Fault diagnosis method and system based on knowledge graph and related device

Abstract

The invention discloses a fault diagnosis method and system based on a knowledge graph and a related device, and the method comprises the steps: obtaining a fault diagnosis framework, and determining a central entity in the fault diagnosis framework; wherein the fault diagnosis framework at least comprises a fault mode, a fault case, a fault reason, a fault phenomenon, an equipment system and a maintenance method as entities, and the fault mode is a central entity; obtaining case data related to a plurality of faults, associating the central entity with at least part of entities based on the case data, and associating part of entities except the central entity at least based on the case data to obtain a fault diagnosis knowledge graph model; and performing fault diagnosis by using the fault diagnosis knowledge graph model. In this way, the efficiency and accuracy of fault diagnosis can be improved.

Description

Technical Field

[0001] The present application relates to the field of data processing technology, and in particular to a fault diagnosis method, system and related devices based on knowledge graph. Background Art

[0002] In recent years, equipment safety has received increasing attention, and fault diagnosis is an important part of equipment safety. Conventional fault diagnosis methods usually require equipment operators to troubleshoot faults according to the equipment manual, or require professional equipment maintenance personnel to perform fault diagnosis. Due to the lack of professional knowledge of equipment operators, the accuracy of the diagnostic results obtained when analyzing the data is low. Waiting for equipment maintenance personnel to perform fault diagnosis can obtain results with higher accuracy, but the efficiency is low, which ultimately makes it difficult to balance efficiency and accuracy. Therefore, how to improve the efficiency and accuracy of fault diagnosis has become an urgent problem to be solved. Summary of the invention

[0003] The main technical problem solved by the present application is to provide a fault diagnosis method, system and related devices based on knowledge graph, which can improve the efficiency and accuracy of fault diagnosis.

[0004] In order to solve the above technical problems, a technical solution adopted in the present application is: to provide a fault diagnosis method based on a knowledge graph, including: obtaining a fault diagnosis framework, and determining a central entity in the fault diagnosis framework; wherein the fault diagnosis framework includes at least fault mode, fault case, fault cause, fault phenomenon, equipment system, and maintenance method as entities, and the fault mode is the central entity; obtaining case data related to multiple faults, and based on the case data, associating the central entity with at least some entities, and at least associating some entities other than the central entity based on the case data to obtain a fault diagnosis knowledge graph model; and using the fault diagnosis knowledge graph model to perform fault diagnosis.

[0005] To solve the above technical problems, another technical solution adopted in the present application is: to provide a fault diagnosis system based on a knowledge graph, including: an acquisition module, used to obtain a fault diagnosis framework and determine the central entity in the fault diagnosis framework; wherein the fault diagnosis framework includes at least fault mode, fault case, fault cause, fault phenomenon, equipment system, and maintenance method as entities, and the fault mode is the central entity; an association module, used to obtain case data related to multiple faults, and based on the case data, associate the central entity with at least some entities, and at least based on the case data, associate some entities other than the central entity to obtain a fault diagnosis knowledge graph model; a diagnosis module, used to perform fault diagnosis using the fault diagnosis knowledge graph model.

[0006] To solve the above technical problems, another technical solution adopted in the present application is: to provide an electronic device, comprising: a memory and a processor coupled to each other, the memory storing program instructions, and the processor being used to execute the program instructions to implement the knowledge graph-based fault diagnosis method mentioned in the above technical solution.

[0007] In order to solve the above technical problems, another technical solution adopted in the present application is: providing a computer-readable storage medium on which program instructions are stored, and when the program instructions are executed by a processor, the knowledge graph-based fault diagnosis method mentioned in the above technical solution is implemented.

[0008] The beneficial effect of the present application is that, different from the prior art, the knowledge graph-based fault diagnosis method proposed in the present application directly or indirectly associates all other entities through the central entity of the fault mode, so that when a device fails, there is no need for the device operator to check the fault one by one according to the device manual, or wait for professional equipment maintenance personnel to diagnose the device. The central entity of the fault mode can be quickly obtained by directly describing the fault phenomenon, thereby enabling the device to be quickly and accurately diagnosed, thereby improving the efficiency and accuracy of fault diagnosis. BRIEF DESCRIPTION OF THE DRAWINGS

[0009] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work. Among them:

[0010] Figure 1 It is a flowchart of an implementation method of a fault diagnosis method based on a knowledge graph of the present application;

[0011] Figure 2 It is a flowchart of an implementation method corresponding to step S102 of the present application;

[0012] Figure 3 It is a structural diagram of an implementation method of the fault diagnosis knowledge graph model of the present application;

[0013] Figure 4 It is a structural schematic diagram of an implementation scheme of a fault diagnosis system based on a knowledge graph of the present application;

[0014] Figure 5 It is a structural schematic diagram of an embodiment of the electronic device of the present application;

[0015] Figure 6 It is a structural schematic diagram of an implementation method of a computer-readable storage medium of the present application. DETAILED DESCRIPTION

[0016] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments, and different implementation methods can be adaptively combined. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0017] The terms "system" and "network" are often used interchangeably in this article. The term "and / or" in this article is only a description of the association relationship of associated objects, indicating that there can be three relationships. For example, A and / or B can mean: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " in this article generally indicates that the associated objects before and after are in an "or" relationship. In addition, "many" in this article means two or more than two.

[0018] The knowledge graph-based fault diagnosis method proposed in this application is used to construct a fault diagnosis knowledge graph model and perform fault diagnosis, and its corresponding execution subject is a processing terminal that can call relevant data.

[0019] See also Figure 1 , Figure 1 It is a flow chart of an implementation method of a fault diagnosis method based on a knowledge graph of the present application, and the method comprises:

[0020] S101: Obtain a fault diagnosis framework and determine a central entity in the fault diagnosis framework; wherein the fault diagnosis framework includes at least a fault mode, a fault case, a fault cause, a fault phenomenon, an equipment system, and a maintenance method as entities, and the fault mode is the central entity.

[0021] Specifically, a fault diagnosis framework is obtained, which includes at least a fault mode, a fault case, a fault cause, a fault phenomenon, an equipment system, and a maintenance method as entities, and the fault mode is determined to be a central entity in the fault diagnosis framework.

[0022] In one application mode, a fault diagnosis framework is obtained, a fault mode annotated using an object is obtained, and the annotated fault mode is used as a central entity in the fault diagnosis framework.

[0023] In another application mode, at least some of the entities correspond to entity attributes, and based on the attribute characteristics of the entity attributes, the fault mode is determined to be the central entity in the fault diagnosis framework.

[0024] It should be noted that the fault diagnosis framework may also include fault classification, key fields of fault phenomena, etc. as entities, and this application does not impose specific restrictions on this.

[0025] S102: Obtain case data related to multiple faults, associate a central entity with at least some entities based on the case data, and associate at least some entities other than the central entity based on the case data to obtain a fault diagnosis knowledge graph model.

[0026] Specifically, case data related to various faults are obtained, and based on the obtained case data, a central entity is associated with at least some entities, and at least some entities other than the central entity are associated based on the case data to obtain a fault diagnosis knowledge graph model.

[0027] Optionally, the fault diagnosis framework may include multiple fault modes and data other than multiple fault modes as entities, and each fault mode is used as a central entity to be associated with other entities according to the above steps. Wherein, when the fault diagnosis framework includes multiple fault modes, the fault diagnosis knowledge graph includes each central entity and its directly or indirectly associated entities, and the entity-relationship-entity triples corresponding to the associated entities in the knowledge graph corresponding to each central entity.

[0028] In one application method, case data related to multiple faults are obtained, and a central entity is associated with at least some entities according to predefined rules and the obtained case data, and at least some entities other than the central entity are associated according to predefined rules and the obtained case data, to obtain a constructed fault diagnosis knowledge graph model.

[0029] In an application scenario, pre-defined rules are used to determine the relationships between entities, including causal relationships, inclusion relationships, and master-slave relationships, etc., and multiple entities in the case data are extracted. Then, the multiple entities are associated based on causal relationships, inclusion relationships, and master-slave relationships, etc.

[0030] In another application method, case data related to multiple faults are obtained, and entity recognition and relationship extraction are performed on the case data through deep learning technology. The central entity is associated with at least some entities based on the identified entities and the extracted relationships, and at least some entities other than the central entity are associated based on the identified entities and the extracted relationships to obtain the final fault diagnosis knowledge graph model.

[0031] In another application scenario, a neural network model is pre-trained to perform entity recognition and relationship extraction, and a large amount of case data is integrated and input into the trained model to obtain multiple entities and relationships between entities, such as causal relationships, master-slave relationships, etc. After identification, multiple entities and the relationships between entities are obtained, and multiple entities are associated.

[0032] S103: Perform fault diagnosis using the fault diagnosis knowledge graph model.

[0033] Specifically, fault diagnosis is performed using the constructed fault diagnosis knowledge graph model.

[0034] In one application method, data to be diagnosed is obtained, wherein the data to be diagnosed includes fault phenomenon text, the fault phenomenon text is input into a fault diagnosis knowledge graph model, and the model performs fault diagnosis based on the obtained fault phenomenon text.

[0035] In another application method, data to be diagnosed is obtained, wherein the data to be diagnosed includes a fault phenomenon image, and the fault phenomenon image is input into a fault diagnosis knowledge graph model, and the model performs fault diagnosis based on the received fault phenomenon image, wherein the fault phenomenon image can be an image captured by an image acquisition device, or a video frame in a video captured by a video acquisition device.

[0036] The above scheme obtains a fault diagnosis framework, which includes at least fault mode, fault case, fault cause, fault phenomenon, equipment system, and maintenance method as entities, determines the fault mode as the central entity in the fault diagnosis framework, obtains case data related to multiple faults, associates the central entity with at least some entities based on the acquired case data, and associates at least some entities outside the central entity based on the case data to obtain a fault diagnosis knowledge graph model, and uses the constructed fault diagnosis knowledge graph model to perform fault diagnosis. Therefore, all other entities are directly or indirectly associated through the central entity of the fault mode, so that when a device fails, there is no need for the equipment operator to check the fault one by one according to the equipment manual, or wait for professional equipment maintenance personnel to diagnose the device. The central entity of the fault mode can be quickly obtained by directly describing the fault phenomenon, so that the device can be quickly and accurately diagnosed, which improves the efficiency and accuracy of fault diagnosis.

[0037] In one implementation scenario, see Figure 2 , Figure 2 This is a flowchart of an implementation method corresponding to step S102 of the present application. The equipment system includes a variety of working equipment, the case data corresponds to the working equipment, and the case data at least includes the case cause, the case phenomenon and the case method. Step S102 specifically includes:

[0038] S201: Based on case causes, case phenomena and case methods, the fault cases are associated with the fault modes; based on case causes, the fault causes are associated with the fault modes; based on case phenomena, the fault phenomena are associated with the fault modes; based on the categories of working equipment, the equipment systems are associated with the fault modes.

[0039] Specifically, based on the case causes, case phenomena and case methods, the correlation between the fault cases and fault modes is determined, and the fault cases and fault modes are associated; based on the case causes, the correlation between the fault causes and fault modes is determined, and the fault causes are associated with the fault modes; based on the case phenomena, the correlation between the fault phenomena and fault modes is determined, and the fault phenomena are associated with the fault modes; based on the category of working equipment, the equipment system is associated with the fault mode.

[0040] Optionally, a fault case may include multiple specific fault modes, each specific fault mode corresponds to different case causes, case phenomena and case methods. Based on the corresponding case causes, case phenomena and case methods, the fault case and each specific fault mode are associated. The fault causes include the causes of occurrence of different fault modes. Based on the fault modes included in the case causes and their corresponding fault causes, the matching fault causes and fault modes are associated. The fault phenomena include the occurrence phenomena of different fault modes. Based on the fault modes included in the case phenomena and their corresponding occurrence phenomena, the matching fault phenomena and fault modes are associated.

[0041] S202: Based on the case method, the cause of the fault is associated with the maintenance method.

[0042] Specifically, according to the case method, the correlation between the cause of the fault and the maintenance method is determined, and the cause of the fault is associated with the maintenance method.

[0043] Optionally, the maintenance method includes maintenance methods for different fault causes, and based on the fault causes and their corresponding maintenance methods included in the case method, the matching fault causes and maintenance methods are associated.

[0044] S203: Based on the association relationship between multiple entities and the fault diagnosis framework, a fault diagnosis knowledge graph model is obtained.

[0045] Specifically, according to the association relationship between multiple entities and the fault diagnosis framework, a constructed fault diagnosis knowledge graph model is obtained.

[0046] In a specific implementation scenario, the equipment system includes 14 types of working equipment, including coal mining machines, continuous mining machines, tunneling machines, anchor boring machines, crushers, transfer machines, conveyors, hydraulic supports, belt conveyors, shuttle cars, bolting machines, multi-purpose tunneling machines, feeder switches, starters and mobile transformers. For examples, please refer to Figure 3 , Figure 3 It is a structural diagram of an implementation method of the fault diagnosis knowledge graph model of the present application. The fault case is an electrical control fault of a coal mining machine in the fully mechanized working face of the Bulianta Coal Mine at a certain time. One of the fault modes is that the coal mining machine fails to protect itself after startup. The case data may specifically include the time when the fault occurred, the phenomenon of the fault, the cause of the fault, and the maintenance method after the fault occurs. The fault case and the fault mode are associated according to the phenomenon of the fault, the cause of the fault, and the maintenance method after the fault occurs. It should be noted that there are many reasons for the occurrence of the fault, which may be a line fault, damage to the main control module in the controller component, or no control power supply. A fault mode can be associated with multiple fault causes. The fault phenomenon is associated with the fault mode according to the phenomenon of the fault. The fault phenomenon is that the coal mining machine does not self-protect after starting. According to the coal mining machine, the equipment system is associated with the fault mode. The equipment system is the coal mining machine of Bulianta Coal Mine. According to the maintenance method after the fault occurs, the fault cause is associated with the maintenance method. For example, when the fault cause is a line fault, the corresponding maintenance method can be to check the control line self-protection circuit according to the wiring diagram and connect it correctly; when the fault cause is the damage of the main control module in the controller component, the corresponding maintenance method can be to repair or replace the controller component; when the fault cause is no control power supply, the corresponding maintenance method can be to check whether the fuse in the power supply component is burned out, whether the power supply module is damaged, and repair or replace the power supply component and power supply module. Among them, the entity attributes in the maintenance method include maintenance standards, standard operating procedures and operating instructions. According to the association between multiple fault modes, fault cases, fault causes, fault phenomena, equipment systems, maintenance methods and fault diagnosis framework, a complete set of fault diagnosis knowledge graph models is obtained.

[0047] It should be noted that the maintenance method is not directly associated with the failure mode, so that it is convenient to directly refer to the standard knowledge of daily maintenance of equipment such as the maintenance standards, standard operating procedures and operating instructions of the working equipment.

[0048] In one implementation scenario, based on the association relationship between multiple entities and the fault diagnosis framework, before obtaining the fault diagnosis knowledge graph model, it also includes: obtaining subordinate entities included in other entities outside the fault mode, and associating the subordinate entities with the corresponding entities based on the inclusion relationship between the subordinate entities and the corresponding entities.

[0049] Specifically, subordinate entities included in entities other than the fault mode are acquired, and the subordinate entities are associated with the corresponding entities according to the inclusion relationship between the subordinate entities and the corresponding entities.

[0050] In a specific implementation scenario, the equipment system can be subdivided into equipment components and equipment parts. The equipment components and equipment parts are subordinate entities of the equipment system. The equipment components are associated with the equipment system based on the inclusion relationship between the equipment components and the equipment system, and the equipment parts are associated with the equipment system based on the inclusion relationship between the equipment parts and the equipment system.

[0051] In an implementation scenario, the subordinate entity includes at least one of a component of the corresponding entity and an attribute feature of the corresponding entity.

[0052] Specifically, the subordinate entity includes the components of the corresponding entity, or the subordinate entity includes the attribute characteristics of the corresponding entity, or the subordinate entity includes both the components and the attribute characteristics of the corresponding entity.

[0053] In one embodiment, the entity in the fault diagnosis framework also includes a fault phenomenon key field, and the method also includes: obtaining multiple phenomenon keywords based on the case phenomenon; and associating the fault phenomenon key field with the fault phenomenon based on the multiple key phenomenon words.

[0054] Specifically, according to the case phenomenon, a plurality of phenomenon keywords are obtained, and based on the obtained plurality of phenomenon keywords, the fault phenomenon key fields are associated with the fault phenomenon.

[0055] Optionally, multiple fault phenomena can be associated with the same fault phenomenon key field based on phenomenon keywords, and this application does not impose any specific restrictions on this.

[0056] In one implementation scenario, step S103 includes: obtaining the fault phenomenon text input by the user, and determining the text keywords in the fault phenomenon text; based on the text keywords and the phenomenon keywords, obtaining the fault phenomenon key fields that match the fault phenomenon text; based on the fault phenomenon key fields, obtaining the fault phenomenon associated with the fault phenomenon key fields; based on the fault phenomenon, obtaining the fault mode associated with the fault phenomenon; based on the fault mode, obtaining the equipment system and the fault cause associated with the fault mode.

[0057] Specifically, the fault phenomenon text input by the user is obtained, and the fault phenomenon text is preprocessed. Through methods such as semantic understanding, text keywords in the fault phenomenon text are extracted. According to the similarity between the text keywords and the phenomenon keywords, the fault phenomenon key fields that match the fault phenomenon text are obtained. According to the fault phenomenon key fields, the fault phenomenon associated with the fault phenomenon key fields is obtained. According to the fault phenomenon, the fault mode associated with the fault phenomenon is obtained. According to the fault mode, the equipment system associated with the fault mode and the fault cause are obtained. The user only needs to describe the specific fault phenomenon to use the fault diagnosis knowledge graph model to quickly and accurately determine the faulty working equipment and the cause of the fault, thereby improving the efficiency and accuracy of fault diagnosis.

[0058] In one embodiment, after obtaining the equipment system associated with the fault mode and the fault cause based on the fault mode, the method further includes: in response to obtaining the fault cause, providing a maintenance plan for the fault cause based on the maintenance method associated with the fault cause.

[0059] Specifically, after the cause of the fault is obtained, a maintenance plan is provided for the cause of the fault according to the maintenance method associated with the cause of the fault, so that the equipment system can be repaired in time to ensure the working efficiency of the equipment system.

[0060] In one implementation scenario, when a new fault occurs in any working device in the equipment system, the fault data is recorded, which includes new causes, new phenomena and new methods, and the fault data is entered into the fault case. A fault mode is added as the central entity in the fault diagnosis knowledge graph model, and multiple entities other than the fault mode are added. They are associated according to the fault data to obtain an updated fault diagnosis knowledge graph model, thereby improving the accuracy of subsequent fault diagnosis.

[0061] In another implementation scenario, when any working device in the equipment system fails, the failure mode of the failure is consistent with the original fault diagnosis knowledge graph model, but the failure phenomenon is different. A failure phenomenon is added as an entity in the fault diagnosis knowledge graph model and associated with the failure mode to obtain an updated fault diagnosis knowledge graph model, thereby improving the accuracy of subsequent fault diagnosis.

[0062] See also Figure 4 , Figure 4 It is a structural diagram of an implementation of a knowledge graph-based fault diagnosis system of the present application. The knowledge graph-based fault diagnosis system 40 includes an acquisition module 400, an association module 402 and a diagnosis module 404 that are coupled to each other.

[0063] Specifically, the acquisition module 400 is used to obtain a fault diagnosis framework and determine a central entity in the fault diagnosis framework; wherein the fault diagnosis framework includes at least a fault mode, a fault case, a fault cause, a fault phenomenon, an equipment system, and a maintenance method as entities, and the fault mode is the central entity.

[0064] The association module 402 is used to obtain case data related to various faults, and based on the case data, associate the central entity with at least some entities, and at least associate some entities other than the central entity based on the case data to obtain a fault diagnosis knowledge graph model.

[0065] The diagnosis module 404 is used to perform fault diagnosis using a fault diagnosis knowledge graph model.

[0066] Optionally, the equipment system includes a plurality of working equipment, the case data corresponds to the working equipment, and the case data includes at least case causes, case phenomena, and case methods. The association module 402 is also used to associate the fault case with the fault mode based on the case cause, the case phenomenon, and the case method, to associate the fault cause with the fault mode based on the case cause, to associate the fault phenomenon with the fault mode based on the case phenomenon, to associate the equipment system with the fault mode based on the category of the working equipment, to associate the fault cause with the maintenance method based on the case method, and to obtain the fault diagnosis knowledge graph model based on the association relationship between multiple entities and the fault diagnosis framework.

[0067] Optionally, the association module 402 is further configured to obtain subordinate entities included in other entities outside the fault mode, and associate the subordinate entities with the corresponding entities based on the inclusion relationship between the subordinate entities and the corresponding entities.

[0068] Optionally, the subordinate entity includes at least one of a component of the corresponding entity and an attribute feature of the corresponding entity.

[0069] Optionally, the association module 402 is further configured to obtain a plurality of phenomenon keywords based on the case phenomenon; and associate the fault phenomenon key fields with the fault phenomenon based on the plurality of phenomenon keywords.

[0070] Optionally, the diagnostic module 404 is also used to obtain the fault phenomenon text input by the user, determine the text keywords in the fault phenomenon text; based on the text keywords and the phenomenon keywords, obtain the fault phenomenon key fields that match the fault phenomenon text; based on the fault phenomenon key fields, obtain the fault phenomenon associated with the fault phenomenon key fields; based on the fault phenomenon, obtain the fault mode associated with the fault phenomenon; based on the fault mode, obtain the equipment system associated with the fault mode and the fault cause.

[0071] Optionally, the diagnosis module 404 is further configured to, in response to obtaining the cause of the fault, provide a maintenance solution for the cause of the fault based on a maintenance method associated with the cause of the fault.

[0072] See also Figure 5 , Figure 5 : is a structural diagram of an embodiment of an electronic device of the present application. The electronic device 50 includes: a memory 502 and a processor 500 coupled to each other. The memory 502 stores program instructions, and the processor 500 is used to execute the program instructions to implement the information feedback method mentioned in any of the above embodiments. Specifically, the electronic device 50 includes but is not limited to: a desktop computer, a laptop computer, a tablet computer, a server, etc., which are not limited here. In addition, the processor 500 can also be called a CPU (Center Processing Unit). The processor 500 may be an integrated circuit chip with signal processing capabilities. The processor 500 can also be a general-purpose processor, a digital signal processor (Digital Signal Processor, DSP), an application-specific integrated circuit (Application Specific Integrated Circuit, ASIC), a field-programmable gate array (Field-Programmable Gate Array, FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor, etc. In addition, the processor 500 can be implemented by an integrated circuit chip.

[0073] See also Figure 6 , Figure 6 The computer-readable storage medium 60 stores program instructions 600 that can be executed by a processor, and when the program instructions 600 are executed by the processor, the information feedback method mentioned in any of the above embodiments is implemented.

[0074] In the several embodiments provided in the present application, it should be understood that the disclosed methods and devices can be implemented in other ways. For example, the device implementation described above is only schematic. For example, the division of modules or units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, and the indirect coupling or communication connection of devices or units can be electrical, mechanical or other forms.

[0075] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0076] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0077] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions to enable a computer device (which can be a personal computer, server, or network device, etc.) or a processor (processor) to perform all or part of the steps of each implementation method of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk and other media that can store program code.

[0078] The above description is only an implementation method of the present application, and does not limit the patent scope of the present application. Any equivalent structure or equivalent process transformation made using the contents of the present application specification and drawings, or directly or indirectly used in other related technical fields, are also included in the patent protection scope of the present application.

Claims

1. A fault diagnosis method based on knowledge graph, characterized in that: include: Obtain a fault diagnosis framework, and determine a central entity in the fault diagnosis framework; wherein the fault diagnosis framework includes at least a fault mode, a fault case, a fault cause, a fault phenomenon, an equipment system, and a maintenance method as entities, and the fault mode is the central entity; Acquire case data related to multiple faults, associate the central entity with at least some entities based on the case data, and associate some entities other than the central entity at least based on the case data to obtain a fault diagnosis knowledge graph model; Fault diagnosis is performed using the fault diagnosis knowledge graph model.

2. The method according to claim 1, characterized in that The equipment system includes a plurality of working equipment, the case data corresponds to the working equipment, and the case data at least includes case causes, case phenomena and case methods; The method of obtaining case data related to a plurality of faults, associating the central entity with at least some entities based on the case data, and associating some entities other than the central entity at least based on the case data, to obtain a fault diagnosis knowledge graph model includes: Based on the case cause, the case phenomenon and the case method, the fault case is associated with the fault mode; based on the case cause, the fault cause is associated with the fault mode; based on the case phenomenon, the fault phenomenon is associated with the fault mode; based on the category of the working equipment, the equipment system is associated with the fault mode; Based on the case method, the cause of the fault is associated with the maintenance method; Based on the association relationship between multiple entities and the fault diagnosis framework, the fault diagnosis knowledge graph model is obtained.

3. The method according to claim 2, characterized in that Before obtaining the fault diagnosis knowledge graph model based on the association relationship between the multiple entities and the fault diagnosis framework, the method further includes: Subordinate entities included in other entities outside the fault mode are obtained, and based on the inclusion relationship between the subordinate entities and the corresponding entity, the subordinate entities are associated with the corresponding entity.

4. The method according to claim 3, characterized in that The subordinate entity includes at least one of a component of a corresponding entity and an attribute feature of the corresponding entity.

5. The method according to claim 2, characterized in that: The entity in the fault diagnosis framework also includes a key field of fault phenomenon, and the method further includes: Based on the case phenomenon, multiple phenomenon keywords are obtained; Based on the plurality of phenomenon keywords, the fault phenomenon key field is associated with the fault phenomenon.

6. The method according to claim 5, characterized in that The method of using the fault diagnosis knowledge graph model to perform fault diagnosis includes: Obtaining a fault phenomenon text input by a user, and determining text keywords in the fault phenomenon text; Based on the text keywords and the phenomenon keywords, obtaining the fault phenomenon key fields that match the fault phenomenon text; Based on the fault phenomenon key field, obtaining the fault phenomenon associated with the fault phenomenon key field; Based on the fault phenomenon, obtaining the fault mode associated with the fault phenomenon; Based on the failure mode, the device system associated with the failure mode and the failure cause are obtained.

7. The method according to claim 6, characterized in that After obtaining the equipment system and the fault cause associated with the fault mode based on the fault mode, the method further includes: In response to obtaining the fault cause, a maintenance solution is provided for the fault cause based on the maintenance method associated with the fault cause.

8. A fault diagnosis system based on knowledge graph, characterized in that: include: An acquisition module is used to acquire a fault diagnosis framework and determine a central entity in the fault diagnosis framework; wherein the fault diagnosis framework includes at least a fault mode, a fault case, a fault cause, a fault phenomenon, an equipment system, and a maintenance method as entities, and the fault mode is the central entity; An association module, used to obtain case data related to multiple faults, associate the central entity with at least some entities based on the case data, and associate some entities other than the central entity based on at least the case data to obtain a fault diagnosis knowledge graph model; The diagnosis module is used to perform fault diagnosis using the fault diagnosis knowledge graph model.

9. An electronic device, characterized in that: include: A memory and a processor coupled to each other, wherein the memory stores program instructions, and the processor is used to execute the program instructions to implement the knowledge graph-based fault diagnosis method as described in any one of claims 1-7.

10. A computer-readable storage medium having program instructions stored thereon, characterized in that: When the program instructions are executed by the processor, the fault diagnosis method based on the knowledge graph as described in any one of claims 1 to 7 is implemented.

Images