Equipment fault diagnosis and maintenance management system based on knowledge graph

Through the equipment fault diagnosis and maintenance management system based on knowledge graph, a fault maintenance knowledge graph is built, which solves the problems of inefficient maintenance efficiency and long equipment downtime caused by relying on manual experience in the existing technology, and achieves rapid fault diagnosis and optimized maintenance Resource allocation improves overall maintenance efficiency and accuracy.

CN119048048APending Publication Date: 2024-11-29湖南润伟智能机器有限公司 +1
View PDF 0 Cites 4 Cited by

Patent Information

Application Number
CN202410988639.9
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-07-23
Publication Date
2024-11-29

AI Technical Summary

Technical Problem

The existing technology relies on manual experience to analyze the causes of failures and formulate maintenance plans, resulting in ineffective maintenance and long downtime of equipment.

Method used

The equipment fault diagnosis and maintenance management system based on knowledge graph is adopted, including fault diagnosis modules, construction modules and update modules, to build fault maintenance knowledge graphs, obtain entities and relationships through historical fault records, and achieve rapid fault diagnosis and maintenance plan generation.

Benefits of technology

It shortens the fault diagnosis time, improves maintenance efficiency and accuracy, optimizes the allocation of maintenance resources, and reduces equipment downtime and maintenance costs.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119048048A_ABST
    Figure CN119048048A_ABST
Patent Text Reader

Abstract

The invention discloses an equipment fault diagnosis and maintenance management system based on a knowledge graph, relates to the technical field of equipment fault diagnosis and maintenance management, and solves the technical problems of low maintenance efficiency and long equipment downtime caused by the fact that the prior art depends on manual experience to analyze fault causes and formulate a maintenance scheme. The method comprises the following steps: constructing a fault maintenance knowledge graph of equipment based on historical fault records; performing similarity analysis on the fault phenomenon of the fault equipment and the fault phenomenon in the fault maintenance knowledge graph to obtain a matched fault phenomenon so as to obtain an associated fault reason, a fault part and a maintenance scheme; by matching the real-time fault phenomenon with a large number of historical cases in the knowledge graph, the system can quickly identify the fault type, so that the fault diagnosis time is greatly shortened, the maintenance response speed is accelerated, and the equipment downtime is shortened.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention belongs to the field of equipment fault diagnosis and maintenance management, and specifically to an equipment fault diagnosis and maintenance management system based on a knowledge graph. Background Art

[0002] With the rapid development of intelligent manufacturing, modern industrial equipment is becoming increasingly complex, and the level of automation and intelligence is constantly improving, which puts higher requirements on equipment maintenance and fault management. The traditional fault diagnosis and maintenance model relies on manual experience judgment and post-maintenance, which often leads to problems such as low maintenance efficiency, long equipment downtime, and high maintenance costs. In this context, the equipment fault diagnosis and maintenance management system based on knowledge graph came into being and became one of the key technologies to improve the level of equipment maintenance management.

[0003] The invention patent application with publication number CN17242412A discloses a fault diagnosis method and a fault diagnosis device. The method includes: after the fault diagnosis device establishes a wireless connection with a first electrical device, the fault diagnosis device sends a first instruction to the first electrical device, the first instruction is used to request to read the fault information of the first battery on the first electrical device; the fault diagnosis device receives the fault information of the first battery sent by the first electrical device based on the first instruction; the fault diagnosis device analyzes the fault information of the first battery, and controls the output device of the fault diagnosis device to output the current fault of the first battery to the diagnostic personnel.

[0004] The above-mentioned prior art requests the battery fault information on the first electrical device through the first instruction of the first electrical device and sends it to the diagnostic personnel, which only saves the fault diagnosis time, and still needs to rely on manual experience to analyze the cause of the fault and formulate a maintenance plan, resulting in low maintenance efficiency and long equipment downtime. Therefore, the present invention proposes an equipment fault diagnosis and maintenance management system based on knowledge graph. Summary of the invention

[0005] The present invention aims to solve at least one of the technical problems existing in the prior art; to this end, the present invention proposes an equipment fault diagnosis and maintenance management system based on a knowledge graph, which is used to solve the technical problem that the prior art relies on manual experience to analyze the cause of the fault and formulate maintenance plans, resulting in low maintenance efficiency and long equipment downtime.

[0006] To achieve the above-mentioned object, the first aspect of the present invention provides a knowledge graph-based equipment fault diagnosis and maintenance management system, including a fault diagnosis module, and a construction module and an update module connected thereto;

[0007] Building module: used to build the equipment fault maintenance knowledge graph;

[0008] Fault repair module: used to diagnose equipment faults and output repair solutions;

[0009] Update module: used to update the equipment fault repair knowledge graph.

[0010] Preferably, the construction of the equipment fault maintenance knowledge graph includes:

[0011] Obtain historical fault information of the equipment from historical fault records; wherein the historical fault information includes faulty equipment, faulty parts, faulty operation data, phenomena, fault causes and maintenance plans;

[0012] The acquired historical fault information is used as the entity in the knowledge graph, and the relationship between the entities is obtained from the fault records to construct the entity-relationship-entity triple data group of the knowledge graph to obtain the fault maintenance knowledge graph.

[0013] Preferably, the relationship between the entities includes the relationship between equipment and components; the connection relationship between components; the relationship between fault phenomenon and fault cause, the relationship between fault cause and faulty component; and the relationship between faulty component and maintenance plan.

[0014] The present invention obtains historical fault information from fault records and constructs a knowledge graph of equipment fault maintenance. The knowledge graph has a clear structure and supports rapid search for all information related to the fault. Maintenance personnel can quickly obtain related information by querying any entity such as a specific fault phenomenon, equipment component or maintenance plan, thus shortening the fault diagnosis time. This improves the efficiency and accuracy of fault maintenance and lays a solid foundation for realizing intelligent maintenance and management.

[0015] Preferably, the fault diagnosis of the equipment includes:

[0016] Obtain the operating data of the device, compare the operating data with the corresponding threshold range, and determine whether the operating data are all within the corresponding threshold range; if not, obtain the fault phenomenon and analyze the cause of the equipment failure; if yes, the device is normal; wherein the operating data includes temperature, current, voltage and vibration amplitude.

[0017] The present invention realizes early fault detection by real-time monitoring of the operating data of the equipment, and promptly discovers the situation where the equipment deviates from the normal operating parameters. Once it is found that the operating data exceeds the threshold, the fault phenomenon can be quickly locked, and the relevant information of the fault can be obtained through the fault maintenance knowledge graph to reduce the troubleshooting time; thus, measures can be taken before the fault occurs to avoid production interruption or equipment damage caused by sudden faults, extend equipment life and reduce maintenance costs.

[0018] Preferably, the failure cause of the analysis device includes:

[0019] The semantic similarity of the equipment's fault phenomenon is compared with the fault phenomenon in the fault maintenance knowledge graph. If the semantic similarity value is greater than the preset threshold, the fault phenomenon in the fault maintenance knowledge graph is the matching fault phenomenon; the fault cause associated with the matching fault phenomenon is the fault cause of the equipment.

[0020] The present invention analyzes the similarity values ​​between fault phenomena through semantic similarity, and can quickly locate the most likely cause of the fault in a short time, greatly shortening the fault diagnosis time and improving maintenance efficiency. Compared with the traditional diagnosis method that relies on personal experience, the automatic matching based on the knowledge graph reduces the influence of subjective judgment and improves the accuracy and consistency of diagnosis.

[0021] Preferably, the associated faulty component information is obtained based on the fault cause; and the fault level of the faulty component is analyzed based on the faulty component information; wherein the faulty component information includes the component number, service life, number of repairs and working hours.

[0022] Preferably, analyzing the fault level of the faulty component according to the faulty component information includes:

[0023] The life index DJ of the faulty component is calculated by the formula DJ=SM / (ln(WX)+ln(GZ)); the life index is compared with the corresponding life index range to obtain the fault level of the faulty component; wherein SM is the rated service life, WX is the number of repairs, and GZ is the working time;

[0024] If the life index is lower than the corresponding life index range, the fault level of the faulty component is level one;

[0025] If the life index is within the corresponding life index range, the fault level of the faulty component is level 2;

[0026] If the life index is greater than the corresponding life index range, the failure level of the faulty component is level three.

[0027] The present invention evaluates the repair complexity of faulty parts by scoring the structural complexity of the parts and the required repair time, thereby achieving scientific sorting of priorities, facilitating efficient allocation of repair resources, and ensuring that the most critical and urgent repair tasks are given priority; at the same time, it ensures that maintenance personnel can work in the most efficient manner, thereby shortening the overall maintenance cycle and improving maintenance efficiency.

[0028] Preferably, the fault repair module outputs a corresponding repair plan according to the cause of the fault, and repairs the faulty components in sequence according to the fault level; wherein the fault degree of the faulty equipment is divided according to the fault level, level one>level two>level three.

[0029] Preferably, when several devices fail, the failure phenomenon of each device is obtained according to the failure repair knowledge graph, and the repair plan corresponding to the failure phenomenon is obtained, including the repair complexity score and the repair time;

[0030] Based on the maintenance plan, the formula FZ=γ×P ln(T) Obtain the maintenance complexity index FZ; sort the maintenance complexity index from large to small, and arrange the maintenance tasks in sequence; the maintenance complexity score is scored by maintenance experts; γ is the proportional coefficient.

[0031] The present invention analyzes the maintenance complexity of each device when multiple devices fail through a maintenance complexity index; by giving priority to tasks with low maintenance complexity, multiple jobs can be completed in a shorter time, quickly reducing the total number of devices to be repaired, freeing up space and resources for handling complex maintenance tasks, optimizing the maintenance process as a whole, and improving work efficiency; and the efficient sequencing and execution of maintenance tasks can significantly reduce the downtime of equipment waiting for maintenance. For manufacturing enterprises, this means maintaining production capacity and controlling production costs, avoiding economic losses caused by long-term equipment downtime.

[0032] Preferably, the updating of the fault maintenance knowledge graph of the equipment includes:

[0033] The similarity value between each equipment failure phenomenon and the failure phenomenon in the failure maintenance knowledge graph is calculated; the equipment failure maintenance information is updated to the corresponding failure maintenance knowledge graph; when the failure phenomenon does not exist in the failure knowledge maintenance graph, the failure maintenance information is added to the failure maintenance knowledge graph.

[0034] Compared with the prior art, the present invention has the following beneficial effects:

[0035] 1. The present invention integrates scattered historical fault information into a unified knowledge graph and uses it as an entity in the knowledge graph. It also organizes the relationship between historical fault information, constructs a ternary array of the knowledge graph, and obtains a fault maintenance knowledge graph. This realizes centralized management of information, facilitates query and update, and ensures the systematicness, integrity, and timeliness of fault maintenance knowledge.

[0036] 2. When multiple parts of the same equipment or multiple equipment fail, the present invention sorts the maintenance tasks according to the failure level of the failed parts or the maintenance complexity index of the failed equipment, and prioritizes the tasks that have the greatest impact on production or are less difficult to maintain, ensuring that limited maintenance resources such as manpower, spare parts, tools, etc. are efficiently utilized, reducing maintenance delays caused by improper resource allocation;

[0037] 3. The present invention constructs a knowledge graph of equipment fault maintenance; performs similarity analysis between the fault phenomenon of the faulty equipment and the fault phenomenon in the knowledge graph of fault maintenance, thereby obtaining the fault information of the equipment and outputting the corresponding maintenance plan; provides an information platform for the equipment that integrates fault detection, analysis, positioning, and plan generation, greatly shortens the troubleshooting time, and improves the efficiency of maintenance work; at the same time, with the continuous enrichment of fault cases and the accumulation of maintenance experience, the knowledge graph can be continuously updated and improved, promoting the iterative optimization of maintenance strategies and promoting the intelligent development of maintenance management. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0039] Figure 1 It is a system structure block diagram of the present invention;

[0040] Figure 2 It is a flowchart of the method of the present invention;

[0041] Figure 3 This is a flowchart of a method for analyzing maintenance priorities of several faulty parts of the present invention;

[0042] Figure 4 The present invention is a flowchart of a method for analyzing maintenance priorities of several faulty equipments. DETAILED DESCRIPTION

[0043] The technical solution of the present invention will be clearly and completely described below in conjunction with the embodiments. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0044] See also Figure 1-Figure 2 , the first aspect of the present invention provides an equipment fault diagnosis and maintenance management system based on knowledge graph, including a fault diagnosis module, and a construction module and an update module connected thereto;

[0045] The construction module is used to construct the equipment fault maintenance knowledge graph;

[0046] Obtain historical fault information of the equipment from historical fault records; wherein the historical fault information includes faulty equipment, faulty parts, faulty operation data, phenomena, fault causes and maintenance plans;

[0047] The acquired historical fault information is used as the entity in the fault maintenance knowledge graph, and the relationship between the entities is obtained from the fault records to construct the entity-relationship-entity triple data group of the fault maintenance knowledge graph.

[0048] The relationships between the entities include the relationship between equipment and parts; the connection relationship between parts; the relationship between fault phenomenon and fault cause, the relationship between fault cause and faulty parts; and the relationship between faulty parts and maintenance plans.

[0049] For example, an industrial robot may contain multiple parts such as motors, sensors, and controllers. In the knowledge graph, each device node is connected to a series of component nodes, and each connection edge is marked as "included", and the model, location, and other information of the component are recorded in detail through attributes.

[0050] Connection relationships between components: describes how different components are physically or logically connected to each other. For example, a motor is connected to a controller via a cable. In the knowledge graph, two component nodes are connected via a "connected to" edge, and additional information such as connection type (electrical, mechanical), interface standard, etc. can be added.

[0051] Relationship between fault phenomenon and fault cause: This relationship links the fault phenomenon (such as "device overheating") to the potential fault cause (such as "cooling fan failure"). In the knowledge graph, a fault phenomenon node points to one or more possible fault cause nodes. Through the "cause" edge, the system can reversely infer the possible fault source from the observed phenomenon.

[0052] Relationship between the cause of the fault and the faulty component: This relationship is particularly important when it is determined that a fault is caused by a specific component failure, such as a "circuit board short" affecting a "power supply unit". It helps the system directly locate the component that needs to be checked or replaced, speeding up the repair process.

[0053] Relationship between faulty parts and maintenance solutions: Once the faulty parts are identified, the knowledge graph needs to provide the corresponding maintenance strategy, i.e., the "maintenance solution". For example, "replace the motor" is the maintenance action for the faulty part "burnt motor". This "need" relationship not only specifies the specific operation, but also can include detailed maintenance guidelines such as required tools, spare parts, and time estimates.

[0054] By carefully constructing and maintaining these relationships, the knowledge graph can support the system in performing efficient reasoning. For example, starting from the fault symptoms exhibited by the equipment, through a series of association analyses, it can ultimately recommend the most reasonable maintenance plan.

[0055] The fault repair module is used to diagnose equipment faults and output repair plans;

[0056] Specifically, the operating data of the equipment is obtained, and the operating data is compared with the corresponding threshold range to determine whether the operating data are all within the corresponding threshold range; if not, the fault phenomenon is obtained and the cause of the equipment failure is analyzed; if yes, the equipment is normal; wherein the operating data includes temperature, current, voltage and vibration amplitude.

[0057] The semantic similarity of the equipment's fault phenomenon is compared with the fault phenomenon in the fault maintenance knowledge graph. If the semantic similarity value is greater than the preset threshold, the fault phenomenon in the fault maintenance knowledge graph is the matching fault phenomenon; the fault cause associated with the matching fault phenomenon is the fault cause of the equipment.

[0058] According to the cause of the failure, the associated faulty parts information is obtained; wherein the faulty parts information includes the part number, service life, number of repairs and working hours.

[0059] For example, the temperature and current of a certain industrial equipment are abnormal, and the fault phenomena are fault phenomenon 1 and fault phenomenon 2 respectively; the fault phenomena in the fault maintenance knowledge graph are compared, assuming that there are fault phenomenon A, fault phenomenon B, fault phenomenon C, etc., and semantic similarity analysis is performed respectively; if the similarity value of fault phenomenon 1 and fault phenomenon B reaches a preset threshold (the preset threshold can be set to a higher similarity ratio such as 95%), then fault phenomenon B is a matching fault phenomenon; if the similarity value of fault phenomenon 2 and fault phenomenon A reaches a preset threshold, then fault phenomenon A is a matching fault phenomenon;

[0060] Obtain the associated fault cause through fault phenomenon B, that is, the fault cause of fault phenomenon 1, and further obtain the associated fault component information through the fault cause, that is, the fault component information corresponding to fault phenomenon 1, and then obtain the corresponding maintenance plan for fault phenomenon 1;

[0061] The associated fault cause is obtained through fault phenomenon A, that is, the fault cause of fault phenomenon 2. The associated fault component information is further obtained through the fault cause, that is, the fault component information corresponding to fault phenomenon 2, and then the corresponding maintenance plan for fault phenomenon 2 is obtained.

[0062] See also Figure 3 , analyzing the fault level of the faulty component according to the faulty component information;

[0063] The life index DJ of the faulty component is calculated by the formula DJ=SM / (ln(WX)+ln(GZ)); the life index is compared with the corresponding life index range to obtain the fault level of the faulty component; wherein SM is the rated service life, WX is the number of maintenance times, and GZ is the working time.

[0064] It should be noted that the rated service life, number of repairs and working hours are all obtained from historical fault records; the rated service life is the usable time set for the equipment when it leaves the factory and is a fixed parameter; the working time is the length of time the faulty component has been working from the start of work to the occurrence of the fault.

[0065] The present invention evaluates the remaining life of a faulty component through a life index; the evaluation of the remaining life is closely related to the rated service life, the number of repairs, and the working time; if a faulty component has been repaired more times and has been working for a longer time, it indicates that the faulty component has a high failure frequency during operation and has been working for a longer time, and its continuously usable life is shorter, that is, the life index is smaller.

[0066] If the life index is lower than the corresponding life index range, the fault level of the faulty component is level one;

[0067] If the life index is within the corresponding life index range, the fault level of the faulty component is level 2;

[0068] If the life index is greater than the corresponding life index range, the failure level of the faulty component is level three.

[0069] The faulty parts are repaired in sequence according to the fault level; among them, the fault degree of the faulty equipment is divided according to the fault level, level one>level two>level three.

[0070] See also Figure 4 ,When several devices fail, the fault phenomenon of each faulty device is obtained based on the fault maintenance knowledge graph, and the maintenance scheme associated with the fault phenomenon is obtained, including the component structure complexity score and the maintenance time;

[0071] Based on the maintenance plan, the formula FZ=γ×P ln(T) Get the maintenance complexity index FZ; sort the maintenance complexity index from small to large, and arrange the maintenance tasks in sequence; where P is the component structure complexity score, which is scored by maintenance experts; T is the maintenance time; γ is the proportional coefficient, which defaults to 1.

[0072] The present invention analyzes the maintenance complexity of each device when multiple devices fail through a maintenance complexity index; wherein the maintenance complexity is closely related to the component structure complexity score and the maintenance time; if the structure of the faulty component is more complex and the maintenance time required for the fault is longer, it indicates that the faulty component is more difficult to repair, the maintenance plan is more complex, and a lot of time and effort are required, so the maintenance complexity index is higher.

[0073] The update module is used to update the equipment fault repair knowledge graph, including:

[0074] The similarity value between each equipment failure phenomenon and the failure phenomenon in the failure maintenance knowledge graph is calculated; the equipment failure maintenance information is updated to the corresponding failure maintenance knowledge graph; when the failure phenomenon does not exist in the failure knowledge maintenance graph, the failure maintenance information is added to the failure maintenance knowledge graph.

[0075] Part of the data in the above formula is calculated by removing the dimension and taking its numerical value. The formula is a formula closest to the actual situation obtained by software simulation of a large amount of collected data; the preset parameters and preset thresholds in the formula are set by technical personnel in this field according to actual conditions or obtained through simulation of a large amount of data.

[0076] The above embodiments are only used to illustrate the technical method of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical method of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical method of the present invention.

Claims

1. Equipment fault diagnosis and maintenance management system based on knowledge graph, characterized by: It includes a fault diagnosis module, and a building module and an updating module connected thereto; Building module: used to build the equipment fault maintenance knowledge graph; Fault repair module: used to diagnose equipment faults and output repair solutions; Update module: used to update the equipment fault repair knowledge graph.

2. The equipment fault diagnosis and maintenance management system based on knowledge graph according to claim 1 is characterized in that: The construction of the equipment fault maintenance knowledge graph includes: Obtain historical fault information of the equipment from historical fault records; wherein the historical fault information includes faulty equipment, faulty parts, faulty operation data, phenomena, fault causes and maintenance plans; The acquired historical fault information is used as the entity in the knowledge graph, and the relationship between the entities is obtained from the fault records to construct the entity-relationship-entity triple data group of the knowledge graph to obtain the fault maintenance knowledge graph.

3. The equipment fault diagnosis and maintenance management system based on knowledge graph according to claim 2 is characterized in that: The relationships between the entities include the relationship between equipment and parts; the connection relationship between parts; the relationship between fault phenomenon and fault cause, the relationship between fault cause and faulty parts; and the relationship between faulty parts and maintenance plans.

4. The equipment fault diagnosis and maintenance management system based on knowledge graph according to claim 1 is characterized in that: The diagnostic equipment failure includes: Obtain the operating data of the device, compare the operating data with the corresponding threshold range, and determine whether the operating data are all within the corresponding threshold range; if not, obtain the fault phenomenon and analyze the cause of the equipment failure; if yes, the device is normal; wherein the operating data includes temperature, current, voltage and vibration amplitude.

5. The equipment fault diagnosis and maintenance management system based on knowledge graph according to claim 4 is characterized in that: The reasons for the failure of the analysis device include: The semantic similarity of the equipment's fault phenomenon is compared with the fault phenomenon in the fault maintenance knowledge graph. If the semantic similarity value is greater than the preset threshold, the fault phenomenon in the fault maintenance knowledge graph is the matching fault phenomenon; the fault cause associated with the matching fault phenomenon is the fault cause of the equipment.

6. The equipment fault diagnosis and maintenance management system based on knowledge graph according to claim 5 is characterized in that: According to the cause of the fault, the associated faulty component information is obtained; according to the faulty component information, the fault level of the faulty component is analyzed; wherein the faulty component information includes the component number, service life, number of repairs and working hours.

7. The equipment fault diagnosis and maintenance management system based on knowledge graph according to claim 6 is characterized in that: Analyzing the fault level of the faulty component according to the faulty component information includes: The life index DJ of the faulty component is calculated by the formula DJ=SM / (ln(WX)+ln(GZ)); the life index is compared with the corresponding life index range to obtain the fault level of the faulty component; wherein SM is the rated service life, WX is the number of repairs, and GZ is the working time; If the life index is lower than the corresponding life index range, the fault level of the faulty component is level one; If the life index is within the corresponding life index range, the fault level of the faulty component is level 2; If the life index is greater than the corresponding life index range, the failure level of the faulty component is level three.

8. The equipment fault diagnosis and maintenance management system based on knowledge graph according to claim 7 is characterized in that: The fault repair module outputs a corresponding repair plan according to the cause of the fault, and repairs the faulty parts in sequence according to the fault level. The fault degree of the faulty equipment is divided according to the fault level, level one>level two>level three.

9. The equipment fault diagnosis and maintenance management system based on knowledge graph according to claim 1 is characterized in that: When several devices fail, the fault phenomenon of each device is obtained based on the fault maintenance knowledge graph, and the maintenance plan corresponding to the fault phenomenon is obtained, including the maintenance complexity score and maintenance time; Based on the maintenance plan, the formula FZ=γ×P ln(T) Obtain the maintenance complexity index FZ; sort the maintenance complexity index from large to small, and arrange the maintenance tasks in sequence; the maintenance complexity score is scored by maintenance experts; γ is the proportional coefficient.

10. The equipment fault diagnosis and maintenance management system based on knowledge graph according to claim 1 is characterized in that: The updating device fault repair knowledge graph includes: The similarity value between each equipment failure phenomenon and the failure phenomenon in the failure maintenance knowledge graph is calculated; the equipment failure maintenance information is updated to the corresponding failure maintenance knowledge graph; when the failure phenomenon does not exist in the failure knowledge maintenance graph, the failure maintenance information is added to the failure maintenance knowledge graph.

Citation Information

Cited By

  • Knowledge graph-based equipment maintenance decision-making method, equipment, medium and product

    CN120106827A

  • Sewage plant multivariate heterogeneous data warehouse construction method and system

    CN120316095A

  • Electromechanical equipment fault diagnosis method and device, equipment and storage medium

    CN120372021A

  • Vehicle maintenance processing method and device

    CN122222603A