Industrial equipment fault management method, device and equipment based on knowledge graph

Abstract

The invention belongs to the technical field of equipment fault management, and discloses an industrial equipment fault management method, device and equipment based on a knowledge graph, and the method comprises the steps: obtaining equipment operation and maintenance entity related information from equipment data based on a knowledge extraction strategy; performing data disambiguation processing and similar entity information aggregation based on a disambiguation strategy, the first target equipment operation and maintenance entity related information and the second target equipment operation and maintenance entity related information to obtain a knowledge network; and identifying the fault data by using a first equipment operation and maintenance knowledge graph obtained by fusing the historical knowledge base and the knowledge network, and obtaining fault handling measure data for fault management. According to the method, the complex relationship among massive entities in the industrial equipment data is effectively extracted and mined, the fault condition of the equipment can be quickly handled according to the equipment operation and maintenance first knowledge graph, and a reasonable and effective maintenance plan is formulated, so that intelligent operation and maintenance of the industrial equipment are realized, the operation and maintenance efficiency of the production equipment is improved, and the operation safety is guaranteed.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of equipment fault management, and in particular to an industrial equipment fault management method and device based on a knowledge graph and equipment. BACKGROUND

[0002] Industrial production equipment is often deployed in harsh industrial environments, and after a long period of continuous operation, the parts of the equipment are prone to failure, affecting production work.

[0003] However, the existing equipment fault management technology has the following problems. One is that it relies too much on human experience, and many fault diagnoses need to be handled by specific employees, lacking systematic fault diagnosis. Another is that it is difficult to quickly and accurately provide detailed maintenance guidance for diagnosed fault causes. The existing industrial equipment fault management system has the problems of low intelligence and low operation and maintenance efficiency, and an effective solution has not yet been proposed.

[0004] The above content is only used to assist in understanding the technical solutions of the present application and does not represent an acknowledgement that the above content is prior art. SUMMARY

[0005] The main purpose of the present application is to provide an industrial equipment fault management method, device and equipment based on a knowledge graph, aiming to solve the technical problems of low intelligence and low operation and maintenance efficiency of the existing industrial equipment fault management system.

[0006] To achieve the above purpose, the present application provides an industrial equipment fault management method based on a knowledge graph, which comprises the following steps: obtaining equipment data, wherein the equipment data comprises structured data, semi-structured data and unstructured data; obtaining equipment operation and maintenance entity related information from the equipment data based on a knowledge extraction strategy, wherein the equipment operation and maintenance entity related information comprises equipment operation and maintenance entities, entity attributes and relationships between entities; performing data disambiguation processing on first target equipment operation and maintenance entity related information based on a disambiguation strategy to obtain disambiguated equipment operation and maintenance entity related information, wherein the first target equipment operation and maintenance entity related information is determined by semi-structured data and unstructured data in the equipment data; aggregating second target equipment operation and maintenance entity related information with the disambiguated equipment operation and maintenance entity related information to obtain a knowledge network, wherein the second target equipment operation and maintenance entity related information is determined by structured data in the equipment data; based on a fusion strategy, fusing a historical knowledge base and the knowledge network to obtain a first equipment operation and maintenance knowledge graph; Obtain fault data of an industrial device, and identify the fault data based on a first knowledge graph of device operation and maintenance to obtain a device fault analysis result. Obtain fault handling measure data for fault management from the first knowledge graph of device operation and maintenance based on the device fault analysis result.

[0007] In an embodiment, the obtaining of device operation and maintenance entity related information from the device data based on a knowledge extraction strategy comprises: Obtaining an entity trigger word detection result in the device data based on a trigger word detection algorithm; If the entity trigger word detection result is that there is a trigger word in the device data, obtaining a device operation and maintenance entity and entity attributes in the device operation and maintenance entity related information from the device data by a feature matching algorithm; If the entity trigger word detection result is that there is no trigger word in the device data, obtaining a device operation and maintenance entity and entity attributes in the device operation and maintenance entity related information from the device data by a deep learning algorithm.

[0008] In an embodiment, the method further comprises: Obtaining the device operation and maintenance entity and the entity attributes in the device operation and maintenance entity related information; Based on a relation extraction algorithm, the entity attributes of the device operation and maintenance entity are used as identifiers to connect the device operation and maintenance entity, to obtain the relationship between the entities.

[0009] In an embodiment, before the obtaining of a first knowledge graph of device operation and maintenance by fusing the historical knowledge base and the knowledge network based on a fusion strategy, the method further comprises: Obtaining historical device data; Preprocessing the historical device data to obtain device historical basic information and device historical operation data; Performing clustering statistical analysis processing on the device historical basic information and the device historical operation data, and extracting device historical operation and maintenance information to form the historical knowledge base, wherein the historical operation and maintenance information includes fault description, fault reason, fault handling process, maintenance guide, and optimization suggestion.

[0010] In an embodiment, the obtaining of a first knowledge graph of device operation and maintenance by fusing the historical knowledge base and the knowledge network based on a fusion strategy comprises: match the entity data in the knowledge network with the historical entity data in the historical knowledge base based on a fusion strategy to obtain a knowledge matching result, wherein the knowledge matching result includes a plurality of knowledge matching sub-results, each knowledge matching sub-result corresponding to a successful matching pair of entity data in the knowledge network and historical entity data in the historical knowledge base; update the knowledge network through the knowledge matching result to obtain the device operation and maintenance first knowledge graph.

[0011] In an embodiment, the method further comprises: deduce and analyze the knowledge in the device operation and maintenance first knowledge graph based on knowledge reasoning to extend and update the device operation and maintenance first knowledge graph; perform quality detection on the device operation and maintenance first knowledge graph based on a preset quality evaluation strategy to obtain a quality detection result; if the quality detection result is that there is incorrect information, send a prompt message to an operation and maintenance personnel terminal; if the quality detection result is that there is no incorrect information, perform the steps of obtaining fault data of an industrial device and identifying the fault data based on the device operation and maintenance first knowledge graph to obtain a device fault analysis result.

[0012] In an embodiment, the identifying the fault data based on the device operation and maintenance first knowledge graph to obtain a device fault analysis result comprises: linearly map the fault data of the industrial device with the knowledge features in the device operation and maintenance first knowledge graph to obtain a mapping result related to the fault data from the device operation and maintenance first knowledge graph; obtain the device fault analysis result according to the mapping result.

[0013] In addition, to achieve the above-mentioned purposes, the present application further proposes an industrial device fault management device based on a knowledge graph, which is applied to the industrial device fault management method based on a knowledge graph as described above. The device comprises: an acquisition module configured to acquire device data, wherein the device data includes structured data, semi-structured data and unstructured data; a knowledge extraction module configured to acquire device operation and maintenance entity related information from the device data based on a knowledge extraction strategy, wherein the device operation and maintenance entity related information includes device operation and maintenance entities, entity attributes and relationships between entities; The disambiguation module is configured to perform data disambiguation processing on the first target device operation and maintenance entity related information based on a disambiguation strategy, and obtain disambiguated device operation and maintenance entity related information, wherein the first target device operation and maintenance entity related information is determined by semi-structured data and unstructured data in the device data. The fusion module is configured to aggregate the second target device operation and maintenance entity related information and the disambiguated device operation and maintenance entity related information to obtain a knowledge network, wherein the second target device operation and maintenance entity related information is determined by structured data in the device data. The fusion module is configured to fuse the historical knowledge base and the knowledge network based on a fusion strategy to obtain a first device operation and maintenance knowledge graph. The fault diagnosis module is configured to obtain fault data of an industrial device, and identify the fault data based on the first device operation and maintenance knowledge graph to obtain a device fault analysis result. The fault diagnosis module is configured to obtain fault handling measure data for fault management from the first device operation and maintenance knowledge graph based on the device fault analysis result.

[0014] In addition, to achieve the above-mentioned purpose, the present application further provides an industrial device fault management device based on a knowledge graph, which comprises a memory, a processor, and an industrial device fault management program based on a knowledge graph stored in the memory and executable on the processor, wherein the industrial device fault management program based on a knowledge graph is configured to implement the steps of the industrial device fault management method based on a knowledge graph as described above.

[0015] In addition, to achieve the above-mentioned purpose, the present application further provides a storage medium, wherein the storage medium stores an industrial device fault management program based on a knowledge graph, and the industrial device fault management program based on a knowledge graph implements the steps of the industrial device fault management method based on a knowledge graph as described above when executed by a processor.

[0016] The application obtains device operation and maintenance entity related information from device data based on a knowledge extraction strategy, performs data disambiguation processing and same type entity information aggregation based on a disambiguation strategy, first target device operation and maintenance entity related information and second target device operation and maintenance entity related information, and obtains a knowledge network. The device operation and maintenance first knowledge graph obtained by fusing a historical knowledge base and the knowledge network is used to identify fault data and obtain fault handling measure data for fault management. The above method effectively extracts and mines the complex relationships between a large number of entities in industrial device data, can quickly respond to fault conditions of the device according to the device operation and maintenance first knowledge graph, and formulates a reasonable and effective maintenance plan, realizes intelligent operation and maintenance of the industrial device, improves the production device operation and maintenance efficiency, and ensures operation safety. BRIEF DESCRIPTION OF DRAWINGS

[0017] Figure 1 FIG. 1 is a flowchart of a first embodiment of the industrial device fault management method based on the knowledge graph of the application. Figure 2 FIG. 2 is a schematic diagram in which the mobile terminal receives a diagnosis device problem in the industrial device fault management method based on the knowledge graph of the application. Figure 3 FIG. 3 is a structure block diagram of a first embodiment of the industrial device fault management device based on the knowledge graph of the application.

[0018] The implementation, functional features and advantages of the application will be further described with reference to the embodiments and the accompanying drawings. DETAILED DESCRIPTION

[0019] It should be understood that the specific embodiments described herein are only used to explain the application and do not limit the application.

[0020] The embodiment of the application provides an industrial device fault management method based on a knowledge graph, referring to Figure 1 , Figure 1 FIG. 1 is a flowchart of a first embodiment of the industrial device fault management method based on the knowledge graph of the application.

[0021] In the embodiment, the industrial device fault management method based on the knowledge graph comprises the following steps: Step S10: obtaining device data.

[0022] In the embodiment, the execution subject of the embodiment is an industrial device fault management device based on a knowledge graph, wherein the industrial device fault management device based on the knowledge graph has functions of data processing, data communication and program running, and the industrial device fault management device based on the knowledge graph can be a computer terminal device or other network device, and of course can be other devices with similar functions, and the embodiment does not limit this.

[0023] It should be noted that industrial production equipment is often deployed in harsh industrial environments, and after a long period of continuous operation, the parts of the equipment are prone to failure, affecting production work. However, the existing equipment fault management technology has the following problems, one is too dependent on manual experience, and many fault diagnoses need to be handled by specific employees, lacking systematic fault diagnosis. Another is that it is difficult to quickly and accurately provide detailed maintenance guidance for the diagnosed fault causes. The existing industrial equipment fault management system has the problems of low intelligence and low operation and maintenance efficiency, and an effective solution has not been proposed.

[0024] To solve the above technical problems, in the embodiment, the device operation and maintenance entity related information is obtained from the device data based on a knowledge extraction strategy; data disambiguation processing and same entity information aggregation are performed based on a disambiguation strategy, first target device operation and maintenance entity related information, and second target device operation and maintenance entity related information, to obtain a knowledge network; and a device operation and maintenance first knowledge graph obtained by fusing a historical knowledge base and the knowledge network is used to identify fault data and obtain fault handling measure data for fault management. The above method effectively extracts and mines the complex relationships between a large number of entities in industrial equipment data, and according to the device operation and maintenance first knowledge graph, the fault conditions of the equipment can be quickly responded to, and a reasonable and effective maintenance plan can be developed, realizing intelligent operation and maintenance of industrial equipment, improving production equipment operation and maintenance efficiency, and ensuring operation safety. Specifically, it can be implemented in the following way.

[0025] In the embodiment, first, device data needs to be obtained, wherein the device data includes structured data, semi-structured data, and unstructured data. The structured data mainly includes basic information of the equipment, sensor readings, process parameters, timestamps, etc.; the semi-structured data mainly includes alarm logs of the equipment, labels and metadata of sensor data, and equipment time records, etc.; and the unstructured data mainly includes fault reports of the equipment, maintenance logs, drawings, images and videos generated by sensors, etc.

[0026] Step S20: obtaining device operation and maintenance entity related information from the device data based on a knowledge extraction strategy.

[0027] In a specific implementation, based on the knowledge extraction strategy, device operation and maintenance entity related information is obtained from semi-structured data, unstructured data, and structured data of the device data, wherein the device operation and maintenance entity related information includes device operation and maintenance entities, entity attributes, and relationships between entities.

[0028] It should be noted that the device operation and maintenance entity refers to a core object related to a specific business in the device data; the entity attribute refers to the attribute information of the core object, which is a complete description of the entity; and the relationship between entities includes the association relationship between entities and entities, and between entities and attributes.

[0029] Specifically, for the acquisition of the device operation entity and the entity attribute in the device operation entity related information, the semi-structured data, the unstructured data and the structured data in the device data are acquired first; then the entity trigger word detection result in the device data is acquired based on a trigger word detection algorithm; if the entity trigger word detection result is that there is a trigger word in the device data, the device operation entity and the entity attribute in the device operation entity related information are extracted from the device data through a feature matching algorithm; if the entity trigger word detection result is that there is no trigger word in the device data, the device operation entity and the entity attribute in the device operation entity related information are extracted from the device data through a deep learning algorithm.

[0030] In an embodiment, the manner of acquiring the inter-entity relationship is to acquire the device operation entity and the entity attribute in the device operation entity related information; the device operation entity is connected in relation based on a relation extraction algorithm, taking the entity attribute of the device operation entity as an identifier, to obtain the inter-entity relationship.

[0031] Step S30: data disambiguation processing is performed on the first target device operation entity related information based on a disambiguation strategy, to obtain disambiguated device operation entity related information.

[0032] In a specific implementation, after the device operation entity related information is acquired from the semi-structured data, the unstructured data and the structured data in the device data through the above steps, there are much data redundancy and noise in the information extracted from the semi-structured and unstructured data, and the data is in a scattered state, which cannot directly support the upper-layer application. Therefore, it is necessary to integrate the entities in the semi-structured and unstructured data from different data sources through entity disambiguation, coreference disambiguation and other data processing means, so as to form more comprehensive entity information. Therefore, in this embodiment, preferably, the first target device operation entity related information corresponding to the semi-structured data and the unstructured data in the device data is processed for data disambiguation based on a global entity disambiguation method and a coreference disambiguation method, and disambiguated device operation entity related information is integrated.

[0033] Step S40: same-type entity information aggregation is performed on the second target device operation entity related information and the disambiguated device operation entity related information, to obtain a knowledge network.

[0034] In a specific implementation, the information units extracted from the above information lack hierarchy and logic, and therefore, the device operation and maintenance entity related information in the extracted structured data needs to be aggregated with the device operation and maintenance entity related information in the disambiguated semi-structured data and unstructured data, that is, the multi-source description information about the same entity is fused to obtain a knowledge network under the same entity.

[0035] Step S50: based on a fusion strategy, fusing the historical knowledge base and the knowledge network to obtain a first knowledge graph for device operation and maintenance.

[0036] In this embodiment, after obtaining the knowledge network under the same entity through the above steps, the historical knowledge base and the knowledge network are fused based on a fusion strategy to obtain a first knowledge graph for device operation and maintenance. Specifically, the entity data in the knowledge network and the historical entity data in the historical knowledge base are matched based on clustering analysis to obtain a knowledge matching result; the knowledge matching result includes a plurality of knowledge matching sub-results, and each knowledge matching sub-result corresponds to a successful matching pair of entity data in the knowledge network and historical entity data in the historical knowledge base; the knowledge network is updated through the knowledge matching result to obtain the first knowledge graph for device operation and maintenance.

[0037] Further, the construction process of the historical knowledge base is to obtain historical device data; the historical device data is preprocessed to obtain device historical basic information and device historical operation data; the device historical basic information and the device historical operation data are subjected to clustering statistical analysis processing to extract device historical operation and maintenance information to form the historical knowledge base, wherein the historical operation and maintenance information includes fault description, fault reason, fault handling process, maintenance guide, and optimization suggestion. In addition, the historical knowledge base needs to be updated regularly to supplement operation and maintenance information to expand the operation and maintenance knowledge graph and provide a basis for industrial device fault operation and maintenance management.

[0038] Further, the obtained first knowledge graph for device operation and maintenance also needs to be subjected to quality judgment, specifically, the knowledge in the first knowledge graph for device operation and maintenance is deduced and analyzed based on knowledge reasoning to expand and update the first knowledge graph for device operation and maintenance; the first knowledge graph for device operation and maintenance is subjected to quality detection based on a preset quality evaluation strategy to obtain a quality detection result; if the quality detection result is that there is incorrect information, a prompt message is sent to an operation and maintenance personnel terminal; if the quality detection result is that there is no incorrect information, the step of obtaining fault data of an industrial device and identifying the fault data based on the first knowledge graph for device operation and maintenance to obtain a device fault analysis result is executed.

[0039] Step S60: Obtain the fault data of the industrial equipment, and identify the fault data based on the first knowledge graph of equipment operation and maintenance to obtain the equipment fault analysis result.

[0040] In this embodiment, if the fault data of the industrial equipment is obtained, the fault data of the industrial equipment is identified based on the first knowledge graph of equipment operation and maintenance and the fault identification rule to obtain the equipment fault analysis result. Specifically, the fault data of the industrial equipment is linearly mapped with the knowledge features in the first knowledge graph of equipment operation and maintenance, and the mapping result related to the fault data is obtained from the first knowledge graph of equipment operation and maintenance. Finally, the equipment fault analysis result is obtained according to the mapping result. Step S70: Obtain the fault handling measure data for fault management from the first knowledge graph of equipment operation and maintenance based on the equipment fault analysis result.

[0041] In this embodiment, based on the equipment fault analysis result, the fault handling measure data is obtained from the first knowledge graph of equipment operation and maintenance through a similarity analysis algorithm. Specifically, the fault features in the equipment fault analysis result are compared with the knowledge features in the first knowledge graph of equipment operation and maintenance through a similarity analysis algorithm, and the comparison result related to the equipment fault analysis result is obtained from the first knowledge graph of equipment operation and maintenance. Finally, the corresponding fault handling measure data is obtained through the comparison result, so that the operation and maintenance efficiency can be quickly improved.

[0042] In actual application, when the computer program end receives the equipment fault information, the system automatically diagnoses the fault information and formulates a recommended solution, and pushes the information to the production line related personnel through the Dingding / WeChat mobile end, as shown in FIG. 8. Figure 2 The production line personnel receive the message notification in the first time and solve the problem according to the solution, so that the fault is quickly solved and the influence of the fault on the production progress is reduced.

[0043] In this embodiment, the equipment operation and maintenance entity related information is obtained from the equipment data based on the knowledge extraction strategy; the data disambiguation processing and the same entity information aggregation are performed based on the disambiguation strategy, the first target equipment operation and maintenance entity related information and the second target equipment operation and maintenance entity related information, and the first knowledge graph of equipment operation and maintenance obtained by fusing the historical knowledge base and the knowledge network is used to identify the fault data and obtain the fault handling measure data for fault management. The above-mentioned method effectively extracts and mines the complex relationship between a large number of entities in the industrial equipment data, can quickly respond to the fault condition of the equipment according to the first knowledge graph of equipment operation and maintenance, formulates a reasonable and effective maintenance plan, realizes the intelligent operation and maintenance of the industrial equipment, improves the operation and maintenance efficiency of the production equipment, and ensures the operation safety.

[0044] In addition, the embodiment of the present application also provides a storage medium, wherein the storage medium stores a knowledge graph-based industrial equipment fault management program, and the knowledge graph-based industrial equipment fault management program is used to realize the steps of the knowledge graph-based industrial equipment fault management method when executed by a processor.

[0045] Referring to Figure 3 , Figure 3 FIG. 1 is a structural block diagram of a first embodiment of a knowledge graph-based industrial equipment fault management device according to the present application.

[0046] As Figure 3 shown, the knowledge graph-based industrial equipment fault management device provided by the embodiment of the present application comprises: an acquisition module 10 configured to acquire equipment data, wherein the equipment data comprises structured data, semi-structured data and unstructured data; a knowledge extraction module 20 configured to acquire equipment operation and maintenance entity related information from the equipment data based on a knowledge extraction strategy, wherein the equipment operation and maintenance entity related information comprises equipment operation and maintenance entities, entity attributes and relationships between entities; a disambiguation module 30 configured to perform data disambiguation processing on first target equipment operation and maintenance entity related information based on a disambiguation strategy to obtain disambiguated equipment operation and maintenance entity related information, wherein the first target equipment operation and maintenance entity related information is determined by semi-structured data and unstructured data in the equipment data; a fusion module 40 configured to aggregate second target equipment operation and maintenance entity related information and the disambiguated equipment operation and maintenance entity related information to obtain a knowledge network, wherein the second target equipment operation and maintenance entity related information is determined by structured data in the equipment data; the fusion module 40 is configured to fuse a historical knowledge base and the knowledge network based on a fusion strategy to obtain a first knowledge graph of equipment operation and maintenance; a fault diagnosis module 50 configured to acquire fault data of industrial equipment and identify the fault data based on the first knowledge graph of equipment operation and maintenance to obtain equipment fault analysis results; the fault diagnosis module 50 is configured to acquire fault handling measure data for fault management from the first knowledge graph of equipment operation and maintenance based on the equipment fault analysis results.

[0047] In this embodiment, the device operation and maintenance entity related information is obtained from the device data based on a knowledge extraction strategy; the data disambiguation processing and the same entity information aggregation are performed based on the disambiguation strategy, the first target device operation and maintenance entity related information, and the second target device operation and maintenance entity related information, to obtain a knowledge network; and the device operation and maintenance first knowledge graph obtained by fusing the historical knowledge base and the knowledge network is used to identify the fault data and obtain the fault handling measure data for fault management. The above method effectively extracts and mines the complex relationships among a large number of entities in the industrial device data, can quickly respond to the fault conditions of the device according to the device operation and maintenance first knowledge graph, and develop a reasonable and effective maintenance plan, realizes the intelligent operation and maintenance of the industrial device, improves the production device operation and maintenance efficiency, and ensures the operation safety.

[0048] The application also provides an industrial device fault management device based on a knowledge graph, which comprises a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory are in communication with each other through the communication bus, the memory is used to store an industrial device fault management program based on a knowledge graph, and the processor is used to execute the program stored in the memory to realize the above-mentioned industrial device fault management method based on a knowledge graph.

[0049] The communication bus mentioned in the above-mentioned industrial device fault management device based on a knowledge graph can be a peripheral component interconnect (PCI) bus or an extended industry standard architecture (EISA) bus, etc. The communication bus can be divided into an address bus, a data bus, a control bus, etc.

[0050] The communication interface is used for communication between the above-mentioned industrial device fault management device based on a knowledge graph and other devices.

[0051] The memory can comprise a random access memory (RAM) and can also comprise a non-volatile memory (NVM), for example at least one disk memory. Optionally, the memory can also be at least one storage device located away from the aforementioned processor.

[0052] The processor described above can be a general processor, including a central processing unit (CPU), a network processor (NP), etc.; or can be a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic device, a discrete gate or transistor logic device, a discrete hardware component.

[0053] In the above embodiments, the implementation can be wholly or partially achieved by software, hardware, firmware or any combination thereof. When implemented by software, the implementation can be wholly or partially in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the processes or functions described in the embodiments of the present application are wholly or partially generated. The computer can be a general purpose computer, a special purpose computer, a computer network or other programmable apparatus. The computer instructions can be stored in a computer readable storage medium or transferred from one computer readable storage medium to another computer readable storage medium, for example, the computer instructions can be transferred from one website, computer, server or data center to another website, computer, server or data center through a wired (such as coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (such as infrared, wireless, microwave, etc.) manner. The computer readable storage medium can be any available medium accessible by a computer or a data storage device such as a server, data center, etc. integrated with one or more available media. The available medium can be a magnetic medium (such as a floppy disk, a hard disk, a magnetic tape), an optical medium (such as a DVD), or a semiconductor medium (such as a solid state disk (SSD)), etc.

[0054] It is to be noted that the relative terms such as first and second and the like are used herein only to differentiate one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between such entities or operations. Moreover, the terms "comprising", "including", or any other variant thereof are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements recited, but can also include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element preceded by "comprises a" does not, without more constraints, foreclose the existence of additional identical elements in the process, method, article, or apparatus that comprises the recited element.

[0055] Each of the embodiments in the specification is described in a relevant manner, and the same and similar parts of each of the embodiments can be referred to each other. Each of the embodiments focuses on the difference from other embodiments. In particular, for the system embodiments, since they are basically similar to the method embodiments, the description is relatively simple, and the relevant parts can be referred to the part of the description of the method embodiments.

[0056] The above embodiments are only used to illustrate the technical solutions of the present application, but not to limit it. Although the present application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that they can still modify the technical solutions recorded in the foregoing embodiments, or make equivalent replacements for some technical features. These modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application.

[0057] It should be understood that the above is only for illustration, and does not constitute any limitation on the technical solutions of the present application. In specific applications, those skilled in the art can set it according to the needs, and the present application does not limit it.

[0058] It should be noted that the above-described workflow is only illustrative and does not limit the scope of protection of the present application. In actual application, those skilled in the art can select part or all of them according to actual needs to achieve the purpose of the embodiment, which is not limited here.

[0059] In addition, technical details not described in detail in the embodiment can be referred to the knowledge graph-based industrial equipment fault management method provided by any embodiment of the present application, which will not be described here.

[0060] Moreover, it is to be understood that the phraseology and terminology used herein is for the purpose of description and should not be regarded as limiting. The use of "including" "comprising" "having" "containing" or "encompassing" and other like terms is used herein to be open-ended, and to mean including, but not limited to, the stated elements or objects, and further allowing for elements or objects not specifically listed or included.

[0061] The above-mentioned embodiment numbers of the present application are only for description, and do not represent the advantages and disadvantages of the embodiments.

[0062] From the above description of the embodiments, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be realized by means of software and the necessary general hardware platform, and of course, they can also be realized by hardware, but in many cases, the former is a better embodiment. Based on such understanding, the technical solutions of the present application can be embodied in the form of a software product, which is stored in a storage medium (such as a read-only memory (ROM) / RAM, a magnetic disk, or an optical disk) and includes a number of instructions for making a terminal device (which can be a mobile phone, a computer, a server, or a network device) execute the methods described in the embodiments of the present application.

[0063] The above is only the preferred embodiment of the present application, and does not limit the patent scope of the present application, and any equivalent structure or equivalent process transformation, or direct or indirect application in other related technical fields, is also included in the patent protection scope of the present application.

[0064] It can be understood that the system provided by the embodiments of the present application corresponds to the method provided by the embodiments of the present application, and the explanation, examples and beneficial effects of the related content can refer to the corresponding part in the above method.

Claims

1. A knowledge graph-based method for industrial equipment fault management, characterized in that, The knowledge graph-based industrial equipment fault management method includes: Acquire device data, wherein the device data includes structured data, semi-structured data, and unstructured data; Based on a knowledge extraction strategy, relevant information about equipment operation and maintenance entities is obtained from the equipment data. The relevant information about equipment operation and maintenance entities includes equipment operation and maintenance entities, entity attributes, and relationships between entities. Based on the disambiguation strategy, the relevant information of the first target equipment operation and maintenance entity is processed to obtain the disambiguated relevant information of the equipment operation and maintenance entity. The relevant information of the first target equipment operation and maintenance entity is determined by the semi-structured data and unstructured data in the equipment data. The relevant information of the second target equipment operation and maintenance entity is aggregated with the relevant information of the disambiguated equipment operation and maintenance entity to obtain a knowledge network, wherein the relevant information of the second target equipment operation and maintenance entity is determined by the structured data in the equipment data; Based on the fusion strategy, the historical knowledge base and the knowledge network are fused to obtain the first knowledge graph of equipment operation and maintenance; Fault data of industrial equipment is acquired, and the fault data is identified based on the first knowledge graph of equipment operation and maintenance to obtain equipment fault analysis results; Based on the equipment fault analysis results, fault handling measures data for fault management are obtained from the first knowledge graph of equipment operation and maintenance.

2. The industrial equipment fault management method based on knowledge graph as described in claim 1, characterized in that, The step of obtaining equipment operation and maintenance entity-related information from the equipment data based on the knowledge extraction strategy includes: Based on the trigger word detection algorithm, the entity trigger word detection results in the device data are obtained; If the entity trigger word detection result indicates that a trigger word exists in the device data, then the device operation and maintenance entity and entity attributes in the device operation and maintenance entity related information are extracted from the device data through a feature matching algorithm. If the entity trigger word detection result indicates that there is no trigger word in the device data, then the device operation and maintenance entity and entity attributes in the device operation and maintenance entity related information are extracted from the device data using a deep learning algorithm.

3. The industrial equipment fault management method based on knowledge graph as described in claim 2, characterized in that, The method further includes: Obtain the equipment operation and maintenance entity and its attributes from the relevant information of the equipment operation and maintenance entity; Based on the relation extraction algorithm, the entity attributes of the equipment operation and maintenance entity are used as identifiers to form relational connections between the equipment operation and maintenance entities, thereby obtaining the relationships between the entities.

4. The industrial equipment fault management method based on knowledge graph as described in claim 1, characterized in that, Before fusing the historical knowledge base and the knowledge network based on the fusion strategy to obtain the first knowledge graph of equipment operation and maintenance, the method further includes: Obtain historical device data; The historical equipment data is preprocessed to obtain basic historical equipment information and historical equipment operation data; Clustering statistical analysis is performed on the historical basic information and historical operation data of the equipment to extract historical operation and maintenance information of the equipment, which is used to form the historical knowledge base. The historical operation and maintenance information includes fault description, fault cause, fault handling process, maintenance guide and optimization suggestions.

5. The industrial equipment fault management method based on knowledge graph as described in claim 1, characterized in that, The aforementioned fusion strategy integrates the historical knowledge base and the knowledge network to obtain a first knowledge graph for equipment operation and maintenance, including: The entity data in the knowledge network is matched with the historical entity data in the historical knowledge base based on the fusion strategy to obtain the knowledge matching result. The knowledge matching result includes several knowledge matching sub-results, and each knowledge matching sub-result corresponds to a successful matching pair between entity data in the knowledge network and historical entity data in the historical knowledge base. The knowledge network is updated using the knowledge matching results to obtain the first knowledge graph for equipment operation and maintenance.

6. The industrial equipment fault management method based on knowledge graph as described in claim 1, characterized in that, The method further includes: Based on knowledge reasoning, the knowledge in the first knowledge graph of equipment operation and maintenance is inferred and analyzed to expand and update the first knowledge graph of equipment operation and maintenance; Based on a preset quality assessment strategy, the first knowledge graph of equipment operation and maintenance is subjected to quality detection to obtain quality detection results. If the quality inspection result indicates that there is incorrect information, a prompt message will be sent to the maintenance personnel's terminal. If the quality inspection result indicates that there is no incorrect information, then the steps of obtaining fault data of industrial equipment and identifying the fault data based on the first knowledge graph of equipment operation and maintenance are performed to obtain equipment fault analysis results.

7. The industrial equipment fault management method based on knowledge graph as described in claim 1, characterized in that, The process of identifying fault data based on the first knowledge graph of equipment operation and maintenance to obtain equipment fault analysis results includes: The fault data of the industrial equipment is linearly mapped to the knowledge features in the first knowledge graph of equipment operation and maintenance, and the mapping results related to the fault data are obtained from the first knowledge graph of equipment operation and maintenance. Based on the mapping results, the equipment fault analysis results are obtained.

8. A knowledge graph-based industrial equipment fault management device, characterized in that, The knowledge graph-based industrial equipment fault management device is applied to the knowledge graph-based industrial equipment fault management method as described in any one of claims 1 to 7, wherein the device comprises: An acquisition module is used to acquire device data, wherein the device data includes structured data, semi-structured data, and unstructured data; The knowledge extraction module is used to obtain equipment operation and maintenance entity-related information from the equipment data based on the knowledge extraction strategy. The equipment operation and maintenance entity-related information includes the equipment operation and maintenance entity, entity attributes, and relationships between entities. The disambiguation module is used to perform data disambiguation processing on the relevant information of the first target device operation and maintenance entity based on the disambiguation strategy to obtain the disambiguated relevant information of the device operation and maintenance entity, wherein the relevant information of the first target device operation and maintenance entity is determined by the semi-structured data and unstructured data in the device data; The fusion module is used to aggregate the information related to the second target equipment operation and maintenance entity with the information related to the disambiguated equipment operation and maintenance entity to obtain a knowledge network, wherein the information related to the second target equipment operation and maintenance entity is determined by the structured data in the equipment data; The fusion module is used to fuse the historical knowledge base and the knowledge network based on the fusion strategy to obtain the first knowledge graph of equipment operation and maintenance. The fault diagnosis module is used to acquire fault data of industrial equipment and identify the fault data based on the first knowledge graph of equipment operation and maintenance to obtain equipment fault analysis results. The fault diagnosis module is used to obtain fault handling measures data for fault management from the first knowledge graph of equipment operation and maintenance based on the equipment fault analysis results.

9. A knowledge graph-based industrial equipment fault management device, characterized in that, The knowledge graph-based industrial equipment fault management device includes: a memory, a processor, and a knowledge graph-based industrial equipment fault management program stored in the memory and executable on the processor, wherein the knowledge graph-based industrial equipment fault management program is configured to implement the steps of the knowledge graph-based industrial equipment fault management method as described in any one of claims 1 to 7.

10. A storage medium, characterized in that, The storage medium stores a knowledge graph-based industrial equipment fault management program, which, when executed by a processor, implements the steps of the knowledge graph-based industrial equipment fault management method as described in any one of claims 1 to 7.

Images