A knowledge graph-based method and system for fault diagnosis of park equipment

Abstract

This invention discloses a knowledge graph-based method and system for fault diagnosis of park equipment. The method includes: S101, constructing an ontology based on knowledge graph of various equipment information and fault information within the park; the ontology construction includes class construction and object attribute construction; class construction includes constructing park equipment classes and fault information classes; object attribute construction includes constructing park equipment object attributes and fault information object attributes; S102, based on the constructed ontology, extracting triplet information from park equipment object attributes and fault information object attributes, and storing it in a database; S103, receiving fault information reported by sensors within the park, and diagnosing the fault information based on the stored triplet information to obtain diagnostic results; S104, displaying the diagnostic results. This invention can improve the speed of fault diagnosis and repair, and improve the digitalization level and operational efficiency of the park.

Description

Technical Field

[0001] This invention relates to the field of fault monitoring and diagnosis, specifically to a method and system for fault diagnosis of campus equipment based on knowledge graphs. Background Technology

[0002] Most parks currently using data-driven management have digitized the reporting and storage of fault information. However, the automation process is limited to the reporting and display of alarm information; the analysis and diagnosis of faults still rely on manual labor, resulting in faults not being resolved in a timely manner and adversely affecting the safety and operational efficiency of the park. Summary of the Invention

[0003] In view of the above problems, the present invention provides a knowledge graph-based method and system for fault diagnosis of park equipment. The method and system automatically analyze the reported fault or alarm information through knowledge graph and quickly provide fault diagnosis information by comparing with the database to assist maintenance personnel in analyzing and judging faults, thereby improving the speed of fault diagnosis and repair, and improving the digitalization level and operational efficiency of the park.

[0004] The technical solution adopted by the present invention to solve the above-mentioned technical problems is as follows:

[0005] On the one hand, a knowledge graph-based method for fault diagnosis of park equipment includes:

[0006] S101, Ontology construction is performed on various equipment information and fault information in the park based on knowledge graph; the ontology construction includes the construction of classes and the construction of object attributes; the construction of classes includes the construction of park equipment classes and fault information classes; the park equipment classes include various park equipment objects, and the fault information classes include various fault information objects; the construction of object attributes includes the construction of park equipment object attributes and fault information object attributes.

[0007] S102, based on the constructed ontology, extracts triplet information from the attributes of park equipment objects and fault information objects, and stores it in the database;

[0008] S103 receives fault information reported by sensors within the park, and diagnoses the fault information based on the stored triplet information to obtain diagnostic results;

[0009] S104, The diagnostic results are displayed.

[0010] Preferably, an ontology is constructed based on knowledge graphs to collect information on various equipment and faults within the park, specifically including:

[0011] Based on knowledge graphs, a seven-step method was used to construct an ontology of various equipment and fault information within the park in Protégé.

[0012] Preferably, in the construction of object attributes, the park equipment object attributes include: location attribute, equipment number attribute, equipment working status attribute, equipment name attribute, and equipment historical fault attribute;

[0013] The attributes of the fault information object include: fault name attribute, fault code attribute, fault phenomenon attribute, fault equipment type attribute, and fault solution attribute.

[0014] Preferably, the triplet form of the knowledge graph refers to the basic storage unit being constructed in the manner of entity-relationship-entity; for campus equipment, triplet information including (equipment name, number, equipment number), (equipment number, type, equipment type), (equipment number, status, equipment working status), and (equipment number, fault, equipment historical fault) is generated based on its object attributes; for fault information, triplet information including (fault, number, fault code), (fault code, equipment type, equipment type), and (fault, solution, fault solution) is generated based on its object attributes.

[0015] Preferably, the extracted triple information is stored using Neo4j. Specifically, in a graph database, the two entities in a triple are considered as nodes, and the relations in the triple are considered as edges of the graph. Neo4j uses Cypher as the query language to view and edit nodes, uses CREATE to create graph nodes, DELETE to delete graph nodes, SET to modify nodes, MATCH to match nodes, WHERE to filter conditions, and RETURN to return query results.

[0016] In Neo4j, nodes are instances of various attributes of objects constructed during ontology construction.

[0017] Preferably, graph nodes are created using CREATE in Neo4j, specifically including:

[0018] Use the CREATE statement to create corresponding device nodes according to the number of devices in the park and assign device numbers to these devices, then associate the device numbers with the device instances; use the CREATE statement to create device working status nodes, device location nodes, device name nodes, and device historical fault nodes for the park device object properties constructed from the ontology, and associate them with the device nodes; finally, associate all park device entities with the park device class.

[0019] For equipment fault information, use the CREATE statement to create fault nodes one by one according to the fault list; for the fault information object attributes constructed in the ontology, use the CREATE statement to create fault code nodes, fault solution nodes, fault equipment type nodes, and fault name nodes, and associate them with the fault nodes; finally, associate all fault nodes with the park equipment class, that is, all park equipment shares fault nodes.

[0020] Preferably, alarm information reported by sensors within the park is received. When the alarm information is fault information, a diagnosis is performed on the fault information based on the stored triplet information to obtain a diagnosis result, specifically including:

[0021] The system receives alarm information reported by sensors within the park, processes it into an XML document, and extracts various attribute values ​​from the XML document, including device type, device code, device location, and fault phenomenon. Based on the device type and fault phenomenon, the system queries the device type code and fault phenomenon code respectively and generates a fault code that uniquely corresponds to the device type and fault phenomenon.

[0022] Search for the fault node corresponding to the fault code in the historical fault information associated with the equipment type. If the query result is true, return the fault solution based on the information associated with the fault node. If the query result is empty, match the fault phenomenon keywords in the historical faults of the equipment associated with the equipment code to query all solutions. If a solution is found, return it; otherwise, prompt the maintenance personnel to handle it.

[0023] Preferably, the system matches fault symptoms with keywords from the historical faults associated with the device code to search for all solutions. If a solution is found, the system also includes:

[0024] After troubleshooting, use CREATE to create a new fault node from the historical fault information of the device type.

[0025] Preferably, after prompting maintenance personnel to handle the issue, it also includes:

[0026] After troubleshooting, use CREATE to create a new fault node from the historical fault information of the device type.

[0027] On the other hand, a knowledge graph-based campus equipment fault diagnosis system includes:

[0028] The ontology construction module is used to construct an ontology based on knowledge graphs for various equipment information and fault information within the park. The ontology construction includes the construction of classes and the construction of object attributes. The construction of classes includes the construction of park equipment classes and fault information classes. The park equipment classes include various park equipment objects, and the fault information classes include various fault information objects. The construction of object attributes includes the construction of park equipment object attributes and fault information object attributes.

[0029] The storage module is used to extract triplet information from the attributes of park equipment objects and fault information objects based on the constructed ontology and store it in the database;

[0030] The diagnostic result acquisition module is used to receive fault information reported by sensors in the park, and to diagnose the fault information based on the stored triplet information to obtain diagnostic results.

[0031] The diagnostic results display module is used to display the diagnostic results.

[0032] The beneficial effects of this invention are as follows:

[0033] (1) This invention uses sensors in the software park to monitor and quantify the status of various hardware devices in real time; based on knowledge graph technology, the real-time data generated by the sensors, the fault information reported by the devices, the fault information manually submitted during the manual inspection, and the progress and results of fault repair are stored in the database in the form of triples and abstracted into a graph structure. With the advantage of knowledge graph technology, the invention realizes automated functions such as storage of equipment information and fault information, retrieval of fault information, diagnosis of fault causes, tracking of fault repair progress, and fault early warning, thereby improving the speed of fault diagnosis and repair and improving the digitalization level and operational efficiency of the park.

[0034] (2) If there is no fault node in the database that matches the reported fault code, the present invention will use CREATE to create a new fault node in the historical fault information of the equipment type after the fault is eliminated. Through the accumulation of fault information, the diagnostic efficiency will be continuously improved, thereby reducing the phenomenon of unclear fault causes and slow repair progress caused by non-professional maintenance. Attached Figure Description

[0035] Figure 1 This is a flowchart of a knowledge graph-based campus equipment fault diagnosis method according to an embodiment of the present invention;

[0036] Figure 2 This is a flowchart of a fault diagnosis process based on alarm information according to an embodiment of the present invention;

[0037] Figure 3 This is an example diagram of an XML document according to an embodiment of the present invention;

[0038] Figure 4 This is a flowchart of the fault code comparison algorithm according to an embodiment of the present invention;

[0039] Figure 5 This is a structural block diagram of a knowledge graph-based campus equipment fault diagnosis system according to an embodiment of the present invention. Detailed Implementation

[0040] The specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings. It should be understood that the specific embodiments described herein are for illustration and explanation only and are not intended to limit the present invention.

[0041] See Figure 1 As shown in the figure, this embodiment of a knowledge graph-based method for fault diagnosis of park equipment includes:

[0042] S101, Ontology construction is performed on various equipment information and fault information in the park based on knowledge graph; the ontology construction includes the construction of classes and the construction of object attributes; the construction of classes includes the construction of park equipment classes and fault information classes; the park equipment classes include various park equipment objects, and the fault information classes include various fault information objects; the construction of object attributes includes the construction of park equipment object attributes and fault information object attributes.

[0043] S102, based on the constructed ontology, extracts triplet information from the attributes of park equipment objects and fault information objects, and stores it in the database;

[0044] S103 receives fault information reported by sensors within the park, and diagnoses the fault information based on the stored triplet information to obtain diagnostic results;

[0045] S104, The diagnostic results are displayed.

[0046] Specifically, in S101, the ontology is built using a seven-step method in the open-source software Protégé.

[0047] The seven-step process mainly involves: determining the domain and scope of the ontology, considering the reuse of existing ontologies, listing important terms in the ontology, defining classes and their hierarchical structure, defining class attributes, defining attribute constraints, and creating instances. For the actually collected data, XML is used to process the text information into a computer-recognizable language. The database is built using the non-relational database Neo4j to store processed fault and alarm information. Fault diagnosis mainly employs various fault reasoning rules, including querying and comparing fault codes, faulty components, and other information to provide auxiliary diagnoses of the fault causes.

[0048] Ontology construction includes the construction of classes and object attributes. Class construction mainly involves the construction of two types of classes: Equipment and Fault. The Equipment class mainly includes various specific equipment objects, while the Fault class includes various fault information objects.

[0049] In constructing object attributes, the campus equipment (Equipment) mainly has the following attributes: Location (equipmentLocation) attribute, which describes the specific location of a device within the campus; Equipment ID (equipmentId) attribute, which describes the ID number of the device; Equipment State (equipmentState) attribute, which describes the operating status of the device; Equipment Message attribute, which describes the purpose, structure, and other information of the device; and Equipment Fault History attribute, which describes the fault information that has occurred in the past for this type of device.

[0050] The fault information object mainly has the following attributes: fault name (faultName) attribute, which describes the name of the fault; fault code (faultId) attribute, which describes the number of the fault instance; fault description (faultDescription) attribute, which describes the phenomenon of the fault occurrence; equipment class of fault (equipmentClassOfFault) attribute, which describes the equipment type to which the fault belongs; and fault solution (faultSolution) attribute, which describes the fault solution, maintenance personnel, contact information, etc.

[0051] In this embodiment, after ontology construction, knowledge representation is also included, that is, information is processed into a type that can be recognized by a computer through the Extensible Markup Language (XML).

[0052] XML files use elements as the basic unit, with each member or attribute considered a node, stored in a tree structure. The entire XML document contains nodes including text nodes, attribute nodes, and comment nodes. Based on the XML DOM standard, JavaScript is used to access and modify XML documents: the `loadXMLDoc()` method loads the XML document, the `.createElement()` method creates a new element node in an XML document, the `.createAttribute()` method creates a new attribute node in an XML document, the `.createTextNode()` method creates a new text node in an XML document, the `.appendChild()` method adds child nodes to a node, the `.setAttribute()` method adds attributes to an element, and the `.insertData()` method adds text to a text node.

[0053] In step S103, if the alarm information reported by the sensors in the park is received, it is also necessary to determine whether the alarm information is fault information. If it is fault information, the fault information is diagnosed based on the stored triplet information to obtain the diagnosis result.

[0054] Alarm information is generated and reported by sensors distributed across various devices throughout the park. First, the alarms are processed into XML documents. Then, various attribute values, such as device type, device location, and fault symptoms, are extracted from the XML document. Specifically, the device type code and fault symptom code are queried separately based on the device type and fault symptom, generating a unique 16-digit fault code corresponding to each. This code is then used to perform the following database query:

[0055] ① Check the fault code. If the codes are the same, it means that the same type of device has the same fault. In this case, directly query the repair plan based on the fault code and display it.

[0056] ② If no fault code is found, try to match the faulty device and fault information. Based on the keywords of the faulty device and fault symptoms, search for all repair solutions in the historical fault diagnosis information, display the repair solutions for maintenance personnel to refer to, and after the repair, enter a new repair solution and associate it with a new fault code to enrich the database;

[0057] ③ If the fault code and historical information fail to match, the maintenance personnel will be prompted to find the relevant repair personnel as soon as possible based on the faulty equipment. After the repair is completed, the new fault code and fault symptoms will be entered and associated with the equipment.

[0058] In step S104, the diagnostic results are displayed. Specifically, the diagnostic results can be displayed or prompted on the terminal devices of maintenance personnel and / or management personnel, such as computers and mobile phones (e.g., via SMS prompts), so that maintenance personnel can be informed of the occurrence of the fault in a timely manner and obtain the corresponding solutions.

[0059] The following will use the central air conditioning system of a park as an example to illustrate how this invention uses knowledge graphs to diagnose equipment faults in a park. The basic steps include:

[0060] (1) The seven-step method is used to construct the ontology of the central air conditioning equipment class and the ontology of the central air conditioning fault class;

[0061] (2) Extract the format of triples from the central air conditioning equipment instance and fault information instance data and store them in the Neo4j database;

[0062] (3) Collect alarm information in XML files during actual operation and perform fault diagnosis.

[0063] See the flowchart for fault diagnosis based on alarm information. Figure 2 As shown.

[0064] Specifically, step (1) involves constructing the ontology using Protégé. The seven-step method mentioned in step (1) includes: determining the scope of the ontology construction, considering the reuse of existing ontology, listing important terms in the ontology, defining classes and hierarchies, defining class attributes, defining attribute constraints, and creating instances. A top-down approach is used in the ontology construction process. First, a "Campus Equipment" class is defined, under which various specific equipment classes exist, and under each equipment class, various specific equipment objects exist. Alongside the Campus Equipment class is a "Fault" class, under which various fault information objects exist. The various attribute value types of the objects include string, integer, floating-point, and boolean types.

[0065] The construction of the central air conditioning equipment body needs to cover the working status of the central air conditioning equipment, including: air outlet temperature (int type, value range 16-30), cooling function (bool type), heating function (bool type), dehumidification function (bool type), outdoor unit working status (bool type), air conditioning filter status (bool type), equipment location (str type), equipment name (str type), etc.

[0066] The core structure for central air conditioning fault categories needs to cover various fault phenomena of central air conditioning, including: abnormal cooling (str type), abnormal heating (str type), abnormal dehumidification (str type), outdoor unit fault (str type), excessive dust on the filter (str type), missing filter (str type), corresponding fault codes (int type with values ​​ranging from 0 to 2^16-1 integers), fault repair solutions (contact information of fault repair personnel (str type), emergency handling solutions (str type), etc.).

[0067] The data storage in step (2) requires the establishment of triplet data. Based on the object attributes constructed in step (1), it is necessary to further construct the relation elements in the triplet. In the process of storing information about central air conditioning equipment, the relations involved include: number, location, working status, and name. In the process of storing information about central air conditioning faults, the relations included include: fault phenomenon, repair plan, and code.

[0068] First, in Neo4j, use the CREATE statement to create corresponding central air conditioning equipment nodes according to the number of central air conditioning units in the park, and assign these equipment numbers. Then, associate the numbers with the equipment instances. Similarly, use the CREATE statement to create working status nodes, equipment location nodes, equipment name nodes, etc., for the central air conditioning object properties on the ontology, and associate them with the equipment nodes. Finally, associate all central air conditioning equipment entities with the central air conditioning equipment class.

[0069] For central air conditioning fault information, the CREATE statement is used to create fault nodes one by one according to the fault list, along with corresponding fault codes, fault solutions, fault equipment type nodes, etc., and then the nodes are associated. Finally, these fault information nodes are associated with the central air conditioning equipment class, meaning that all central air conditioning systems share the fault information nodes.

[0070] The fault diagnosis in step (3) specifically involves first extracting various attribute values, such as device type, device location, and fault symptoms, from the XML file generated based on the fault information reported by the sensors. An example XML document is shown below. Figure 3 As shown, based on the information in the XML document, the fault code is 00030f3d. First, use the `MATCH(equipment{equipmentId:0003})-[class]->(targetClass)` statement to query the device type corresponding to 0003. Then, use `MATCH({equipmentClass:targetClass}-[equipmentFaultHistory]->(targetFault:faultMessage)`.

[0071] The algorithm `{faultId:0f3d})return targetFault` searches the historical fault information associated with the device type for the fault node corresponding to the fault code `0f3d`. If the query result is true, a fault repair plan is returned based on the information associated with that node. If the query result is empty, the historical fault information of the device type associated with device 0003 is searched using keywords such as "refrigeration," and the results are returned for reference. After the fault is resolved, a new fault node is created in the historical fault information of the device type using `CREATE`. If both searches are empty, manual intervention is immediately requested, and a new fault node is created in the historical fault information of the device type using `CREATE` again after the fault is resolved. The flowchart of the fault code comparison algorithm is as follows: Figure 3 As shown.

[0072] See Figure 5 As shown, according to another aspect of the present invention, this embodiment also discloses a knowledge graph-based campus equipment fault diagnosis system, including:

[0073] The ontology construction module 501 is used to construct an ontology based on knowledge graphs for various equipment information and fault information within the park. The ontology construction includes the construction of classes and the construction of object attributes. The construction of classes includes the construction of park equipment classes and fault information classes. The park equipment classes include various park equipment objects, and the fault information classes include various fault information objects. The construction of object attributes includes the construction of park equipment object attributes and fault information object attributes.

[0074] Storage module 502 is used to extract triplet information from the attributes of park equipment objects and fault information objects based on the constructed ontology and store it in the database;

[0075] The diagnostic result acquisition module 503 is used to receive fault information reported by sensors in the park, and to diagnose the fault information based on the stored triplet information to obtain diagnostic results.

[0076] The diagnostic result display module 504 is used to display the diagnostic results.

[0077] A specific implementation of a knowledge graph-based campus equipment fault diagnosis system is described in this embodiment, which is the same as the knowledge graph-based campus equipment fault diagnosis method.

[0078] The above embodiments are only used to illustrate the technical solutions of the present invention, and are not intended to limit it. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some or all of the technical features therein. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for fault diagnosis of park equipment based on knowledge graph, characterized in that, include: S101, Ontology construction is performed on various equipment information and fault information in the park based on knowledge graph; the ontology construction includes the construction of classes and the construction of object attributes; the construction of classes includes the construction of park equipment classes and fault information classes; the park equipment classes include various park equipment objects, and the fault information classes include various fault information objects; the construction of object attributes includes the construction of park equipment object attributes and fault information object attributes. S102, based on the constructed ontology, extracts triplet information from the attributes of park equipment objects and fault information objects, and stores it in the database; S103 receives fault information reported by sensors within the park, and diagnoses the fault information based on the stored triplet information to obtain diagnostic results; S104, Display the diagnostic results; In constructing object attributes, the park equipment object attributes include: location attribute, equipment number attribute, equipment working status attribute, equipment name attribute, and equipment historical fault attribute; The attributes of the fault information object include: fault name attribute, fault code attribute, fault phenomenon attribute, fault equipment type attribute, and fault solution attribute; Receive fault information reported by sensors within the park, and diagnose the fault information based on stored triplet information to obtain diagnostic results, specifically including: The system receives fault information reported by sensors within the park, processes it into an XML document, and extracts various attribute values ​​from the XML document, including equipment type, equipment code, equipment location, and fault phenomenon. Based on the equipment type and fault phenomenon, the system queries the equipment type code and fault phenomenon code respectively and generates a fault code that uniquely corresponds to the equipment type and fault phenomenon. Search for the fault node corresponding to the fault code in the historical fault information associated with the equipment type. If the query result is true, return the fault solution based on the information associated with the fault node. If the query result is empty, match the fault phenomenon keywords in the historical faults of the equipment associated with the equipment code to query all solutions. If a solution is found, return it; otherwise, prompt the maintenance personnel to handle it.

2. The knowledge graph-based fault diagnosis method for park equipment according to claim 1, characterized in that, Based on knowledge graphs, an ontology is constructed for various equipment and fault information within the park, specifically including: Based on knowledge graphs, a seven-step method was used to construct an ontology of various equipment and fault information within the park in Protégé.

3. The knowledge graph-based fault diagnosis method for park equipment according to claim 2, characterized in that, The triple form of a knowledge graph refers to the basic storage unit constructed in the manner of entity-relationship-entity; for campus equipment, triple information including (equipment name, number, equipment number), (equipment number, type, equipment type), (equipment number, status, equipment working status) and (equipment number, fault, equipment historical fault) is generated based on its object attributes. For fault information, generate triplet information including (fault, number, fault code), (fault code, associated device type, device type) and (fault, solution, fault solution) based on its object attributes.

4. The knowledge graph-based fault diagnosis method for park equipment according to claim 3, characterized in that, The extracted triple information is stored using Neo4j. Specifically, in a graph database, the two entities in a triple are considered nodes, and the relation in the triple is considered an edge of the graph. Neo4j uses Cypher as the query language to view and edit nodes, using CREATE to create graph nodes, DELETE to delete graph nodes, SET to modify nodes, MATCH to match nodes, WHERE to filter conditions, and RETURN to return query results. In Neo4j, nodes are instances of various attributes of objects constructed during ontology construction.

5. The knowledge graph-based fault diagnosis method for park equipment according to claim 4, characterized in that, Creating graph nodes using CREATE in Neo4j specifically includes: Use the CREATE statement to create corresponding device nodes according to the number of devices in the park and assign device numbers to these devices, then associate the device numbers with the device instances; use the CREATE statement to create device working status nodes, device location nodes, device name nodes, and device historical fault nodes for the park device object properties constructed from the ontology, and associate them with the device nodes; finally, associate all park device entities with the park device class. For equipment fault information, use the CREATE statement to create fault nodes one by one according to the fault list; for the fault information object attributes constructed in the ontology, use the CREATE statement to create fault code nodes, fault solution nodes, fault equipment type nodes, and fault name nodes, and associate them with the fault nodes; finally, associate all fault nodes with the park equipment class, that is, all park equipment shares fault nodes.

6. The knowledge graph-based fault diagnosis method for park equipment according to claim 5, characterized in that, Search for all solutions by matching fault symptoms with keywords in the historical fault records of the device associated with the device code. If a solution is found, it also includes: After troubleshooting, use CREATE to create a new fault node from the historical fault information of the device type.

7. The knowledge graph-based fault diagnosis method for park equipment according to claim 5, characterized in that, After prompting maintenance personnel to handle the issue, the following is also included: After troubleshooting, use CREATE to create a new fault node from the historical fault information of the device type.

8. A knowledge graph-based fault diagnosis system for park equipment, characterized in that, include: The ontology construction module is used to construct an ontology based on knowledge graphs for various equipment information and fault information within the park. The ontology construction includes the construction of classes and the construction of object attributes. The construction of classes includes the construction of park equipment classes and fault information classes. The park equipment classes include various park equipment objects, and the fault information classes include various fault information objects. The construction of object attributes includes the construction of park equipment object attributes and fault information object attributes. In constructing object attributes, the park equipment object attributes include: location attribute, equipment number attribute, equipment working status attribute, equipment name attribute, and equipment historical fault attribute; the fault information object attributes include: fault name attribute, fault code attribute, fault phenomenon attribute, fault equipment type attribute, and fault solution attribute. The storage module is used to extract triplet information from the attributes of park equipment objects and fault information objects based on the constructed ontology and store it in the database; The diagnostic result acquisition module is used to receive fault information reported by sensors in the park, and to diagnose the fault information based on the stored triplet information to obtain diagnostic results. A diagnostic result display module is used to display the diagnostic results; Receive fault information reported by sensors within the park, and diagnose the fault information based on stored triplet information to obtain diagnostic results, specifically including: The system receives fault information reported by sensors within the park, processes it into an XML document, and extracts various attribute values ​​from the XML document, including equipment type, equipment code, equipment location, and fault phenomenon. Based on the equipment type and fault phenomenon, the system queries the equipment type code and fault phenomenon code respectively and generates a fault code that uniquely corresponds to the equipment type and fault phenomenon. Search for the fault node corresponding to the fault code in the historical fault information associated with the equipment type. If the query result is true, return the fault solution based on the information associated with the fault node. If the query result is empty, match the fault phenomenon keywords in the historical faults of the equipment associated with the equipment code to query all solutions. If a solution is found, return it; otherwise, prompt the maintenance personnel to handle it.

Images