Digital operation and maintenance management method and system for crane

Abstract

The invention provides a digital operation and maintenance management method and system for a crane. The method comprises the following steps: acquiring data of the crane in a working state; processing and analyzing the data based on a knowledge graph; based on an analysis result, carrying out resource analysis on the fault and early warning data; automatically generating a work order according to the resource analysis result; fault processing is carried out based on the dispatched work order; after fault processing is completed, fault processing information feedback is carried out, and system updating is carried out based on feedback. The equipment state of the crane can be monitored in real time, whether the crane needs to be maintained or not is evaluated in real time, the corresponding maintenance plan is made, the matched maintenance personnel are determined, and therefore the maintenance management level and the maintenance efficiency of the crane are improved, crane accidents caused by untimely maintenance are avoided, and the production safety is improved.

Description

Technical Field

[0001] The present invention relates to the field of special equipment operation and maintenance, and in particular to a digital operation and maintenance management method and system for cranes. Background Art

[0002] At present, the maintenance of cranes can be divided into preventive maintenance and non-preventive maintenance. Non-preventive maintenance includes post-maintenance, which is only carried out after the crane breaks down. Preventive maintenance includes regular maintenance and situation-based maintenance. Regular maintenance is usually based on the working time of the crane. Repair and maintenance are carried out after the crane has reached a certain working time. Situation-based maintenance usually determines whether maintenance is needed based on the actual operating status of the crane.

[0003] In terms of maintenance management efficiency, condition-based maintenance is the most efficient maintenance method, but the current crane operation status monitoring technology and fault prediction technology have certain problems in prediction accuracy, and relying entirely on condition-based maintenance may lead to accidents. Regular maintenance is widely used in current crane maintenance, but the time interval for regular maintenance of cranes is often determined based on experience, with low inspection efficiency and high labor intensity, which may cause excessive maintenance and unnecessary waste of resources.

[0004] Therefore, it is necessary to provide a comprehensive maintenance management solution that can determine the maintenance plan according to the real-time status of the crane, reduce the safety hazards of the crane and avoid the waste of maintenance resources. Summary of the invention

[0005] In order to overcome the problem that it is difficult to perform maintenance according to the real-time status of the crane, the present application provides a digital operation and maintenance management method and system for the crane.

[0006] To achieve the above objectives, some embodiments of the present application provide a crane digital operation and maintenance management method, comprising the following steps: Step 1. Obtain data when the crane is in working state; Step 2. Process and analyze the data based on the knowledge graph; Step 3. Based on the analysis results, perform resource analysis on the fault and warning data; Step 4. Automatically generate a work order based on the resource analysis results; Step 5. Handle the fault based on the dispatched work order; Step 6: After the fault handling is completed, the fault handling information is fed back and the system is updated based on the feedback.

[0007] Furthermore, the data obtained in step 1 when the crane working status is in operation includes: data collected by a programmable logic controller (PLC), status monitoring data, manually input maintenance data, fault repair records, and crane design data.

[0008] Furthermore, the data processing in step 2 includes data integration, data cleaning and preprocessing; wherein, the data integration is to integrate the data collected by the PLC, the status monitoring data, the manually input maintenance data, the fault repair record and the crane design data on a unified database platform to form a comprehensive data view; the data cleaning is to remove redundant information in the integrated data; and the preprocessing is to process missing values ​​and outliers.

[0009] Furthermore, the analysis of the data in step 2 includes feature engineering, knowledge graph update, state monitoring and anomaly detection, fault prediction and analysis, maintenance resource coordination, decision support and feedback loop and fault handling; wherein, the feature engineering is to extract key features from different data sources and identify important variables that affect operation and maintenance decisions; the knowledge graph update is to use the information in the knowledge graph to associate the relationship between different data; the state monitoring and anomaly detection is to compare the real-time monitoring data with the normal working state in the knowledge graph, use machine learning algorithms to detect anomalies, and identify potential faults; the fault prediction and analysis uses historical data and fault mode analysis in the knowledge graph to predict potential faults using prediction models and formulate maintenance plans in advance; the maintenance resource coordination is based on the data analysis results to optimize the inventory management of spare parts and arrange reasonable maintenance time; the decision support and feedback loop is to generate maintenance suggestions and decision support based on the results of processing and analysis, and feedback to the operation and maintenance personnel to optimize the maintenance strategy; the fault handling is to quickly locate the cause of the fault through data analysis when a fault occurs, and use the solutions and maintenance records provided by the knowledge graph to formulate response strategies for fault handling; The method of using a machine learning algorithm to detect anomalies and identify potential faults further includes: training a prediction model using an XGBoost algorithm based on data collected by the PLC on the crane and status monitoring data monitored by sensors. The algorithm flow is as follows: S1: Initialize the predicted value of each sample; S2: Define a specific loss function; S3: Calculate the derivative of the loss function for each of the sample prediction values; S4: Build a new decision tree based on the derivative information; S5: using the new decision tree to predict sample values ​​and adding them to the original values; S6: creating a decision tree in a loop until the loss function satisfies a condition; For the sensor signal value, the historical operation data is processed and used for model training; the trained model uses PLC data as input, finds the relationship between PLC data and sensor signal value based on historical data, predicts the signal data of the specified sensor, and then calculates the predicted value with the data value collected by the sensor in actual work, using the time series residual as the judgment standard, and issues an alarm if an abnormality continues to occur within a certain time series.

[0010] Furthermore, in step 4, after the resource analysis, there are two cases: one is that the relevant spare parts of the spare parts management system or the relevant resources of the equipment management system need to be connected, and then a work order is generated; the other is that the work order is directly generated without connecting to the relevant resources; The spare parts management system is used to provide logistical support for work order processing by importing the existing spare parts quantity through management personnel; The equipment management system includes equipment ledger entry, maintenance strategy, repair strategy and fault tree; the equipment management system establishes a crane equipment ledger to record equipment information; formulates maintenance strategies based on equipment usage and operating condition data, including preventive maintenance and planned maintenance, to ensure stable operation of the equipment; when encountering a fault, adopts a repair strategy to efficiently complete the repair process by generating a repair work order, allocating resources and tracking the repair progress; at the same time, the equipment management system uses fault tree analysis to decompose the fault by level, find out the possible causes, and accurately locate the root cause of the fault.

[0011] Furthermore, the step 4 automatically generates work orders including work orders with spare parts requirements, work orders with resource requirements, and work orders without relevant resources according to the resource analysis results; The step of generating the work order with spare parts requirement includes the following steps: S1. Spare parts confirmation: When a work order is generated, the system automatically identifies and verifies the inventory of the required spare parts to ensure that there are sufficient spare parts; S2. Generate work orders and assign tasks: When it is confirmed that the spare parts inventory meets the demand, the system generates a work order and assigns it to the maintenance team, marking the model, quantity and location information of the required spare parts; S3. Spare parts reservation and notification: The system reserves the required spare parts when generating a work order, and notifies the warehouse and operation and maintenance personnel to prepare them to avoid the lack of the spare parts during maintenance; Generating the work order with resource requirements includes the following steps: A1. Resource confirmation: The system automatically checks the availability of required resources and adjusts the task time if there is a conflict; A2. Generate work orders and allocate resources: After confirming that resources are available, the system generates a work order and specifies the required equipment, Maintenance site and operator information, notifying maintenance personnel to prepare resources; A3. Task reminders and resource coordination: The system automatically pushes task reminders and coordinates resources to ensure that maintenance work is completed on time within the planned time; Generating the work order that does not require related resources includes the following steps: B1. Directly generate work orders: Without the need for spare parts and resources, the system simplifies the process and directly generates work orders; B2. Work order assignment and feedback: Tasks will be directly assigned to the responsible personnel or maintenance team, and the system status will be updated after the task is completed.

[0012] Furthermore, the step 6 further includes: after the fault processing is completed, analyzing the fault data, feeding back the fault processing information to the spare parts management system, the equipment management system and the knowledge management module respectively, and the spare parts management system, the equipment management system and the knowledge management module perform system updates according to the fed-back information; The fault handling information is fed back to the spare parts management system and the system is updated, including: when spare parts are used in the fault handling process, the system automatically updates the spare parts inventory information and records the spare parts consumption. The system evaluates the replacement cycle and usage trend of spare parts according to the consumption and maintenance frequency, and adjusts the inventory plan; The fault handling information is fed back to the equipment management system and the system is updated, including: the equipment management system updates the equipment operation status and maintenance records after the fault is repaired, including the maintenance time, maintenance content, replacement parts and related test data; the equipment management system records and updates the maintenance cycle, performance status and historical faults of the equipment to form an equipment status file for subsequent status evaluation and adjustment of preventive maintenance strategies; The fault handling information is fed back to the knowledge management module and the module is updated, including: the fault handling data and analysis results are transmitted to the knowledge management module as experience cases to form a maintenance knowledge base; the knowledge management module collects typical fault handling processes, root cause analysis and optimal handling methods for maintenance guidance.

[0013] Furthermore, the knowledge management module performs systematic management based on data, and the specific management content includes the following aspects: ①. The knowledge management module receives and manages the following key data: Fault handling data: including the cause of each fault, handling steps, time consumption, spare parts used and effect evaluation, forming a detailed fault handling record; Equipment maintenance records: covering regular maintenance, inspection data, maintenance effects, key parameter adjustments of equipment, forming a maintenance file for the equipment life cycle; Experience summary and analysis data: including maintenance experience, fault trend analysis, and best practices; Spare parts usage information: tracking spare parts consumption, replacement cycle, life data and actual effects; Environmental and working condition data: equipment working environment, load conditions and external conditions, as external variables for fault and life analysis; ②. The knowledge management module manages the above data as follows: 1) Fault case management: Collect specific records of fault handling, including fault description, handling method, spare parts used, root cause analysis, and repair time, to form a standardized fault case library, and manage different types of faults through classification and labeling; 2) Experience knowledge management: The system stores experience data in the knowledge base and extracts standardized operating procedures applicable to common failures and maintenance scenarios. By analyzing the commonalities and trends of multiple failures, it extracts best practices and optimization suggestions to optimize maintenance processes and decisions. 3) Spare parts usage and replacement strategy management: record the actual usage of spare parts, the effect after fault repair, the frequency of spare parts consumption and the replacement cycle, and form a reference for the service life of spare parts and the best replacement time; and based on the spare parts consumption trend, the knowledge management module adjusts the inventory to improve the accuracy of the spare parts supply plan; 4) Maintenance strategy optimization management: The system dynamically adjusts the maintenance strategy and optimizes the maintenance cycle and content based on the historical maintenance data and failure frequency of the equipment; manages the historical data of the maintenance plan to analyze the past maintenance effects and failure reduction, and improves the maintenance process of the equipment; 5) Skill training and knowledge sharing: Collect and analyze typical cases of fault handling, create maintenance flowcharts and skill manuals; use visualization tools to display best practices for different faults and maintenance for knowledge sharing.

[0014] Furthermore, a knowledge graph is constructed based on the knowledge management module, and the specific construction process is as follows: S1. Knowledge acquisition and ontology model construction: ① Knowledge acquisition: Extract knowledge from various data sources related to crane fault diagnosis, including fault type, fault handling method, maintenance experience of professionals, and equipment technical manuals. The knowledge provides detailed background and handling measures for various crane faults; ② Ontology model construction: construct the crane fault diagnosis ontology model and define the core concepts and relationships in the graph; ③Graph data storage: convert the ontology model into structured graph data and store it in the database of the knowledge graph to support subsequent fault diagnosis reasoning and knowledge retrieval; S2. Preliminary construction and visualization of the map: ① Relationship entity mapping: From the collected knowledge and data, fault cases, diagnostic processes, and equipment components are mapped to nodes and relationships in the knowledge graph; ② Hierarchical relationship construction: hierarchical relationships are established in the knowledge graph according to the fault type, so that the fault nodes at different levels reflect the correlation between the fault symptoms and the root causes, and from the treatment methods to the spare parts requirements; ③ Visualization display: Generate a visualization view of the knowledge graph to clearly present the core nodes and important relationships; S3. Knowledge graph update mechanism: ① Trend change determination and knowledge graph update: Operation and maintenance personnel analyze the causes of fault trend changes based on the equipment's operating trends and diagnostic data, and add the diagnostic results to the knowledge graph; by recording the cause analysis and treatment methods, the knowledge graph's ability to identify and respond to trend faults is improved; ② Manual judgment and trend update: In the early stage, operation and maintenance experts manually judge trend changes and update the nodes or relationships of the knowledge graph; ③ Manual and algorithmic updates: In the later stage, expert judgment is combined with diagnostic algorithms for updates. When the algorithm identifies abnormal trends, the knowledge graph is automatically updated, and nodes and relationships are improved after manual confirmation, gradually reducing manual participation; S4. Recording and processing of diagnostic algorithm output information: ① Information flow reception and storage: The knowledge graph framework receives the key fault information flow output by the diagnosis algorithm, including detected anomalies, predicted fault types and possible causes; ② Graph update of important information: Map the key information output by the algorithm to the graph nodes. If a new fault mode or new processing method is detected, add or modify nodes and relationships in the graph to improve the fault diagnosis content of the graph; ③ Automatic update of anomalies: When the algorithm identifies a new abnormal pattern, the system will automatically generate a corresponding abnormal node in the graph and establish associations with related equipment and fault types; S5. Knowledge graph training and self-learning: ① Automatic graph training: The updated graph data is used to train and optimize the fault diagnosis model to form a closed loop; the diagnosis algorithm will improve the recognition rate of new fault types based on the structured data of the graph; ② Self-learning mechanism: Through the fault handling cases and experience data continuously accumulated by the graph, the diagnostic algorithm gradually achieves self-learning, which can more quickly identify new faults and adjust maintenance strategies; ③ Manual supervision and feedback: The self-learning process of the graph still requires manual supervision, and the automatically updated content of the graph must be checked regularly to ensure the diagnostic accuracy of the model; S6. Continuous optimization and application of knowledge graph: ① Fault prediction and reasoning: Through the retrieval and reasoning of knowledge graphs, the system can predict potential faults, assist operation and maintenance personnel in early troubleshooting, and automatically recommend treatment methods based on historical data; ② Intelligent operation and maintenance decision support: The knowledge graph integrates the fault information and working condition data of all crane equipment, supports the operation and maintenance team to make quick decisions, and improves the efficiency of fault handling; ③Model visualization optimization: Through the continuous optimization of the visualization map, complex relationships can be visualized, which will help further operation and maintenance personnel training and knowledge sharing.

[0015] On the other hand, the present application also provides a digital operation and maintenance management system for a crane, which includes a memory for storing computer program instructions and a processor for executing program instructions, wherein when the computer program instructions are executed by the processor, the system is triggered to execute the above method. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 This is a flow chart of the digital operation and maintenance management method for cranes of the present invention. DETAILED DESCRIPTION

[0017] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. 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 those skilled in the art without creative work are within the scope of protection of the present invention.

[0018] The embodiments of the present invention are described in detail below with reference to the accompanying drawings.

[0019] Here, the digital operation and maintenance management method of the crane of the embodiment of the present application is suitable for the scenario of real-time maintenance and inspection of the crane.

[0020] In this scenario, the crane may have real-time failures during operation, reducing the service life of the crane's structure, spare parts, consumables, etc. These situations require timely maintenance of the crane. The maintenance can include immediate repair of real-time failures, as well as maintenance and regular maintenance based on the situation, such as replacement of consumables that are about to expire, or overall inspection and maintenance of a crane component.

[0021] However, both situational maintenance and regular maintenance have the problem of failing to respond to the maintenance needs of the crane in a timely manner, making it difficult to control the potential accidents of the crane and also difficult to improve the maintenance efficiency of the crane.

[0022] The digital operation and maintenance management method for cranes provided in the embodiment of the present application can perform status warning and fault diagnosis on the crane based on the real-time operating data and status monitoring data of the crane, and determine the maintenance plan and matching maintenance personnel of the crane based on the diagnosis results. It can also perform real-time evaluation on whether the crane needs maintenance, formulate a corresponding maintenance plan and determine matching maintenance personnel, thereby improving the maintenance management level and maintenance efficiency of the crane and avoiding crane accidents caused by untimely maintenance.

[0023] It is understandable that equipment status warning and fault diagnosis require the support of an intelligent digital operation and maintenance system. The digital operation and maintenance management method and system for cranes provided in the embodiments of the present application, based on the analysis of the characteristics and problems of traditional operation and maintenance work, combines the advanced technology of the industrial Internet to realize the digital operation and maintenance management of lifting equipment. The operation and maintenance management system is based on a database platform. The system has functional modules such as centralized equipment control, personalized equipment operation and maintenance, intelligent diagnosis, and equipment operation and maintenance work order circulation, so as to realize the online circulation of the operation and maintenance management of lifting equipment. It can improve the perception, monitoring, early warning, disposal and evaluation capabilities of safe production of lifting equipment, thereby improving the safety of shipyard production.

[0024] Some embodiments of the present application provide a crane digital operation and maintenance management method, such as Figure 1 As shown, the following steps are included: Step 1. Obtain data when the crane is in working state.

[0025] In some embodiments, the crane-related data is collected by: (1) The data collected by the programmable logic controller (PLC) include: the weight of the lifting mechanism, lifting height, lifting speed, trolley running speed, trolley running distance, trolley running speed, trolley running distance, etc.

[0026] (2) Condition monitoring data: Condition monitoring data is obtained by installing sensors at key locations such as important structural parts and key components. For example, vibration sensors are installed at key locations of the lifting mechanism to collect vibration monitoring data, and strain sensors are installed at key locations of the main beam to collect strain monitoring data.

[0027] (3) Manually input maintenance data: Equipment management personnel prepare various implementation plans, implementation contents and standards according to requirements, and formulate maintenance task plans such as point inspection, level 1 and 2 maintenance, overhaul / item repair, and periodic inspection through plan management. These plans are pushed to production operators or equipment maintenance personnel according to the settings. After the relevant personnel complete the implementation, they will provide closed-loop manual feedback information after maintenance.

[0028] (4) Fault repair record: The production operator creates a repair work order in the system according to the fault situation. The equipment management personnel dispatches the order according to the repair situation. The equipment maintenance personnel carry out repairs after receiving the order. After the repair is completed, the production operator provides feedback on the repair situation in the system.

[0029] (5) Crane design data: including crane design drawings, spare parts information, etc.

[0030] Step 2. Based on the knowledge graph, the acquired crane data is processed and analyzed.

[0031] Based on the knowledge graph, the obtained data related to the crane in the working state is processed and analyzed. In some embodiments, the process of processing the data is as follows: (1) Data integration: Integrate crane operating data, condition monitoring data, maintenance records, manual feedback information, design data, and spare parts information on a unified database platform to form a comprehensive data view.

[0032] (2) Data cleaning and preprocessing: Remove redundant information from the integrated data and handle missing values ​​and outliers to ensure data quality and prepare for analysis.

[0033] The processed data is analyzed, and illustratively, the analysis includes the following steps: (1) Feature engineering: Extract key features from different data sources to identify important variables that affect operation and maintenance decisions, such as usage frequency and fault type.

[0034] (2) Knowledge graph update: Use the information in the knowledge graph to associate the relationships between different data, such as the relationship between faults and maintenance records, thereby enhancing the intelligence of the analysis.

[0035] (3) Condition monitoring and anomaly detection: Compare real-time monitoring data with the normal working status in the knowledge graph, use machine learning algorithms to perform anomaly detection, and identify potential faults.

[0036] (4) Fault prediction and analysis: Through the analysis of fault patterns in historical data and knowledge graphs, the prediction model is used to predict potential faults and make maintenance plans in advance.

[0037] (5) Coordination of maintenance resources: Based on data analysis results, optimize the inventory management of spare parts to ensure that necessary maintenance resources are available at any time, arrange reasonable maintenance time, and avoid equipment downtime.

[0038] (6) Decision support and feedback loop: Based on the results of processing and analysis, maintenance recommendations and decision support are generated and fed back to operation and maintenance personnel to promote the optimization of maintenance strategies.

[0039] (7) Fault handling process: When a fault occurs, quickly locate the cause of the fault through data analysis, use the solutions and maintenance records provided by the knowledge graph, formulate response strategies, and coordinate resources from all parties to handle the problem.

[0040] In some embodiments, the state monitoring and anomaly detection in (3) is as follows: real-time monitoring data is compared with the normal working state in the knowledge graph, and anomaly detection is performed using a machine learning algorithm to identify potential faults.

[0041] Among them, the machine learning algorithm is to train the prediction model through the XGBoost algorithm based on the data collected by the PLC on the crane and the status monitoring data monitored by sensors. The XGBoost algorithm is a machine learning algorithm that is widely used in big data processing, and its full name is eXtreme Gradient Boosting. The biggest feature of XGBoost is that it can automatically use the multi-threading of the CPU for parallelism, and at the same time improve the algorithm to improve the accuracy. XGBoost performs a second-order Taylor expansion on the loss function, and adds a regularization term to the loss function to find the optimal solution as a whole, in order to weigh the decrease of the loss function and the complexity of the model to avoid overfitting. The XGBoost algorithm uses a second-order Taylor expansion to approximate the objective function, so that it can perform leaf splitting optimization based only on the value of the input data, which improves the scalability and freedom, and can construct a corresponding error function according to the specific application scenario to train a specific tree model.

[0042] The algorithm flow of XGBoost is as follows: S1: Initialize the predicted value of each sample; S2: Define a specific loss function; S3: Calculate the derivative of the loss function for each sample prediction value; S4: Build a new decision tree based on the derivative information; S5: Use the new decision tree to predict the sample value and add it to the original value; S6: Loop to create decision trees until the loss function meets the conditions.

[0043] For sensor signals, the historical operation data is processed and used for model training. The trained model uses PLC data as input, finds the relationship between PLC data and sensor signal values ​​based on historical data, predicts the signal data of the specified sensor, and then calculates its predicted value with the data value collected by the sensor in actual work. The time series residual is used as the judgment standard, and an alarm is issued if an abnormality continues to occur within a certain time series. This alarm signal reflects the difference between the current equipment condition of the crane and the equipment condition when it is healthy.

[0044] Step 3. Based on the analysis results, the operation and maintenance center conducts resource analysis on the fault and warning data.

[0045] After processing and analyzing the relevant data of the crane, based on the analysis results, resource analysis is performed on the fault and warning data in the operation and maintenance center, wherein the resource analysis method is a commonly used analysis method in the prior art and is not limited in this embodiment.

[0046] Step 4. Automatically generate a work order based on the resource analysis results.

[0047] After resource analysis, there are two situations: one is that it is necessary to connect to the relevant spare parts of the spare parts management system or the relevant resources of the equipment management system, and then generate a work order; the other is to directly generate a work order without connecting to the relevant resources.

[0048] In some embodiments, the spare parts management system provides logistical support for work order processing by having management personnel import the existing spare parts quantity; at the same time, in the spare parts overview, grassroots management personnel and work order processing personnel can grasp the inventory status of spare parts in real time and rationally allocate relevant resources; as needed, it can be connected to the customer procurement management system to achieve efficient management of front-end procurement of spare parts, back-end repair, use, and maintenance.

[0049] In some embodiments, the equipment management system includes equipment ledger entry, maintenance strategy, repair strategy, fault tree and other contents. First, the system establishes a crane equipment ledger to record equipment information; then, the equipment management system formulates a maintenance strategy based on the equipment usage and working condition data, including preventive maintenance and planned maintenance, to ensure stable operation of the equipment. When a fault occurs, the system adopts a maintenance strategy to efficiently complete the maintenance process by generating a maintenance work order, allocating resources and tracking the progress of the repair. At the same time, the system introduces fault tree analysis to decompose the fault by level and find out the possible causes so as to locate the root cause of the fault more accurately. The system regularly updates the ledger and maintenance records, optimizes the maintenance and repair strategies by analyzing the historical data of the equipment, and realizes the management of the entire life cycle of the equipment.

[0050] The operation and maintenance management system integrates the spare parts management function with the equipment management and operation and maintenance management functions. Through real-time data collection and intelligent analysis, it automatically identifies the inventory status and usage of spare parts, generates replenishment needs in a timely manner, predicts the service life of spare parts based on equipment operation conditions and maintenance history data, and issues early warnings, thus forming full-process tracking and closed-loop control of spare parts replacement, analysis, early warning, collection, repurchase, and repair.

[0051] Exemplarily, the spare parts management system is connected to the ERP system to obtain spare parts for the equipment. The ERP system contains detailed information about the equipment, such as model, spare parts requirements, and maintenance cycle, which are provided to the spare parts management system for planning and procurement. The spare parts management system regularly obtains the working status and spare parts requirements of the equipment from ERP, and adjusts and replenishes the spare parts inventory based on historical maintenance data, equipment failure cycles, usage frequency, etc., to ensure that the spare parts supply meets the demand.

[0052] For example, if the ERP system indicates that the replacement cycle of a crane wire rope is 1,000 hours, the spare parts management system will purchase sufficient wire rope in advance to reduce waiting time in the event of a sudden failure.

[0053] For example, when the equipment management system needs resources, it coordinates the maintenance resource library to provide resources. Among them, resources refer to the man-hours, maintenance personnel, testing equipment, maintenance sites, etc. used for maintenance. The equipment management system updates the maintenance strategy according to the status of the equipment and allocates corresponding resources. When the equipment fails or is planned for maintenance, the equipment management system will retrieve the spare parts inventory to confirm whether the required spare parts are available, and coordinate maintenance personnel and tools and other resources to ensure smooth maintenance.

[0054] For example, if abnormal wear of the crane hook is detected, the equipment management system will arrange maintenance personnel, retrieve hook spare parts, and coordinate the maintenance site and time to ensure that the hook is replaced quickly.

[0055] It is understood that equipment refers to complete devices such as cranes that perform their main functions. Spare parts are replaceable parts prepared for maintenance and fault repair, such as crane wire ropes, hooks, winch brake pads, motors, etc. Spare parts are usually equipment components used to restore the normal operation of the equipment. For example, in a gantry crane, the motor as a key component is a spare part, while the entire crane is considered equipment.

[0056] Through this collaboration, spare parts supply and maintenance resources are guaranteed, cranes can operate efficiently and downtime caused by insufficient spare parts or insufficient resource allocation is reduced.

[0057] When the system automatically generates work orders based on planned maintenance, manual inspection feedback results, and intelligent diagnosis results, the system will automatically analyze and determine the resources required by the work order based on the required resource conditions. The following is the specific process for generating work orders based on the above resource conditions: (1) Work orders with spare parts requirements ① Spare parts confirmation: When a work order is generated, the system automatically identifies and verifies the inventory status of the required spare parts to ensure that there are sufficient spare parts.

[0058] ② Generate work orders and assign tasks: When it is confirmed that the spare parts inventory meets the demand, the system generates a work order and assigns it to the maintenance team, marking detailed information such as the model, quantity and location of the required spare parts.

[0059] ③ Spare parts reservation and notification: The system reserves the required spare parts when generating a work order, and notifies the warehousing and operation and maintenance personnel to prepare them to avoid out-of-stock situations during maintenance.

[0060] For example, for the repair of worn wire ropes, the system generates a work order and confirms the inventory of wire rope spare parts, and waits for the inspection results of the maintenance personnel to complete the spare parts delivery, ensuring that the maintenance personnel can replace the spare parts in time. After the maintenance personnel completes the replacement, the maintenance results are uploaded to the system to complete the maintenance closed loop.

[0061] (2) Work orders with resource requirements ① Resource confirmation: If specific testing tools, sites, technicians and other resources are required, the system will automatically check the availability of resources and adjust the task time if there is a conflict.

[0062] ② Generate work orders and allocate resources: After confirming that resources are available, the system generates a work order and specifies the required equipment, maintenance site, and operator information, and notifies maintenance personnel to prepare resources.

[0063] ③Task reminders and resource coordination: The system automatically pushes task reminders and coordinates resources to ensure that maintenance work is completed on time at the planned time.

[0064] For example, for motor inspections that require special testing equipment, the system arranges the time for the required instruments and technicians when generating a work order, ensuring that the motor inspection is completed in a suitable environment and time, improving troubleshooting efficiency and reducing waiting time in the event of sudden failures.

[0065] (3) Work orders that do not require related resources ① Directly generate work orders: Without the need for spare parts and resources, the system simplifies the process and directly generates work orders.

[0066] ② Work order assignment and feedback: The task will be directly assigned to the responsible personnel or maintenance team, and the system status will be updated after the task is completed.

[0067] For example, for simple routine inspections such as lubrication maintenance, the system generates a work order and directly assigns it to the relevant personnel without the need to prepare other resources in advance.

[0068] The three work order generation methods simplify the operation process, improve resource utilization efficiency, and enable the operation and maintenance guarantee system to intelligently and dynamically manage and schedule tasks based on resource conditions, thereby reducing maintenance downtime and optimizing spare parts and resource management.

[0069] Step 5. Perform troubleshooting based on the dispatched work order.

[0070] In the actual application process, the conclusions of fault diagnosis and early warning are connected with operation and maintenance work to ensure the timeliness of exception handling and realize the logical closed loop of intelligent operation and maintenance work. When the fault diagnosis algorithm infers an abnormality, the abnormal content needs to be sent to the "Message Center" module, and a repair work order is automatically generated to remind maintenance personnel to check the abnormality and troubleshoot the fault. The message and the repair are associated with a unified work order number. After the abnormality is eliminated, the system will complete the reset action of the alarm message based on the feedback results, and complete the refresh of spare parts information, equipment and maintenance information, and dynamic update and knowledge accumulation of relevant information in knowledge management based on the collected feedback information.

[0071] Step 6: After the fault handling is completed, the fault handling information is fed back and the system is updated based on the feedback.

[0072] After the fault handling is completed, the fault data is analyzed and the fault handling information is fed back to the spare parts management system, equipment management system and knowledge management module respectively. The above three system modules perform system updates based on the feedback information. The following are three system update situations.

[0073] (1) Fault handling information is fed back to the spare parts management system and the system is updated.

[0074] When spare parts are used during troubleshooting, the system automatically updates spare parts inventory information and records spare parts consumption. Based on consumption and maintenance frequency, the system evaluates spare parts replacement cycles and usage trends, adjusts inventory plans, and ensures adequate supply of commonly used spare parts.

[0075] Example: After replacing the brake friction pad of a crane, the system deducts one piece from the friction pad inventory and generates a demand reminder.

[0076] (2) Fault handling information is fed back to the equipment management system and the system is updated.

[0077] The equipment management system updates the equipment operation status and maintenance records after the fault is repaired, including the repair time, repair content, replacement parts and related test data, etc. The system records and updates the equipment's maintenance cycle, performance status and historical faults to form an equipment status file for subsequent status evaluation and adjustment of preventive maintenance strategies.

[0078] Example: If the hook is replaced after a fault is fixed, the equipment management system will record the hook replacement time and extend the next planned maintenance cycle.

[0079] (3) Fault handling information is fed back to the knowledge management module and the module is updated.

[0080] Fault handling data and analysis results are transmitted to the knowledge management module as experience cases to form a maintenance knowledge base. The knowledge management module collects typical fault handling processes, root cause analysis and optimal handling methods for future maintenance guidance and shortens fault repair time.

[0081] For example, for a certain type of fault that frequently occurs in the rope-laying mechanism, the system records the fault handling steps, spare parts used, and root cause analysis, and incorporates this information into the knowledge base for reference next time the same fault occurs.

[0082] This multi-level feedback mechanism ensures the dynamic update of spare parts and equipment information and the accumulation of knowledge, which helps to improve the overall efficiency and preventive maintenance capabilities of the operation and maintenance support system.

[0083] In some of these embodiments, the knowledge management module performs systematic management based on the transmitted fault handling data, equipment maintenance records and experience analysis data, aiming to accumulate, optimize and apply knowledge to improve the efficiency and accuracy of equipment operation and maintenance. The specific management content includes the following aspects: (1) The knowledge management module receives and manages the following key data: Fault handling data: including the cause of each fault, handling steps, time consumption, spare parts used and effect evaluation, forming a detailed fault handling record.

[0084] Equipment maintenance records: covering regular maintenance, inspection data, maintenance results, key parameter adjustments, etc., forming a maintenance file for the equipment life cycle.

[0085] Experience summary and analysis data: Contains maintenance experience, failure trend analysis, and best practices obtained from the operation and maintenance team.

[0086] Spare parts usage information: Track spare parts consumption, replacement cycles, life data and actual results to provide a basis for inventory planning.

[0087] Environmental and operating data: Equipment operating environment, load conditions, and external conditions (such as temperature and humidity) as external variables for failure and life analysis.

[0088] (2) The knowledge management module manages the above data in the following ways: 1) Fault case management Collect specific records of each fault handling, including fault description, handling method, spare parts used, root cause analysis and maintenance time, to form a standardized fault case library. Manage different types of faults through classification and labeling to provide direct reference for similar problems in the future.

[0089] Example: A failure case involving wear of the transmission pulley of a crane's rope-arranging mechanism is classified into the "pulley wear problem" category, with processing steps and precautions marked.

[0090] 2) Experience knowledge management The system stores the experience data summarized by operation and maintenance personnel (such as special processing methods, improvement suggestions, etc.) in the knowledge base, and extracts standardized operating procedures applicable to common failures and maintenance scenarios. By analyzing the commonalities and trends of multiple failures, the system extracts best practices and optimization suggestions to optimize future maintenance processes and decisions.

[0091] Example: If a certain failure occurs repeatedly, the knowledge management system provides preventive measures based on empirical data, such as the frequency of replacing spare parts or strengthening the regular inspection of a certain part.

[0092] 3) Spare parts usage and replacement strategy management Record the actual usage of each type of spare parts, the effect after fault repair, the frequency of spare parts consumption and the replacement cycle, and form a reference for the "service life" and "optimal replacement time" of spare parts. Based on the spare parts consumption trend, the knowledge management module can adjust inventory recommendations to improve the accuracy of spare parts supply plans.

[0093] For example: If a certain type of bearing failure occurs frequently and has a significant impact, the knowledge base will recommend increasing the inventory of that spare part or shortening the replacement cycle.

[0094] 4) Optimization and management of maintenance strategies The system dynamically adjusts the maintenance strategy and optimizes the maintenance cycle and content based on the transmitted historical maintenance data and failure frequency of the equipment. It manages the historical data of the maintenance plan and improves the equipment maintenance process by analyzing the past maintenance effects and failure reduction.

[0095] Example: The system analyzes historical data through the knowledge management module and finds that the lubrication cycle of the lifting mechanism should be shortened to improve equipment reliability.

[0096] 5) Skills training and knowledge sharing Collect and analyze typical cases of fault handling, create maintenance flowcharts and skill manuals, and provide rapid training for new employees. Use visualization tools to display best practices for different faults and maintenance, support knowledge sharing among team members, and improve overall operation and maintenance skills.

[0097] Example: A new maintenance engineer can use the knowledge base to view the repair manual for a crane component failure, reducing learning time and standardizing operations.

[0098] Knowledge management helps build a systematic knowledge network, making equipment operation and maintenance management more efficient and professional, while also improving the ability to diagnose and predict equipment faults.

[0099] In some embodiments, the role of the knowledge graph for the knowledge management module is to visualize the association relationship between data and improve the intelligence of operation and maintenance management through dynamic updates. The knowledge graph is constructed based on the knowledge management module, and the specific construction process is as follows: S1. Knowledge acquisition and ontology model construction: ① Knowledge acquisition: Extract knowledge from various data sources related to crane fault diagnosis, including fault type, fault handling method, maintenance experience of professionals, and equipment technical manuals. The knowledge provides detailed background and handling measures for various crane faults; ② Ontology model construction: Construct the gantry crane fault diagnosis ontology model and define the core concepts and relationships in the graph; ③Graph data storage: convert the ontology model into structured graph data and store it in the database of the knowledge graph to support subsequent fault diagnosis reasoning and knowledge retrieval; S2. Preliminary construction and visualization of the map: ① Relationship entity mapping: From the collected knowledge and data, fault cases, diagnostic processes, and equipment components are mapped to nodes and relationships in the knowledge graph; ② Hierarchical relationship construction: hierarchical relationships are established in the knowledge graph according to the fault type, so that the fault nodes at different levels reflect the correlation between the fault symptoms and the root causes, and from the treatment methods to the spare parts requirements; ③ Visualization display: Generate a visualization view of the knowledge graph to clearly present the core nodes and important relationships; S3. Knowledge graph update mechanism: ① Trend change determination and knowledge graph update: Operation and maintenance personnel analyze the causes of fault trend changes based on the equipment's operating trends and diagnostic data, and add the diagnostic results to the knowledge graph; by recording the cause analysis and treatment methods, the knowledge graph's ability to identify and respond to trend faults is improved; ② Manual judgment and trend update: In the early stage, operation and maintenance experts manually judge trend changes and update the nodes or relationships of the knowledge graph; ③ Manual and algorithmic updates: In the later stage, expert judgment is combined with diagnostic algorithms for updates. When the algorithm identifies abnormal trends, the knowledge graph is automatically updated, and nodes and relationships are improved after manual confirmation, gradually reducing manual participation; S4. Recording and processing of diagnostic algorithm output information: ① Information flow reception and storage: The knowledge graph framework receives the key fault information flow output by the diagnosis algorithm, including detected anomalies, predicted fault types and possible causes; ② Graph update of important information: Map the key information output by the algorithm to the graph nodes. If a new fault mode or new processing method is detected, add or modify nodes and relationships in the graph to improve the fault diagnosis content of the graph; ③ Automatic update of anomalies: When the algorithm identifies a new abnormal pattern, the system will automatically generate a corresponding abnormal node in the graph and establish associations with related equipment and fault types; S5. Knowledge graph training and self-learning: ① Automatic graph training: The updated graph data is used to train and optimize the fault diagnosis model to form a closed loop; the diagnosis algorithm will improve the recognition rate of new fault types based on the structured data of the graph; ② Self-learning mechanism: Through the fault handling cases and experience data continuously accumulated by the graph, the diagnostic algorithm gradually achieves self-learning, which can more quickly identify new faults and adjust maintenance strategies; ③ Manual supervision and feedback: The self-learning process of the graph still requires manual supervision, and the automatically updated content of the graph must be checked regularly to ensure the diagnostic accuracy of the model; S6. Continuous optimization and application of knowledge graph: ① Fault prediction and reasoning: Through the retrieval and reasoning of knowledge graphs, the system can predict potential faults, assist operation and maintenance personnel in early troubleshooting, and automatically recommend treatment methods based on historical data; ② Intelligent operation and maintenance decision support: The knowledge graph integrates the fault information and working condition data of all crane equipment, supports the operation and maintenance team to make quick decisions, and improves the efficiency of fault handling; ③Model visualization optimization: Through the continuous optimization of the visualization map, complex relationships can be visualized, which will help further operation and maintenance personnel training and knowledge sharing.

[0100] It can be understood that as new fault data and maintenance records are input, the knowledge graph will update the fault mode and form a fault association path, which will help identify the potential root causes of similar faults. The knowledge graph analyzes the historical data of equipment and spare parts, automatically optimizes the replacement cycle, and marks the spare parts nodes with higher frequency of use, providing data support for spare parts inventory and equipment maintenance decisions. When new equipment failure cases and processing procedures are added to the system, the associations in the graph are automatically updated to identify the equipment's unique failure modes and optimal processing methods, making operation and maintenance decisions more accurate. Through the continuous updating of the knowledge graph, the crane operation and maintenance guarantee system can continuously accumulate operation and maintenance experience, improve fault identification and processing efficiency, and enhance the system's ability to predict potential risks.

[0101] Some embodiments of the present application also provide a digital operation and maintenance management system for a crane, which includes a memory for storing computer program instructions and a processor for executing the program instructions, wherein when the computer program instructions are executed by the processor, the system is triggered to execute the aforementioned digital operation and maintenance management method for the crane.

[0102] To sum up, the solution provided in this application performs status warning and fault diagnosis on the crane based on the real-time operating data and status monitoring data of the crane, and determines the maintenance plan and matching maintenance personnel of the crane based on the diagnosis results. It can conduct real-time evaluation on whether the crane needs maintenance, formulate corresponding maintenance plans and determine matching maintenance personnel, thereby improving the maintenance management level and maintenance efficiency of the crane, avoiding crane accidents caused by untimely maintenance, and thus improving the safety of shipyard production.

[0103] It should be noted that the present application can be implemented in software and / or a combination of software and hardware, for example, can be implemented by using an application specific integrated circuit (ASIC), a general purpose computer or any other similar hardware device. In one embodiment, the software program of the present application can be executed by a processor to realize the steps or functions described above. Similarly, the software program of the present application (including relevant data structures) can be stored in a computer-readable recording medium, for example, a RAM memory, a magnetic or optical drive or a floppy disk and similar devices. In addition, some steps or functions of the present application can be implemented by hardware, for example, as a circuit that cooperates with a processor to perform each step or function.

[0104] In a typical configuration of the present application, the terminal and the network device each include one or more processors (CPU), input / output interface, network interface and memory.

[0105] The memory may include non-permanent storage in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0106] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, read-only compact disk (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include non-transitory media such as modulated data signals and carrier waves.

[0107] In addition, a part of the present application may be applied as a computer program product, such as a computer program instruction, which, when executed by a computer, can call or provide the method and / or technical solution according to the present application through the operation of the computer. The program instruction for calling the method of the present application may be stored in a fixed or removable recording medium, and / or transmitted through a data stream in a broadcast or other signal-bearing medium, and / or stored in a working memory of a computer device that runs according to the program instruction. Here, according to an embodiment of the present application, a device is included, the device including a memory for storing computer program instructions and a processor for executing program instructions, wherein, when the computer program instruction is executed by the processor, the device is triggered to run the method and / or technical solution based on the aforementioned multiple embodiments according to the present application.

[0108] It is obvious to those skilled in the art that the present application is not limited to the details of the above exemplary embodiments, and that the present application can be implemented in other specific forms without departing from the spirit or basic features of the present application. Therefore, from any point of view, the embodiments should be regarded as exemplary and non-restrictive, and the scope of the present application is defined by the attached claims rather than the above description, and it is intended that all changes falling within the meaning and scope of the equivalent elements of the claims are included in the present application. Any figure mark in the claims should not be regarded as limiting the claims involved. In addition, it is obvious that the word "comprising" does not exclude other units or steps, and the singular does not exclude the plural. Multiple units or devices stated in the device claim can also be implemented by one unit or device through software or hardware.

Claims

1. A crane digital operation and maintenance management method, characterized in that: The steps include: Step 1. Obtain data when the crane is in working state; Step 2. Process and analyze the data based on the knowledge graph; Step 3. Based on the analysis results, perform resource analysis on the fault and warning data; Step 4. Automatically generate a work order based on the resource analysis results; Step 5. Handle the fault based on the dispatched work order; Step 6: After the fault handling is completed, the fault handling information is fed back and the system is updated based on the feedback.

2. The method according to claim 1, characterized in that The data obtained in step 1 when the crane is in working condition includes: data collected by the programmable logic controller (PLC), condition monitoring data, manually input maintenance data, fault repair records and crane design data.

3. The method according to claim 2, characterized in that The data processing in step 2 includes data integration, data cleaning and preprocessing; wherein, the data integration is to integrate the data collected by the PLC, the status monitoring data, the manually input maintenance data, the fault repair record and the crane design data on a unified database platform to form a comprehensive data view; the data cleaning is to remove redundant information in the integrated data; and the preprocessing is to process missing values ​​and outliers.

4. The method according to claim 2, characterized in that: The analysis of the data in step 2 includes feature engineering, knowledge graph update, state monitoring and anomaly detection, fault prediction and analysis, maintenance resource coordination, decision support and feedback loop and fault handling; wherein, the feature engineering is to extract key features from different data sources and identify important variables that affect operation and maintenance decisions; the knowledge graph update is to use the information in the knowledge graph to associate the relationship between different data; the state monitoring and anomaly detection is to compare the real-time monitoring data with the normal working state in the knowledge graph, use machine learning algorithms to detect anomalies, and identify potential faults; the fault prediction and analysis uses historical data and fault mode analysis in the knowledge graph to predict potential faults using prediction models and formulate maintenance plans in advance; the maintenance resource coordination is based on the data analysis results to optimize the inventory management of spare parts and arrange reasonable maintenance time; the decision support and feedback loop is to generate maintenance suggestions and decision support based on the results of processing and analysis, and feedback to the operation and maintenance personnel to optimize the maintenance strategy; the fault handling is to quickly locate the cause of the fault through data analysis when a fault occurs, and use the solutions and maintenance records provided by the knowledge graph to formulate response strategies for fault handling; The method of using a machine learning algorithm to detect anomalies and identify potential faults further includes: training a prediction model using an XGBoost algorithm based on data collected by the PLC on the crane and status monitoring data monitored by sensors. The algorithm flow is as follows: S1: Initialize the predicted value of each sample; S2: Define a specific loss function; S3: Calculate the derivative of the loss function for each of the sample prediction values; S4: Build a new decision tree based on the derivative information; S5: using the new decision tree to predict sample values ​​and adding them to the original values; S6: creating a decision tree in a loop until the loss function satisfies a condition; For the sensor signal value, the historical operation data is processed and used for model training; the trained model uses PLC data as input, finds the relationship between PLC data and sensor signal value based on historical data, predicts the signal data of the specified sensor, and then calculates the predicted value with the data value collected by the sensor in actual work, using the time series residual as the judgment standard, and issues an alarm if an abnormality continues to occur within a certain time series.

5. The method according to claim 1, characterized in that In step 4, after the resource analysis, there are two cases: one is that the relevant spare parts of the spare parts management system or the relevant resources of the equipment management system need to be connected, and then a work order is generated; the other is that the work order is directly generated without connecting to the relevant resources; The spare parts management system is used to provide logistical support for work order processing by importing the existing spare parts quantity through management personnel; The equipment management system includes equipment ledger entry, maintenance strategy, repair strategy and fault tree; the equipment management system establishes a crane equipment ledger to record equipment information; formulates maintenance strategies based on equipment usage and operating condition data, including preventive maintenance and planned maintenance, to ensure stable operation of the equipment; when encountering a fault, adopts a repair strategy to efficiently complete the repair process by generating a repair work order, allocating resources and tracking the repair progress; at the same time, the equipment management system uses fault tree analysis to decompose the fault by level, find out the possible causes, and accurately locate the root cause of the fault.

6. The method according to claim 5, characterized in that The step 4 automatically generates work orders according to the resource analysis result, including: work orders with spare parts requirements, work orders with resource requirements, and work orders without relevant resources; The step of generating the work order with spare parts requirement includes the following steps: S1. Spare parts confirmation: When a work order is generated, the system automatically identifies and verifies the inventory of the required spare parts to ensure that there are sufficient spare parts; S2. Generate work orders and assign tasks: When it is confirmed that the spare parts inventory meets the demand, the system generates a work order and assigns it to the maintenance team, marking the model, quantity and location information of the required spare parts; S3. Spare parts reservation and notification: The system reserves the required spare parts when generating a work order, and notifies the warehouse and operation and maintenance personnel to prepare them to avoid the lack of the spare parts during maintenance; Generating the work order with resource requirements includes the following steps: A1. Resource confirmation: The system automatically checks the availability of required resources and adjusts the task time if there is a conflict; A2. Generate work orders and allocate resources: After confirming that resources are available, the system generates a work order and specifies the required equipment, Maintenance site and operator information, notifying maintenance personnel to prepare resources; A3. Task reminders and resource coordination: The system automatically pushes task reminders and coordinates resources to ensure that maintenance work is completed on time within the planned time; Generating the work order that does not require related resources includes the following steps: B1. Directly generate work orders: Without the need for spare parts and resources, the system simplifies the process and directly generates work orders; B2. Work order assignment and feedback: Tasks will be directly assigned to the responsible personnel or maintenance team, and the system status will be updated after the task is completed.

7. The method according to claim 6, characterized in that The step 6 further includes: after the fault processing is completed, analyzing the fault data, feeding back the fault processing information to the spare parts management system, the equipment management system and the knowledge management module respectively, and the spare parts management system, the equipment management system and the knowledge management module perform system updates according to the fed-back information; The fault handling information is fed back to the spare parts management system and the system is updated, including: when spare parts are used in the fault handling process, the system automatically updates the spare parts inventory information and records the spare parts consumption. The system evaluates the replacement cycle and usage trend of spare parts according to the consumption and maintenance frequency, and adjusts the inventory plan; The fault handling information is fed back to the equipment management system and the system is updated, including: the equipment management system updates the equipment operation status and maintenance records after the fault is repaired, including the maintenance time, maintenance content, replacement parts and related test data; the equipment management system records and updates the maintenance cycle, performance status and historical faults of the equipment to form an equipment status file for subsequent status evaluation and adjustment of preventive maintenance strategies; The fault handling information is fed back to the knowledge management module and the module is updated, including: the fault handling data and analysis results are transmitted to the knowledge management module as experience cases to form a maintenance knowledge base; the knowledge management module collects typical fault handling processes, root cause analysis and optimal handling methods for maintenance guidance.

8. The method according to claim 7, characterized in that The knowledge management module performs systematic management based on data, and the specific management content includes the following aspects: ①. The knowledge management module receives and manages the following key data: Fault handling data: including the cause of each fault, handling steps, time consumption, spare parts used and effect evaluation, forming a detailed fault handling record; Equipment maintenance records: covering regular maintenance, inspection data, maintenance effects, key parameter adjustments of equipment, forming a maintenance file for the equipment life cycle; Experience summary and analysis data: including maintenance experience, fault trend analysis, and best practices; Spare parts usage information: tracking spare parts consumption, replacement cycle, life data and actual effects; Environmental and working condition data: equipment working environment, load conditions and external conditions, as external variables for fault and life analysis; ②. The knowledge management module manages the above data as follows: 1) Fault case management: Collect specific records of fault handling, including fault description, handling method, spare parts used, root cause analysis, and repair time, to form a standardized fault case library, and manage different types of faults through classification and labeling; 2) Experience knowledge management: The system stores experience data in the knowledge base and extracts standardized operating procedures applicable to common failures and maintenance scenarios. By analyzing the commonalities and trends of multiple failures, it extracts best practices and optimization suggestions to optimize maintenance processes and decisions. 3) Spare parts usage and replacement strategy management: record the actual usage of spare parts, the effect after fault repair, the frequency of spare parts consumption and replacement cycle, and form a reference for the service life of spare parts and the best replacement time; Based on spare parts consumption trends, the knowledge management module adjusts inventory to improve the accuracy of spare parts supply plans; 4) Maintenance strategy optimization management: The system dynamically adjusts the maintenance strategy and optimizes the maintenance cycle and content based on the equipment's historical maintenance data and failure frequency; Manage historical data of maintenance plans to analyze past maintenance results and failure reductions, and improve equipment maintenance processes; 5) Skill training and knowledge sharing: Collect and analyze typical cases of fault handling, create maintenance flowcharts and skill manuals; use visualization tools to display best practices for different faults and maintenance for knowledge sharing.

9. The method according to claim 8, characterized in that The knowledge graph is constructed based on the knowledge management module. The specific construction process is as follows: S1. Knowledge acquisition and ontology model construction: ① Knowledge acquisition: Extract knowledge from various data sources related to crane fault diagnosis, including fault type, fault handling method, maintenance experience of professionals, and equipment technical manuals. The knowledge provides detailed background and handling measures for various crane faults; ② Ontology model construction: construct the crane fault diagnosis ontology model and define the core concepts and relationships in the graph; ③Graph data storage: convert the ontology model into structured graph data and store it in the database of the knowledge graph to support subsequent fault diagnosis reasoning and knowledge retrieval; S2. Preliminary construction and visualization of the map: ① Relationship entity mapping: From the collected knowledge and data, fault cases, diagnostic processes, and equipment components are mapped to nodes and relationships in the knowledge graph; ② Hierarchical relationship construction: hierarchical relationships are established in the knowledge graph according to the fault type, so that the fault nodes at different levels reflect the correlation between the fault symptoms and the root causes, and from the treatment methods to the spare parts requirements; ③ Visualization display: Generate a visualization view of the knowledge graph to clearly present the core nodes and important relationships; S3. Knowledge graph update mechanism: ① Trend change determination and knowledge graph update: Operation and maintenance personnel analyze the causes of fault trend changes based on the equipment's operating trends and diagnostic data, and add the diagnostic results to the knowledge graph; by recording the cause analysis and treatment methods, the knowledge graph's ability to identify and respond to trend faults is improved; ② Manual judgment and trend update: In the early stage, operation and maintenance experts manually judge trend changes and update the nodes or relationships of the knowledge graph; ③ Manual and algorithmic updates: In the later stage, expert judgment is combined with diagnostic algorithms for updates. When the algorithm identifies abnormal trends, the knowledge graph is automatically updated, and nodes and relationships are improved after manual confirmation, gradually reducing manual participation; S4. Recording and processing of diagnostic algorithm output information: ① Information flow reception and storage: The knowledge graph framework receives the key fault information flow output by the diagnosis algorithm, including detected anomalies, predicted fault types and possible causes; ② Graph update of important information: Map the key information output by the algorithm to the graph nodes. If a new fault mode or new processing method is detected, add or modify nodes and relationships in the graph to improve the fault diagnosis content of the graph; ③ Automatic update of anomalies: When the algorithm identifies a new abnormal pattern, the system will automatically generate a corresponding abnormal node in the graph and establish associations with related equipment and fault types; S5. Knowledge graph training and self-learning: ① Automatic graph training: The updated graph data is used to train and optimize the fault diagnosis model to form a closed loop; the diagnosis algorithm will improve the recognition rate of new fault types based on the structured data of the graph; ② Self-learning mechanism: Through the fault handling cases and experience data continuously accumulated by the graph, the diagnostic algorithm gradually achieves self-learning, which can more quickly identify new faults and adjust maintenance strategies; ③ Manual supervision and feedback: The self-learning process of the graph still requires manual supervision, and the automatically updated content of the graph must be checked regularly to ensure the diagnostic accuracy of the model; S6. Continuous optimization and application of knowledge graph: ① Fault prediction and reasoning: Through the retrieval and reasoning of knowledge graphs, the system can predict potential faults, assist operation and maintenance personnel in early troubleshooting, and automatically recommend treatment methods based on historical data; ② Intelligent operation and maintenance decision support: The knowledge graph integrates the fault information and working condition data of all crane equipment, supports the operation and maintenance team to make quick decisions, and improves the efficiency of fault handling; ③Model visualization optimization: Through the continuous optimization of the visualization map, complex relationships can be visualized, which will help further operation and maintenance personnel training and knowledge sharing.

10. A digital operation and maintenance management system for a crane, the system comprising a memory for storing computer program instructions and a processor for executing the program instructions, wherein: When the computer program instructions are executed by the processor, the system is triggered to execute the method according to any one of claims 1 to 9.

Images