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

Abstract

The invention discloses an equipment maintenance decision-making method and equipment based on a knowledge graph, a medium and a product, and relates to the technical field of intelligent maintenance, and the method comprises the steps: constructing the knowledge graph according to historical data of various types of equipment; the historical data comprises historical operation state data and historical maintenance data; preprocessing the current running state data of each type of equipment, and determining the preprocessed running state data; determining an operation deviation rate according to the preprocessed operation state data and preset operation state data; and on the basis of the knowledge graph, according to the operation deviation rate and a preset operation deviation rate threshold value, generating maintenance strategies of various types of equipment. Defects caused by excessive relying on personal experience of technicians are avoided, and the accuracy of equipment fault diagnosis and the maintenance efficiency are improved.

Description

Technical Field

[0001] The present application relates to the field of intelligent maintenance technology, and in particular to a knowledge graph-based equipment maintenance decision-making method, device, medium and product. Background Art

[0002] In the field of maintenance guidance for complex equipment, the main means currently adopted are still for professional maintenance personnel to perform equipment maintenance, equipment inspection, equipment fault repair and other maintenance work through their own experience, maintenance instruction manuals, industry specification materials, etc. This maintenance mode, due to the influence of human factors, often leads to problems such as untimely problem handling, unreasonable maintenance methods, and waste of maintenance human resources; in terms of equipment maintenance and overhaul, the traditional regular maintenance and overhaul mode is no longer applicable. Too frequent maintenance and overhaul will cause serious waste of manpower and time costs. Untimely maintenance and overhaul will cause equipment failures and even safety accidents. Under different environmental conditions, the inspection and maintenance time provided by equipment manufacturers often has a large deviation, which leads to the fact that the actual effect of preventive maintenance based on the inspection and maintenance suggestions provided by manufacturers or industries is often not ideal. Therefore, there is an urgent need for a method that can avoid excessive reliance on the personal experience of technicians and can improve the accuracy of fault diagnosis and maintenance efficiency. Summary of the invention

[0003] The purpose of this application is to provide a knowledge graph-based equipment maintenance decision-making method, device, medium and product, which can solve the problems of inaccurate and low efficiency of equipment maintenance diagnosis in related technologies.

[0004] To achieve the above objectives, this application provides the following solutions: In a first aspect, the present application provides an equipment maintenance decision-making method based on a knowledge graph, comprising: constructing a knowledge graph based on historical data of various types of equipment; the historical data includes historical operating status data and historical maintenance data; the historical operating status data includes real-time parameters of various types of equipment; preprocessing the current operating status data of various types of equipment to determine the preprocessed operating status data; determining the operating deviation rate based on the preprocessed operating status data and preset operating status data; based on the knowledge graph, generating maintenance strategies for various types of equipment according to the operating deviation rate and a preset operating deviation rate threshold.

[0005] In a second aspect, the present application provides a computer device, comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the equipment maintenance decision method based on the knowledge graph described above.

[0006] In a third aspect, the present application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the equipment maintenance decision-making method based on the knowledge graph described above.

[0007] In a fourth aspect, the present application provides a computer program product, including a computer program, which, when executed by a processor, implements the equipment maintenance decision-making method based on the knowledge graph described above.

[0008] According to the specific embodiments provided in this application, this application discloses the following technical effects.

[0009] This application first constructs a knowledge graph based on the historical data of various types of equipment, and then preprocesses the current operating status data of various types of equipment to determine the preprocessed operating status data. And determine the operating deviation rate based on the preprocessed operating status data and the preset operating status data. Based on the knowledge graph, maintenance strategies for various types of equipment are generated according to the operating deviation rate and the preset operating deviation rate threshold. That is, through the constructed knowledge graph, equipment failures are automatically diagnosed and corresponding maintenance strategies are given, avoiding the disadvantages caused by excessive reliance on the personal experience of technicians, and improving the accuracy of equipment fault diagnosis and maintenance efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0011] Figure 1 A flow chart of a knowledge graph-based equipment maintenance decision-making method provided in an embodiment of the present application.

[0012] Figure 2 This is a flow chart of the knowledge graph construction method provided in the embodiments of this application. DETAILED DESCRIPTION

[0013] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0014] In order to make the above-mentioned objects, features and advantages of the present application more obvious and easy to understand, the present application is further described in detail below in conjunction with the accompanying drawings and specific implementation methods.

[0015] like Figure 1 and Figure 2 As shown, the present application provides an equipment maintenance decision method based on a knowledge graph, including: Step 101: construct a knowledge graph based on historical data of various types of equipment; the historical data includes historical operating status data and historical maintenance data; the historical operating status data includes real-time parameters of various types of equipment.

[0016] Wherein, the real-time parameters include at least temperature, pressure and rotation speed.

[0017] Step 102: pre-process the current operating status data of each type of equipment to determine the pre-processed operating status data.

[0018] Step 103: Determine the operation deviation rate according to the preprocessed operation status data and the preset operation status data.

[0019] Step 104: Based on the knowledge graph, maintenance strategies for various types of equipment are generated according to the operation deviation rate and a preset operation deviation rate threshold.

[0020] In some embodiments, step 101 specifically includes steps 201 and 202.

[0021] Step 201: Analyze and sort out the historical data of the same type of equipment to determine the relationship matching degree between the historical operating status data and the historical maintenance data of the same type of equipment.

[0022] Step 202: Determine the knowledge graph based on the relationship matching between the historical operating status data and the historical maintenance data of each type of equipment, and a preset matching threshold.

[0023] In some embodiments, step 201 specifically includes: extracting and summarizing entities and entity relationships in equipment manuals and historical maintenance data; the entities include equipment components, operating status data, fault types and maintenance operation data; the entity relationships include the relationship between equipment components and operating status data, the relationship between fault types and abnormal operating status data, and the relationship between fault types and maintenance operation data; based on the entities and the entity relationships, statistically analyzing the abnormal distribution of operating status data corresponding to different fault types and the frequency of different fault types occurring in various types of equipment in different operating time periods; based on the abnormal distribution of operating status data and the frequency of different fault types, establishing an association relationship between historical operating status data and fault types, and calculating the relationship matching degree between historical operating status data and historical maintenance data of the same type of equipment.

[0024] In some embodiments, step 202 specifically includes: determining whether the relationship matching degree is greater than or equal to a preset matching degree threshold to obtain a second judgment result; if the second judgment result is yes, adding the relationship between the historical operating status data and maintenance data of the equipment to the maintenance manual and maintenance case to obtain the knowledge graph; if the second judgment result is no, eliminating the historical maintenance data and updating the maintenance manual or maintenance case; the historical data also includes a maintenance manual and maintenance cases.

[0025] In some embodiments, step 104 specifically includes steps 301 to 303 .

[0026] Step 301: Determine whether the operation deviation rate is greater than or equal to a preset operation deviation rate threshold, and determine a first determination result.

[0027] Step 302: If the first judgment result is yes, generate abnormal operating status data corresponding to each type of equipment, and analyze the abnormal operating status data based on the knowledge graph to generate maintenance strategies for each type of equipment.

[0028] Step 303: If the first judgment result is no, the current operating status data of each type of equipment is monitored in real time, and the current operating status data of each type of equipment is transmitted to the terminal in real time.

[0029] In some embodiments, step 302 specifically includes: extracting key features of the abnormal operating status data; the key features include at least an offset value and a frequency of occurrence of the offset value when an abnormality occurs in a real-time parameter; determining the fault type of each type of equipment and the maintenance operation guidance plan associated with the fault type based on the knowledge graph and the key features; and using the maintenance operation guidance plan as the maintenance strategy.

[0030] The present application obtains equipment historical data based on big data technology, and constructs a knowledge graph based on the equipment historical data; obtains equipment operating status data, preprocesses the equipment operating status data, and obtains preprocessed operating status data; compares the preprocessed operating status data with the set status data to obtain the operating deviation rate; determines whether the operating deviation rate is greater than or equal to the set operating deviation rate threshold; if greater than or equal to, generates abnormal operating status data, analyzes the abnormal operating status data based on the knowledge graph, and generates a maintenance strategy; if less than, monitors the equipment operating status data in real time, and transmits the equipment operating status data to the terminal in real time; automatically diagnoses the cause of the equipment failure through the constructed knowledge graph, and gives corresponding solutions to avoid excessive reliance on the personal experience of technicians, improve the accuracy of fault diagnosis, and improve maintenance efficiency.

[0031] In practical applications, the method of determining the intelligent maintenance strategy of equipment through knowledge graph in this application is used for terminal equipment, and the specific steps are as follows.

[0032] Step 401, obtain historical data of equipment based on big data technology, and build a knowledge graph based on the historical data of equipment.

[0033] Step 402, acquiring the running status data of the equipment, and preprocessing the running status data of the equipment to obtain the preprocessed running status data.

[0034] Step 403, comparing the preprocessed running status data with the set running status data to obtain the running deviation rate.

[0035] Step 404: determine whether the operation deviation rate is greater than or equal to a set operation deviation rate threshold.

[0036] Step 405: if it is greater than or equal to, abnormal operation status data is generated, the abnormal operation status data is analyzed based on the knowledge graph, and a maintenance strategy is generated; if it is less than, the equipment operation status data is monitored in real time and the equipment operation status data is transmitted to the terminal in real time.

[0037] It should be noted that by constructing a knowledge graph to analyze the abnormal operating status data of the equipment, a matching maintenance strategy can be generated to ensure that the equipment can be repaired quickly and improve the operating safety of the equipment.

[0038] Specifically, the pre-processed operating status data covers various real-time parameters of the equipment, such as temperature, pressure, speed, etc.; the set operating status data is the standard value of each parameter determined according to the equipment design standard, ideal operating conditions, etc. Before making a comparison, it is necessary to ensure that the parameters in the two types of data correspond one to one. For example, the temperature value in the operating status data must correspond to the standard temperature value in the set status data, and the same applies to parameters such as pressure and speed. During the data collection and sorting process, the parameters are clearly identified and classified for accurate matching. For each corresponding parameter, its deviation value is calculated. For example, the normal operating temperature set for a certain equipment is 50°C, and the real-time temperature data after preprocessing is 55°C, then the deviation of the temperature parameter is 5°C. In this way, the deviation of each parameter from the standard value can be intuitively seen, whether it is higher or lower than the standard value, it can be clearly presented. After obtaining the deviation of a single parameter, the operating deviation rate is further calculated. The calculation formula for the operating deviation rate is: operating deviation rate = (operating status data deviation of a single parameter / set operating status data) × 100%.

[0039] Among them, step 401 specifically includes: step 501, obtaining the maintenance manual, maintenance case and historical maintenance record data of the equipment based on big data technology; step 502, sorting out the historical data of the same equipment from the maintenance manual, maintenance case and historical maintenance record to obtain the relationship between the equipment operation status data and the maintenance data; step 503, analyzing the relationship matching degree between the equipment operation status data and the maintenance data; step 504, judging whether the relationship matching degree is greater than or equal to the set matching degree threshold; step 505, if it is greater than or equal to the set matching degree threshold, then adding the relationship between the equipment operation status data and the maintenance data to the maintenance manual and maintenance case to obtain a knowledge graph; if it is less than the set matching degree threshold, then eliminating the maintenance data and updating the maintenance manual or maintenance case.

[0040] Specifically, in the operation of various complex systems (such as industrial equipment, information systems, etc.), abnormal operating status data frequently appears. As a semantic network, knowledge graph can integrate various knowledge related to system operation and provide a powerful tool for abnormal operating status data analysis.

[0041] The knowledge graph construction method is as follows: Determine the source of knowledge: collect equipment manuals, technical documents, historical fault records, expert experience, etc. For example, for industrial equipment, the equipment manual provides information such as the structure, performance parameters, and normal operation indicators of the equipment; historical fault records contain the fault phenomena, causes, and solutions that occurred in the past. Entity and relationship extraction: Entity extraction: Extract relevant entities from knowledge sources, such as equipment components (motors, valves, etc.), operating parameters (temperature, pressure, speed), fault types (short circuit, overload, leakage), etc. Relationship extraction: Determine the relationship between entities, such as "equipment components-operating parameters", "fault type-abnormal phenomenon", "maintenance operation-solution-fault type", etc. For example, the motor and speed have a corresponding relationship between operating parameters, and a short circuit will cause abnormal equipment shutdown. Specifically, the maintenance manual is parsed, and the parsed text information is organized according to a specific data structure, such as using a table to list the equipment component name, normal operating parameters, fault type, fault cause, maintenance operation, etc. as different fields, which is convenient for subsequent data processing and analysis. Professional equipment maintenance websites, forums, and the company's internal maintenance case database are visited to collect maintenance cases related to the target equipment. The maintenance case contains a detailed description of the actual maintenance process, such as the operating status of the equipment when the fault occurred, the detection methods adopted, the final cause of the fault, and the feedback on the effect after the maintenance.

[0042] Statistics are collected on the distribution of equipment operating parameters corresponding to different fault types. For example, when an engine overheats, the average, maximum, and minimum values ​​of operating parameters such as coolant temperature and oil temperature are analyzed, and by comparing the parameter range during normal operation, the abnormal changes in operating parameters are determined to be closely related to the overheating fault. Relationship between fault frequency and operation time: Statistics on the frequency of various types of faults in equipment during different operation time periods. By drawing a curve of fault frequency versus operation time, we can analyze the types of faults that are prone to occur in the early, middle and late stages of equipment use, as well as the potential patterns between fault frequency and operation time. For example, it was found that the frequency of component wear failures of a certain type of equipment increased significantly after 5,000 hours of operation.

[0043] Mining association rules with certain support and confidence from equipment operation status data and maintenance data. For example, it is found that when the vibration value of the equipment exceeds a certain threshold and the temperature rises at the same time, there is an 80% probability that the mechanical parts will loosen. Thus, the association rules between the operation status data and the fault type are established and the matching degree is calculated.

[0044] It should be noted that by analyzing the historical maintenance record information of the equipment, the contents of the maintenance cases and maintenance manuals are sorted out to ensure the accuracy of the maintenance cases, and the maintenance manuals and maintenance cases are continuously supplemented based on the historical maintenance records to realize the learning ability of the knowledge graph.

[0045] Wherein, step 402 also includes the following steps.

[0046] Step 601, obtaining the operating status data of the equipment and extracting data features.

[0047] Step 602, normalize the data features to obtain processed data features.

[0048] Step 603, determining whether the processed data feature is within a set feature interval.

[0049] Step 604: If the data is not within the set feature interval, the corresponding data feature is removed.

[0050] Step 605: If it is in the set characteristic interval, pre-processed operation status data is generated based on the data characteristics.

[0051] It should be noted that various sensors are deployed at key parts of the equipment. For example, temperature sensors can obtain the real-time temperature of each component when the equipment is running, pressure sensors monitor the pressure value in the system, and vibration sensors collect vibration data generated by the operation of the equipment. The sensor converts physical quantities into electrical signals or digital signals, and transmits them to the data acquisition system in real time through wired or wireless transmission. For example, the temperature sensor installed at the bearing of an industrial steam turbine can always feedback the operating temperature of the bearing to prevent failures caused by excessive temperature, and calculate basic statistics of the data, such as the mean, median, and standard deviation. The mean reflects the average level of the data. Taking the temperature data of the equipment operation as an example, the temperature mean within a period of time is calculated to analyze the average operating temperature of the equipment within the set time. The standard deviation reflects the degree of discreteness of the data. The larger the standard deviation, the greater the data fluctuation and the more unstable the equipment operation status. By performing feature analysis on the operation status data, abnormal features can be eliminated, the reflection ability of the operation status data can be improved, and the collected operation status data can be ensured to accurately reflect the operation status of the equipment.

[0052] Among them, generating abnormal operating status data specifically includes: obtaining pre-processed operating status data, setting the time value of the analysis window, dividing the pre-processed operating status data according to the time value of the analysis window to obtain multiple sub-windows; comparing the pre-processed operating status data in each sub-window with the set status data separately to obtain a comparison result; analyzing the time node when the operating status of the equipment is abnormal based on the comparison result; analyzing the sub-window where the time node when the abnormality occurs is located to obtain the abnormal time node; extracting the operating status data in the sub-window corresponding to the abnormal time node and performing a secondary comparison analysis with the set status data to obtain the abnormal operating status data.

[0053] It should be noted that by dividing the collected operating status data into time nodes, multiple analysis windows are established. When analyzing abnormal conditions of equipment, the analysis window where the abnormal condition is located can be quickly located, thereby quickly analyzing the abnormal operating status data and abnormal time nodes of the equipment.

[0054] Specifically, the abnormal operating status data is analyzed based on the knowledge graph to generate a maintenance strategy, which specifically includes: obtaining abnormal operating status data; analyzing the abnormal operating status data based on the knowledge graph to generate problem location and maintenance operation guidance; analyzing the problem location and maintenance operation guidance based on the knowledge graph to generate a maintenance task plan; generating an adaptive maintenance plan based on the maintenance task plan to obtain a maintenance strategy.

[0055] It should be noted that by analyzing abnormal operating status data through knowledge graphs, the abnormal position of equipment can be efficiently located, thereby quickly generating maintenance strategies and improving equipment maintenance efficiency.

[0056] The abnormal operation status data analysis process is as follows. Data collection and preprocessing. Collection: Collect system operation status data through sensors, log files, etc., including real-time operation parameters, equipment status information, etc. Preprocessing: Clean the collected data, remove noise data and outliers, and perform data standardization to ensure data quality. Feature extraction and matching. Feature extraction: Extract key features from the pre-processed abnormal operation status data, such as the degree to which the parameters deviate from the normal range, the frequency of abnormalities, etc. For example, if the normal temperature range of a device is 30℃-50℃ and the current temperature is 65℃, the temperature deviation value is 15℃. Matching: Match the extracted features with entities and relationships in the knowledge graph. For example, based on the abnormal temperature rise feature, find the relevant equipment components, fault types and other information in the knowledge graph.

[0057] Reasoning and problem-solving. Rule-based reasoning: Formulate a series of reasoning rules, such as "If the operating parameters of a certain equipment component exceed the normal range, and other related components also have abnormalities, it may be that the failure of the equipment component triggers a chain reaction." Use the rules to reason in the knowledge graph to further determine the root cause of the problem. Probabilistic reasoning: Combine historical data with information in the knowledge graph to calculate the probability of different fault types. For example, based on past experience, when the temperature rises abnormally and the pressure drops at the same time, the probability of a cooling system failure is 80%, which helps locate the problem. The specific method of generating maintenance operation instructions is as follows.

[0058] Associated maintenance knowledge: Once the problem is located, the maintenance operation knowledge related to the fault type is associated in the knowledge graph. Maintenance operation knowledge includes maintenance steps, required tools, safety precautions, etc. For example, for a "motor short circuit" fault, the maintenance steps may be: disconnect the power supply, disassemble the motor housing, check the windings, replace the damaged windings, and reinstall the motor housing; the required tools include screwdrivers, multimeters, insulating tape, etc.; safety precautions include ensuring that the power supply is completely disconnected during maintenance to avoid electric shock, etc.

[0059] Generate guidance documents: Organize maintenance operation knowledge into maintenance operation guidance documents in a clear and easy-to-understand manner. You can use pictures and text to provide maintenance personnel with detailed operation instructions. For example, insert a schematic diagram of motor disassembly and installation in the document, marking the key points of each step.

[0060] The knowledge graph updating and optimization methods are as follows: Maintenance feedback collection: After the maintenance is completed, feedback information from the maintenance personnel is collected, including the problems encountered during the actual maintenance process, whether the maintenance was successfully completed according to the instructions, and whether new causes of failure were found. Knowledge graph update: The knowledge graph is updated based on maintenance feedback information. If a new cause of failure or a more effective maintenance method is found, it is added to the knowledge graph; if the original knowledge does not match the actual maintenance situation, the relevant knowledge is corrected. For example, if a new cause of failure is found when repairing a certain equipment, the cause of failure is added to the knowledge graph as a new entity, and a relationship with related abnormal phenomena and equipment components is established. Through the above-mentioned abnormal operating status data analysis and guidance generation scheme based on knowledge graph, the efficiency and accuracy of system fault diagnosis and maintenance can be effectively improved, and the stable operation of various complex systems can be ensured.

[0061] Specifically, real-time monitoring of equipment operation status data and real-time transmission of equipment operation status data to the terminal include: The equipment operation status data is obtained, and the operation status data of different types of equipment are stored separately according to the type of equipment.

[0062] Based on the same type of equipment, the operating status data of the equipment at different time nodes is obtained to obtain a sub-data table.

[0063] Integrate the sub-data tables of different types of equipment to obtain a complete data report.

[0064] Transmit complete data reports to the terminal in real time.

[0065] It should be noted that by analyzing the type of equipment, the corresponding type of operating status data can be stored separately according to the type of equipment. When calling the operating status data of the same type of equipment, only the data in the matching sub-data table needs to be analyzed, thereby improving data calling efficiency.

[0066] Specifically, generating abnormal operating status data also includes: obtaining equipment maintenance decision information, including equipment drawings, user manuals, design specifications, status reports, operating events, internal events, work order tasks, maintenance procedures, maintenance plans and papers, and establishing an equipment maintenance information library; based on the common / preset failure modes of the equipment and the corresponding causes of failures, determining equipment fault information and establishing an equipment fault library; obtaining the current operating status information of the equipment, comparing the current operating status information of the equipment with the data in the equipment fault library, and obtaining abnormal operating status data.

[0067] Specifically, the failure modes include mechanical component failure and electrical failure. Mechanical component failure includes natural wear caused by long-term operation. For example, the gears, bearings and other components in the equipment will gradually wear out due to continuous friction on the surface during long-term relative motion. Insufficient lubrication: If the lubrication system of the equipment fails or the amount of lubricating oil is insufficient or the quality is reduced, an effective lubricating film cannot be formed on the surface of the components, which will increase the friction between the components or accelerate the wear.

[0068] In addition, mechanical parts may also suffer from fatigue fracture after long-term operation. Under the action of long-term alternating loads, equipment parts, such as the crankshaft of an engine, will gradually form tiny cracks inside the material. As the cracks expand, they will eventually cause the parts to break.

[0069] Failure analysis of electrical parts Electrical failures, such as component aging, electrical components such as resistors, capacitors, inductors, etc., will gradually change their performance parameters during long-term use, such as increased resistance, reduced capacitance, and changed inductance, which will affect the normal operation of the electrical system. Electromagnetic interference, the presence of strong electromagnetic fields in the surroundings, such as the electromagnetic fields generated by large motors, transformers and other equipment, will interfere with the electrical system, affecting its signal transmission and electrical performance, causing equipment malfunction or performance degradation. Power supply problems, unstable power supply voltage, excessive fluctuations, or increased internal resistance of the power supply may prevent electrical equipment from obtaining normal operating voltage and current, resulting in a decrease in electrical performance.

[0070] Failures also include sensor failures and signal transmission failures. For example, temperature sensors, pressure sensors, position sensors, etc. fail and output incorrect signals, causing the control system to receive incorrect feedback information and issue incorrect control instructions. If the signal transmission cable is interfered with, damaged, or has poor contact, the control signal will be distorted, attenuated, or lost during transmission, affecting the normal operation of the control system.

[0071] The present application obtains equipment historical data based on big data technology, and constructs a knowledge graph based on the equipment historical data; obtains equipment operating status data, preprocesses the equipment operating status data, and obtains preprocessed operating status data; compares the preprocessed operating status data with the set status data to obtain the operating deviation rate; determines whether the operating deviation rate is greater than or equal to the set operating deviation rate threshold; if greater than or equal to, generates abnormal operating status data, analyzes the abnormal operating status data based on the knowledge graph, and generates a maintenance strategy; if less than, monitors the equipment operating status data in real time, and transmits the equipment operating status data to the terminal in real time; automatically diagnoses the cause of equipment failure through the constructed knowledge graph, and gives corresponding solutions to avoid excessive reliance on the personal experience of technicians, improve the accuracy of fault diagnosis, and improve maintenance efficiency.

[0072] In an exemplary embodiment, a computer device is further provided, including a memory and a processor, wherein a computer program is stored in the memory, and the above method is implemented when the processor executes the computer program.

[0073] In an exemplary embodiment, a computer-readable storage medium is provided, storing a computer program, which implements the above method when executed by a processor.

[0074] In an exemplary embodiment, a computer program product is provided, including a computer program, which implements the above method when executed by a processor.

[0075] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.

[0076] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM may be in various forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM).

[0077] The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. The non-relational database may include a distributed database based on blockchain, etc., but is not limited thereto. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., but is not limited thereto.

[0078] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0079] This article uses specific examples to illustrate the principles and implementation methods of this application. The description of the above embodiments is only used to help understand the method and core ideas of this application. At the same time, for those skilled in the art, according to the ideas of this application, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as limiting this application.

Claims

1. A knowledge graph-based equipment maintenance decision-making method, characterized in that: include: Construct a knowledge graph based on the historical data of various types of equipment; the historical data includes historical operating status data and historical maintenance data; The historical operation status data includes real-time parameters of various types of equipment; Preprocess the current operating status data of various equipment and determine the preprocessed operating status data; Determining an operation deviation rate according to the preprocessed operation status data and preset operation status data; Based on the knowledge graph, maintenance strategies for various types of equipment are generated according to the operation deviation rate and a preset operation deviation rate threshold.

2. The equipment maintenance decision-making method based on knowledge graph according to claim 1 is characterized in that: Based on the historical data of various types of equipment, a knowledge graph is constructed, including: Analyze and sort out the historical data of the same type of equipment to determine the matching degree between the historical operation status data and the historical maintenance data of the same type of equipment; The knowledge graph is determined based on the relationship matching degree between the historical operating status data and the historical maintenance data of each type of equipment, and a preset matching degree threshold.

3. The equipment maintenance decision-making method based on knowledge graph according to claim 2 is characterized in that: Analyze and sort out the historical data of the same type of equipment to determine the matching degree between the historical operating status data and the historical maintenance data of the same type of equipment, including: Extract and summarize entities and entity relationships in equipment manuals and historical maintenance data; the entities include equipment components, operating status data, fault types, and maintenance operation data; the entity relationships include the relationship between equipment components and operating status data, the relationship between fault types and operating status data anomalies, and the relationship between fault types and maintenance operation data; Based on the entities and the entity relationships, statistics are collected on abnormal distribution of operating status data corresponding to different fault types and frequencies of different fault types occurring in various types of equipment in different operating time periods; Based on the abnormal distribution of the operating status data and the frequencies of the different fault types, an association relationship between the historical operating status data and the fault type is established, and a matching degree between the historical operating status data and the historical maintenance data of the same type of equipment is calculated.

4. The equipment maintenance decision-making method based on knowledge graph according to claim 1 is characterized in that: Based on the knowledge graph, according to the operation deviation rate and the preset operation deviation rate threshold, a maintenance strategy for each type of equipment is generated, specifically including: Determine whether the operation deviation rate is greater than or equal to a preset operation deviation rate threshold, and determine a first determination result; If the first judgment result is yes, generate abnormal operation status data corresponding to each type of equipment, and analyze the abnormal operation status data based on the knowledge graph to generate maintenance strategies for each type of equipment; If the first judgment result is no, the current operating status data of each type of equipment is monitored in real time, and the current operating status data of each type of equipment is transmitted to the terminal in real time.

5. The equipment maintenance decision-making method based on knowledge graph according to claim 2 is characterized in that: Based on the relationship matching degree between the historical operation status data and the historical maintenance data of various types of equipment, and the preset matching degree threshold, the knowledge graph is determined, specifically including: Determine whether the relationship matching degree is greater than or equal to a preset matching degree threshold, and obtain a second determination result; If the second judgment result is yes, the relationship between the historical operation status data and the maintenance data of the equipment is added to the maintenance manual and the maintenance case to obtain the knowledge graph; If the second judgment result is no, the historical maintenance data is deleted and the maintenance manual or maintenance case is updated; the historical data also includes the maintenance manual and maintenance case.

6. The equipment maintenance decision-making method based on knowledge graph according to claim 1 is characterized in that: Preprocess the current operating status data of various equipment and determine the preprocessed operating status data, including: Extracting data features of current operating status data of the various types of equipment; Normalizing the data features to obtain processed data features; Determine whether the processed data feature is less than or equal to a preset feature interval, and obtain a third determination result; If the third judgment result is yes, eliminating the processed data feature; If the third judgment result is no, the pre-processed operating status data is generated based on the processed data features.

7. The equipment maintenance decision-making method based on knowledge graph according to claim 4 is characterized in that: The abnormal operation status data is analyzed based on the knowledge graph to generate maintenance strategies for various types of equipment, including: Extracting key features of the abnormal operation status data; the key features at least include an offset value when an abnormality occurs in a real-time parameter and a frequency of occurrence of the offset value; Determine, based on the knowledge graph and the key features, the fault types of various types of equipment and the maintenance operation guidance solutions associated with the fault types; The maintenance operation guidance plan is used as the maintenance strategy.

8. A computer device comprising: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the equipment maintenance decision method based on the knowledge graph as described in any one of claims 1 to 7.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the knowledge graph-based equipment maintenance decision method described in any one of claims 1 to 7 is implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the knowledge graph-based equipment maintenance decision method described in any one of claims 1 to 7 is implemented.

Images