction of avionics fault knowledge models, and the fault mechanisms and cross-linking relationships embodied in avionics fault characterization models can be applied to fault diagnosis systems, thereby improving fault isolation rates, reducing fault troubleshooting time, and improving maintenance efficiency.

[0098] In addition, in some embodiments, a computer terminal storage medium is provided, which stores computer terminal executable instructions, and the computer terminal executable instructions are used to execute the multi-scenario fine-grained avionics fault characterization model dynamic generation method as described in the above embodiments. Examples of computer storage media include magnetic storage media (e.g., floppy disks, hard disks, etc.), optical recording media (e.g., CD-ROMs, DVDs, etc.), or memories, such as memory cards, ROMs, or RAMs, etc. Computer storage media can also be distributed on network-connected computer systems, such as application stores.

[0099] In addition, in some embodiments, a computing device is proposed, comprising: at least one processor; and a memory connected to the at least one processor in communication; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the multi-scenario fine-grained avionics fault characterization model dynamic generation method as described in the above embodiments. Examples of computing devices include PCs, tablet computers, smart phones, or PDAs.

[0100] In addition, in some embodiments, a computer program product is provided. When the computer program is executed by a processor, the method for dynamically generating a multi-scenario fine-grained avionics fault characterization model is implemented.

[0101] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A method for dynamically generating a multi-scenario fine-grained avionics fault characterization model, characterized in that: The following steps are involved: S1, in view of the subjectivity, ambiguity and incompleteness of user fault description, the concept of fault element is proposed to describe the fault phenomenon in a fine-grained manner, and the basic elements of the avionics fault characterization model are analyzed and extracted; S2, defines the complex relationships between different fault factors at multiple levels of avionics complete machines, modules, and components, and builds an avionics fault characterization model; S3, based on the results of fault impact relationship analysis, a preliminary avionics fault characterization model is constructed; on this basis, based on the accumulated fault cases during the use phase, the avionics fault characterization model is dynamically updated and improved by combining automatic recommendation with expert review; S4, for different avionics fault characterization model analysis scenarios, proposes different analysis perspectives of cluster centers, and displays avionics fault characterization models for different analysis scenarios and user roles based on multi-analysis perspective fault maps.

2. The method for dynamically generating a multi-scenario fine-grained avionics fault characterization model according to claim 1 is characterized in that: Step S1 includes: The avionics equipment fault knowledge files and specific fault cases are analyzed. Based on the characteristics of user fault descriptions, the avionics fault characterization model is characterized with the fine-grained fault element to ensure the standardization and generalization of the fault characterization model, and the following fault elements are proposed: Failure mode: A standardized description of the failure phenomenon that occurs in a product and can be observed and measured; Failure mode object: a product that experiences a certain failure mode; Failure cause: the reason that caused the failure mode to occur; Fault cause object: the component that causes the failure mode to occur; Failure cases: specific failure events and handling processes that occurred during actual application; Case fault phenomenon: description of the phenomenon of the specific fault case; Standard fault cases: Classify specific fault cases by fault phenomenon to form standardized fault phenomenon description and handling methods; Standard fault phenomenon: description of the phenomenon of standard fault cases; Fault confirmation method: a method to determine whether the specific fault phenomenon of the product belongs to a certain type of standard fault case; Fault location method: A method to determine the exact location or component where a product failure occurs; Fault element: the smallest element describing a standard fault phenomenon; Fault Element Alias: A non-standard name or alias for a fault element.

3. The method for dynamically generating a multi-scenario fine-grained avionics fault characterization model according to claim 2 is characterized in that: Step S2 includes: The possible cross-linking and transmission relationships among fault elements, fault causes, fault phenomena and fault modes at multiple levels of avionics complete machines, modules and components are analyzed, and the relationships among the main fault elements are defined as follows: Standard fault phenomenon - fault element: In the fault analysis stage, the smallest element that forms the standard fault phenomenon is the fault element. The fault element includes component units, functional signals, fault modes and fault conditions. Among them, the fault conditions include working parameters, occurrence timing, power supply type and fault status; Failure case - Failure mode - Failure cause: By sorting out and analyzing the failure cases that have occurred, the corresponding failure mode and failure cause can be summarized; Failure mode - standard failure phenomenon - failure cause: Through failure impact and cause analysis, confirm the relationship between the product's failure mode, failure phenomenon and failure cause from both positive and negative directions, that is, the product fault tree; Fault case - fault element alias - fault element: In a specific fault case, the fault phenomenon is decomposed into several types of fault elements. The relationship between the fault element alias and the fault element is established by combining manual labeling and intelligent recognition, thereby establishing the relationship between the fault phenomenon and the fault element.

4. The method for dynamically generating a multi-scenario fine-grained avionics fault characterization model according to claim 2 is characterized in that: Step S3 includes: Initially build an avionics fault characterization model: starting from the functions and signals of avionics products, analyze the product fault tree, and comprehensively consider the impact of fault mode, working parameters and fault conditions on fault phenomena, confirm the underlying cause of a certain type of fault mode under the corresponding working parameters and fault conditions; at the same time, store the smallest elements of these types of elements as fault elements, that is, group different types of fault elements into standard fault phenomena, and form a fault mode-standard fault phenomenon-fault cause relationship; Dynamically update the avionics fault characterization model: First, based on the newly added cases of the project, identify the fault elements in the fault phenomenon through a combination of manual labeling and intelligent recognition, and build a fault case-fault element alias-fault element relationship; then, intelligently identify the fault causes of the newly added cases and whether the fault elements are incremental knowledge of the fault characterization model, and complete the dynamic update of the fault knowledge characterization model.

5. The method for dynamically generating a multi-scenario fine-grained avionics fault characterization model according to claim 4 is characterized in that: The fault element in the identified fault phenomenon includes: On the construction side, based on the specific phenomena of the fault case, the fault element intelligent labeling software is used to manually establish the relationship between the fault element and the fault element alias, and then a fault element-fault element alias library is constructed by combining manual labeling and intelligent recognition. On the user side, a prefix dictionary is jointly constructed based on the constructed fault element-fault element alias library and the open source Chinese natural language dictionary library; the input fault phenomenon is vectorized and converted into a directed acyclic graph; then, a path with the highest probability is found on the directed acyclic graph based on dynamic programming, and word segmentation is performed based on this path to identify all word sequences that may be fault element aliases; then, the longest common subsequence method is used to calculate the textual similarity between the word sequences of all possible fault element aliases extracted and all fault elements and their fault element aliases in the fault element-fault element alias library, and based on the set similarity measurement threshold, fault element-fault element alias similar pairs that are greater than the similarity measurement threshold are recommended to achieve intelligent matching of fault elements.

6. The method for dynamically generating a multi-scenario fine-grained avionics fault characterization model according to claim 5 is characterized in that: The dynamic updating of the fault knowledge representation model includes: In the constructed avionics fault characterization model, let the standard fault phenomenon library be FP = {fp1, fp2, ..., fp n }, where fp i Represents a standard fault phenomenon in the standard fault phenomenon library. i It is composed of multiple fault elements, which constitute the standard fault phenomenon fp i The set of fault elements is Fe i ={fe 1 ,fe 2 ,...,fe m }, fe k It is the standard fault phenomenon fp i One of the fault elements, and ∑Fe i =fp i Denotes the fault element set Fe i Arrange and add according to a certain rule to form the standard fault phenomenon fp i ; Let FE be the large set of fault element sets that constitute the standard fault phenomenon in the entire avionics fault characterization model, then FE={fe1,fe2,...,fe n }. Let the fault cause library FR in the avionics fault characterization model be FR = {fr1, fr2, ..., fr s }, resulting in the standard failure phenomenon fp i There may be one or more reasons for the failure, which can be expressed mathematically as fp i ←{fr o ,fr p ,...,fr q }, where the fault cause {fr o ,fr p ,...,fr q }∈FR; Let the failure reason of the newly added case be fr c , the identified fault element set is Fe c ={fe 1 ,fe 2 ,...,fe n }, the standard fault phenomenon composed of the fault element set is fp c , make the following judgment: If fr c ∈FR, find fp in the library j ←fr c , fp j The corresponding fault element set is Fe j , and the fault element set Fe corresponding to the new case c ∈Fe j , then the avionics fault characterization model remains unchanged; If fr c ∈FR, but This means that the newly added case adds a new fault element to the fault element set associated with the standard fault phenomenon in the library, and c With the result fp j Phase separation can increase fault isolation. The specific method is: let Fe s =Fe c ∪Fe j , if Fe s ∈FE, then first according to fp s =∑Fe s 、fp s ∈FP query fp s , add another fp s ←fr c relationship, and enter the sequence for expert review; if Then build fp first s =∑Fe s , and then construct fp s ←fr c Relationship, enter the sequence for expert review; like But Fe c ∈Fe j , then first according to fp c =∑Fe c 、fp c ∈FP query fp c , add another fp c ←fr c relationship, and enter the sequence for expert review; like but Then first add a new fault cause fr to the fault cause set FR c , then add fp to the fault phenomenon set FP c =ΣFe c , and finally construct fp c ←fr c Relationship, enter the sequence for expert review.

7. The method for dynamically generating a multi-scenario fine-grained avionics fault characterization model according to claim 2 is characterized in that: Step S4 includes: On-site whole machine troubleshooting scenario: centered on specific fault cases, it displays the integration of single fault cases, including fault cases, fault modes, fault causes, fault cause objects, fault elements and their fault element aliases; Failure analysis scenario of a certain category: Based on the standard failure phenomenon, multiple cases are clustered to display the standard failure phenomenon, failure mode, failure cause, failure case and failure element; Fault tree-based analysis scenario: Centered on the fault mode, it displays the results of the entire fault tree, including the fault mode, standard fault phenomenon, fault cause and fault case.

8. A computer terminal storage medium storing computer terminal executable instructions, characterized in that: The computer terminal executable instructions are used to execute the multi-scenario fine-grained avionics fault characterization model dynamic generation method as described in any one of claims 1-7.

9. A computing device, characterized in that: include: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the method for dynamically generating a multi-scenario fine-grained avionics fault characterization model as described in any one of claims 1-7.

10. A computer program product, characterized in that When the computer program is executed by a processor, the method for dynamically generating a multi-scenario fine-grained avionics fault characterization model according to any one of claims 1 to 7 is implemented.

Images