Fan fault guidance system and fan fault guidance method

Abstract

The invention discloses a fan fault guidance system and a fan fault guidance method, relates to the technical field of fan operation and maintenance, and can automatically identify a target fan and associate an equipment file, reduce manual query and matching time, shorten a fault processing period, generate a preventive operation and maintenance work order and reduce a sudden fault shutdown risk. The system comprises a fault analysis module used for determining an equipment file corresponding to a target fan according to a to-be-processed fault work order uploaded by an operation and maintenance terminal, querying a fault guidance manual corresponding to the equipment file in a fault guidance library, and sending the fault guidance manual to the operation and maintenance terminal, adding a to-be-processed fault work order and a work ticket and an operation ticket generated in the fault processing process to an equipment file, and adding the target fan to a health assessment queue; and the health assessment module is used for continuously selecting fan identifiers in the health assessment queue, performing health assessment on target fans corresponding to the fan identifiers, and generating an operation and maintenance work order according to a health assessment result.

Description

Technical Field

[0001] This application relates to the technical field of fan operation and maintenance, and particularly to a fan fault guidance system and a fan fault guidance method. Background Art

[0002] With the rapid development of the new energy industry and the accelerated promotion of the large-scale construction of offshore wind farms, fan equipment shows a trend of high power and complex structure, and the types of equipment failures and the complexity of operation and maintenance increase exponentially. The offshore distance of offshore wind farms continues to extend (some stations are more than 100 kilometers away from the shore), and combined with the high corrosiveness of the harsh marine environment on equipment, the failure rate of fans is significantly higher than that in onshore scenarios, which puts higher requirements on the response speed of fault diagnosis and the accuracy of maintenance guidance.

[0003] In the related art, operation and maintenance personnel carry paper-based fault code manuals, equipment maintenance guides and other materials to the site for investigation. However, this mode has problems such as lagging data update, damage or loss of the manual caused by the susceptibility of sea transportation to weather, and the need to cross-reference multiple manuals for complex faults, resulting in low equipment processing efficiency and high risk of misoperation. Summary of the Invention

[0004] In view of this, this application provides a fan fault guidance system and a fan fault guidance method, mainly aiming to solve the problems such as lagging data update of paper-based fault code manuals, equipment maintenance guides and other materials, damage or loss of the manual caused by the susceptibility of sea transportation to weather, and the need to cross-reference multiple manuals for complex faults, resulting in low equipment processing efficiency and high risk of misoperation.

[0005] According to the first aspect of this application, a fan fault guidance system is provided, which includes: a fault analysis module, an archive management module, and a health assessment module;

[0006] The fault analysis module is used to determine the target fan according to the fault work order to be processed uploaded by the operation and maintenance terminal, send a data acquisition request to the archive query module according to the fan identifier corresponding to the target fan, receive the equipment archive sent by the archive query module, query the fault guidance manual corresponding to the equipment archive in the fault guidance library, send the fault guidance manual to the operation and maintenance terminal, add the fault work order to be processed and the work tickets and operation tickets generated during the fault handling process to the equipment archive, and add the fan identifier of the target fan to the health assessment queue, waiting for the health assessment module to select the target fan from the health assessment queue for health assessment;

[0007] The archive management module is used to receive the data acquisition request initiated by the fault analysis module, query the corresponding equipment archive according to the fan identifier in the data acquisition request, and send the equipment archive to the fault analysis module;

[0008] The health assessment module is used to continuously select wind turbine identifiers from the health assessment queue, perform health assessments on target wind turbines corresponding to the wind turbine identifiers, and generate operation and maintenance work orders based on the health assessment results.

[0009] According to a second aspect of the present application, a wind turbine fault guidance method is provided, the method comprising:

[0010] The fault analysis module determines the target wind turbine according to the pending fault work order uploaded by the operation and maintenance terminal, and initiates a data acquisition request to the file query module according to the wind turbine identifier corresponding to the target wind turbine;

[0011] The file management module receives the data acquisition request, searches for a corresponding device file according to the wind turbine identifier in the data acquisition request, and sends the device file to the fault analysis module;

[0012] The fault analysis module receives the equipment file sent by the file query module, searches for a fault guidance manual corresponding to the equipment file in the fault guidance library, sends the fault guidance manual to the operation and maintenance terminal, adds the pending fault work order and the work ticket and operation ticket generated during the fault handling process to the equipment file, and adds the fan identifier of the target fan to the health assessment queue;

[0013] The health assessment module continuously selects wind turbine identifiers from the health assessment queue, performs health assessment on target wind turbines corresponding to the wind turbine identifiers, and generates an operation and maintenance work order according to the health assessment results.

[0014] According to a third aspect of the present application, a computer device is provided, comprising a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of any one of the methods described in the first aspect when executing the computer program.

[0015] According to a fourth aspect of the present application, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps of any one of the methods in the first aspect are implemented.

[0016] With the above technical solution, a fan fault guidance system and a fan fault guidance method provided by this application. The fault analysis module of this application determines the target fan according to the to-be-processed fault work order uploaded by the operation and maintenance terminal, and initiates a data acquisition request to the file query module according to the fan identifier corresponding to the target fan. The file management module receives the data acquisition request, queries the corresponding equipment file according to the fan identifier in the data acquisition request, and sends the equipment file to the fault analysis module. The fault analysis module receives the equipment file sent by the file query module, queries the fault guidance manual corresponding to the equipment file in the fault guidance library, sends the fault guidance manual to the operation and maintenance terminal, adds the to-be-processed fault work order and the work tickets and operation tickets generated during the fault handling process to the equipment file, and adds the fan identifier of the target fan to the health assessment queue. The health assessment module continuously selects fan identifiers in the health assessment queue, performs a health assessment on the target fan corresponding to the fan identifier, and generates an operation and maintenance work order according to the health assessment result. In the embodiment of this application, the fault analysis module automatically identifies the target fan and associates the equipment file, reducing the manual query and matching time and shortening the fault handling cycle. By continuously monitoring the fan identifiers in the queue through the health assessment module, predicting potential risks based on equipment status data (such as historical faults, maintenance records), and generating preventive operation and maintenance work orders, the risk of sudden fault shutdown is reduced.

[0017] The above description is only an overview of the technical solution of this application. In order to be able to understand the technical means of this application more clearly, it can be implemented according to the content of the specification. And in order to make the above and other purposes, features and advantages of this application more obvious and understandable, the following specifically gives the specific implementation manners of this application. Brief Description of the Drawings

[0018] By reading the detailed description of the preferred embodiments below, various other advantages and benefits will become clear to those of ordinary skill in the art. The drawings are only for the purpose of showing the preferred embodiments and are not considered to be a limitation of this application. And throughout the drawings, the same reference numerals are used to represent the same components. In the drawings:

[0019] Figure 1 Shows a schematic structural diagram of a fan fault guidance system provided by an embodiment of this application;

[0020] Figure 2 Shows a schematic diagram of the fault guidance book maintenance page of a fan fault guidance system provided by an embodiment of this application;

[0021] Figure 3 Shows a schematic diagram of the fault guidance manual page of a fan fault guidance system provided by an embodiment of this application;

[0022] Figure 4Shows a schematic diagram of the quick search page of a fan fault guidance system provided by an embodiment of the present application;

[0023] Figure 5 Shows a schematic diagram of the quick search page of a fan fault guidance system provided by an embodiment of the present application;

[0024] Figure 6 Shows a schematic diagram of the quick search page of a fan fault guidance system provided by an embodiment of the present application;

[0025] Figure 7 Shows a schematic diagram of the drawing link page of a fan fault guidance system provided by an embodiment of the present application;

[0026] Figure 8 Shows a schematic diagram of the home page map of a fan fault guidance system provided by an embodiment of the present application;

[0027] Figure 9 Shows a schematic diagram of the fan query function on the home page map of a fan fault guidance system provided by an embodiment of the present application;

[0028] Figure 10 Shows a schematic diagram of the health trend dashboard of a fan fault guidance system provided by an embodiment of the present application;

[0029] Figure 11 Shows a schematic diagram of the flow of a fan fault guidance method provided by an embodiment of the present application;

[0030] Figure 12 Shows a schematic diagram of the device structure of a computer device provided by an embodiment of the present application. Detailed implementation manners

[0031] The embodiments of the present application will be described in detail below. The examples of the embodiments are shown in the accompanying drawings, where the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions from beginning to end. The embodiments described below by referring to the accompanying drawings are exemplary and are only used to explain the present application and should not be construed as limiting the present application.

[0032] Those skilled in the art of the present technology can understand that unless specifically stated otherwise, the singular forms "a", "an", "the" and "said" used herein may also include the plural forms. It should be further understood that the term "including" used in the specification of the present application means the presence of the described features, integers, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components and / or their groups.

[0033] Those skilled in the art can understand that, unless otherwise defined, all terms (including technical and scientific terms) used herein have the same meaning as the general understanding of those of ordinary skill in the art to which this application belongs. It should also be understood that terms such as those defined in a general dictionary should be understood to have a meaning consistent with the meaning in the context of the prior art, and will not be interpreted in an idealized or overly formal sense unless specifically defined as here.

[0034] Those skilled in the art can understand that the "terminal" used herein includes both a device with a wireless signal receiver that only has the ability to receive and no ability to transmit, and a device with receiving and transmitting hardware that has the receiving and transmitting hardware capable of performing two-way communication on a two-way communication link. Such devices can include: cellular or other communication devices, which have a single-line display or a multi-line display or a cellular or other communication device without a multi-line display; PCS (Personal Communications Service), which can combine voice, data processing, fax, and / or data communication capabilities; PDA (Personal Digital Assistant), which can include a radio frequency receiver, a pager, Internet / intranet access, a web browser, a notepad, a calendar, and / or a GPS (Global Positioning System) receiver; conventional laptop and / or palm-top computers or other devices, which are conventional laptop and / or palm-top computers or other devices that have and / or include a radio frequency receiver. The "terminal" used herein can be portable, transportable, installed in a vehicle (air, sea, and / or land), or suitable for and / or configured to operate locally, and / or operate in a distributed manner at any other location on the earth and / or in space. The "terminal" used herein can also be a communication terminal, an Internet access terminal, a music / video playback terminal, such as a PDA, a MID (Mobile Internet Device), and / or a mobile phone with music / video playback functions, or can also be a smart TV, a set-top box, and other devices.

[0035] This application provides a fan fault guidance system. The system analyzes the historical fault work orders of the power production management system, the work tickets of the wind turbine generator sets, and the data in the fan standard fault code library through natural language processing technology, extracts semantic features related to fault analysis and fault handling to generate a structured fault guidance manual. In addition, the fault work orders, inspection work orders, defect work orders, warning work orders, and two-ticket data records in the power production management system record detailed processes and information such as equipment operations and maintenance details, covering operation time, operators, operation content, equipment status changes, etc. These data are real records of the fan operation and maintenance process, hiding key information such as the operation rules of the equipment and the potential factors for faults. By analyzing the above data, the frequency and key points of the fan's daily maintenance operations can be understood, the changes in the operation status of the equipment after different operations can be judged, and basic data support can be provided for the analysis and evaluation of the fan's health status and fault prediction.

[0036] The current fan fault guidance system adopts the Spring Cloud technology system, utilizes its mature distributed system solution, and realizes the complete autonomy and controllability of the system. The lightweight open-source web server nginx is introduced as the forwarding service for page resources, realizing the separation of static and dynamic resources. The static resources are processed by nginx, and the dynamic resources are handed over to the backend server for processing.

[0037] The system supports access and use by two types of terminals, namely PC and APP. All functions of the two types of terminals are synchronized and adapted. The App side has an offline viewing function to cope with the situation where there is no signal on the mobile phone during on-site defect elimination work at sea.

[0038] As Figure 1 shown, a fan fault guidance system provided by an embodiment of this application includes: a fault analysis module 11, an archive management module 12, and a health assessment module 13.

[0039] Among them, the fault analysis module 11 is used to determine the target fan according to the to-be-processed fault work order uploaded by the operation and maintenance terminal, send a data acquisition request to the archive query module 12 according to the fan identifier corresponding to the target fan, receive the equipment archive sent by the archive query module 12, query the fault guidance manual corresponding to the equipment archive in the fault guidance library, send the fault guidance manual to the operation and maintenance terminal, add the to-be-processed fault work order and the work tickets and operation tickets generated during the fault handling process to the equipment archive, and add the fan identifier of the target fan to the health assessment queue, waiting for the health assessment module 13 to select the target fan from the health assessment queue for health assessment.

[0040] The archive management module 12 is used to receive the data acquisition request initiated by the fault analysis module 11, query the corresponding equipment archive according to the fan identifier in the data acquisition request, and send the equipment archive to the fault analysis module 11.

[0041] A health assessment module 13 is used to continuously select a fan identifier from a health assessment queue, perform a health assessment on the target fan corresponding to the fan identifier, and generate an operation and maintenance work order based on the health assessment result.

[0042] Furthermore, in order to more effectively implement fault guidance, facilitate efficient knowledge query and reasoning during fault diagnosis and elimination, and enhance the intelligent support ability of the system for fault handling, a fan fault guidance system provided by an embodiment of the present application further includes a construction module.

[0043] In the embodiment of the present application, the construction module is used to construct a fault guidance library. The fault guidance library can consist of multiple fault guidance manuals. Among them, a complete structured fault guidance manual should at least include basic fault handling principles (including handling basic principles and safety operation teaching videos of key equipment), fault codes, fault names, model series, applicable fan models, fault descriptions, fault causes, maintenance materials (tool list, material preparation), safety measures, maintenance steps, maintenance instructions, and corresponding pictures, multimedia information, and drawing information. Among them, pictures, multimedia information, and drawing information can vividly and intuitively assist in guiding fault diagnosis and elimination. In the embodiment of the present application, the construction module generates a structured fault guidance manual by integrating the historical data of fault work orders and wind turbine work tickets in the power production management system, ensuring that each manual has detailed content and clear steps, facilitating operation and maintenance personnel to quickly locate problems and solve them efficiently.

[0044] During the actual operation process, the construction module needs to obtain operation and maintenance data from the power production management system. It should be noted that the operation and maintenance data includes the historical structured data of fault work orders and wind turbine work tickets of all stations in the power production management system and the structured data of the fault code library. Among them, the fault work order records the fault code, fault cause, name of the faulty equipment, fan model, and handling method (maintenance steps). The wind turbine work ticket records the work location, work content, fault phenomenon description, fault cause, and handling method. The fan standard fault code library records the equipment manufacturer name, model series, equipment model, fault code, fault name, fault classification, and fault description. Furthermore, the construction module deletes redundant information and corrects incorrect entries in the operation and maintenance data by comparing the operation and maintenance data (fault work order, fan ticket data, standard code library data) of the same fault. At the same time, the construction module unifies the date and field formats in the operation and maintenance data to complete data standardization. For example, ensuring the consistency of the date format, etc.

[0045] Furthermore, the construction module also uses NLP (Natural Language Processing) technology to parse the text content of the standardized operation and maintenance data. Specifically, the construction module needs to identify key entities in the text content, such as fault descriptions, fault names, fault causes, safety measures, maintenance steps, etc. By accurately identifying entities, it provides basic elements for subsequent determination of relationships between entities and construction of the graph structure. Furthermore, the relationships between various entities are determined. These relationships between entities are the key to the knowledge graph expressing knowledge and reasoning. For example, it is determined that a certain fault is caused by a specific operation. Next, faults of similar types are grouped together. Further, based on semantic similarity algorithms and causal reasoning algorithms, target fields in the operation and maintenance data are extracted. The various extracted target fields cover all aspects related to faults, providing rich data support for constructing a comprehensive and accurate knowledge graph. The target fields include, but are not limited to, fault codes, fault names, fan brands, model series, applicable fan models, fault descriptions, fault causes, safety measures, tool lists, material preparations, maintenance steps, and maintenance instructions. The extraction logic of the key fields is shown in Table 1 below:

[0046] Table 1 Extraction Logic of Key Fields

[0047]

[0048]

[0049] Furthermore, the construction module defines entity types and relationships between entities based on the extracted target fields. Among them, entity types include faults, equipment, spare parts, operation steps, safety specifications, etc. The relationships between entities include fault - cause, fault - applicable equipment, tool and spare part - applicable fault, cause - step - associated tool, etc. Furthermore, a knowledge graph model is constructed based on entity types and relationships between entities. By constructing a knowledge graph model based on the above - defined entity types and relationships between entities, the conversion process from data to structured knowledge representation is completed, enabling knowledge to be stored, queried, and reasoned in the form of a graph. Through this conversion, the knowledge graph not only realizes the structured storage of data but also improves the efficiency and accuracy of fault diagnosis. The complex relationships between entities are clearly shown, providing accurate decision - making support for operation and maintenance personnel and further optimizing the full - process management of fan operation and maintenance.

[0050] In the embodiment of the present application, the construction module provides an active learning mechanism. Specifically, when extracting the target fields from the operation and maintenance data, the construction module also determines the confidence level of the extraction result and compares the confidence level with a preset confidence threshold. If the confidence level is lower than the preset confidence threshold, an artificial review process is generated, enabling the reviewer to review the target fields based on the artificial review process and upload the review results based on the review terminal. In addition, the construction module also receives the review results uploaded by the reviewer, deletes or modifies the extracted targets according to the review results, and updates the model parameters to improve the extraction accuracy. Through continuous iterative optimization, the system gradually reduces manual intervention, realizes efficient and accurate automated operation and maintenance, and ensures the stable and reliable operation of the fan.

[0051] In the embodiment of the present application, the construction module also provides a version control function. Specifically, when the construction module detects that the power production management system receives new work order data, it identifies the fault name corresponding to the work order data, the fault cause and repair steps corresponding to the fault name, and queries the fault cause set and repair step set corresponding to the fault name in the fault guidance library. If the fault cause does not exist in the fault cause set or the repair step does not exist in the repair step set, the fault guidance library is updated by adding the fault cause to the fault cause set or adding the repair step to the repair step set. Otherwise, there is no need to update the fault guidance library. Through version control, the system can update the fault guidance library in a timely manner, ensuring that the operation and maintenance personnel can obtain the latest fault handling solutions, and further improving the efficiency and reliability of fan operation and maintenance.

[0052] In addition, the construction module also provides a feedback mechanism. The feedback mechanism allows users to report inaccurate or missing information, and updates the model and database accordingly to ensure the accuracy and practicality of the system. Specifically, the construction module receives the feedback report uploaded by the operation and maintenance personnel and updates the fault guidance library according to the entities and the relationships between the entities recorded in the feedback report. In addition, as Figure 2 shown, the administrator user can manually create and maintain the fault guidance manual through the fault guidance data maintenance application. The fault code, fault description, fan brand, model series, and applicable fan model are directly obtained from the fault code library of the power production management system. The material repair (tool list, material preparation) data is selected from the tool management and material management of the power production management system, thus ensuring the accuracy, integrity, consistency, and timeliness of the data. The extended filling data includes form text information such as fault causes, fault repair steps, repair materials, and repair instructions, and uploads pictures, multimedia files, and drawings as attachments. In response to the maintenance request uploaded by the review terminal, the construction module controls through the artificial review process to ensure that all newly added or updated manual information can be reviewed, and then updates the fault guidance library according to the entities and the relationships between the entities carried in the maintenance request.

[0053] In the embodiment of the present application, the fault analysis module 11 queries the fault guidance manual corresponding to the equipment file in the fault guidance library and sends the fault guidance manual to the operation and maintenance terminal. It should be noted that before actual operation, the operation and maintenance personnel can upload the fault work order to be processed through the operation and maintenance terminal. The fault analysis module 11 queries the corresponding fault guidance manual according to the fault information in the fault work order to be processed and returns it to the operation and maintenance terminal. As Figure 3 shown, the operation and maintenance personnel can view the fault description, fault cause, processing steps, etc. according to the fault guidance manual, and can also trigger the function of viewing the drawing through the terminal to view the fan equipment drawing corresponding to the corresponding fan model, which is convenient for the operation and maintenance personnel to maintain the target fan. Further, the fault analysis module 11 also adds the fault work order to be processed, the work ticket and operation ticket generated during the fault handling process to the equipment file, and adds the fan identifier of the target fan to the health assessment queue, waiting for the health assessment module 13 to select the target fan from the health assessment queue for health assessment. In the embodiment of the present application, the fault analysis module 11 is the core application function of the system. The on-site operation and maintenance personnel can view the fault manual library by model series and fault type through the APP and PC. As Figures 4 to 6 shown, the system also provides a user quick search and query function. The system constructs an interactive query function, uses the search dialog box, and uses query means such as fault codes and keywords to determine the uniqueness of the fault guidance through the fault code and model series, and then quickly locates and queries the required fault handling manual in the fault guidance library. When the user views the fault guidance, as Figure 7 shown, they can quickly link to the complete drawings of each part of the fan currently handling the fault, improving the efficiency of viewing the manual drawings and on-site fault handling. The App end will obtain the fault handler, fault equipment name, and fault code of the unprocessed fault work order in the power production management system. Search for the longitude and latitude, fan manufacturer, and fan model in the physical equipment table of the power production management system through the fault equipment name. Compare the longitude and latitude of the fan in the physical equipment with the geographical location of the current user. After the positions match, the corresponding fault guidance data will be found in the fault guidance library according to the fault code of the fault work order, the fan manufacturer and fan model of the physical equipment and pushed directly to the user, without the user having to search by themselves.

[0054] In the embodiment of the present application, the fan is associated with the file to achieve "one machine, one file", and all relevant documents, data, maintenance records, etc. of the commissioned fan can be viewed. As Figure 8 and Figure 9As shown, the file management module 12 marks the fan icons of the already commissioned fans on the home page map according to the corresponding real-time geographical locations, and when it detects that a fan icon on the home page map is clicked, it displays the device details page corresponding to the fan icon. The details page is used to display the operation and maintenance information and device drawings of the fan corresponding to the fan icon. The operation and maintenance information includes, but is not limited to, fan equipment technical parameters, recent work, unit list, unit test list, unit pile foundation list, offshore engineering (underwater) list, work records, work statistics, and fault statistics. Among them, the fault statistics include fault work order data based on the power production management system, statistically analyzing the fault-related situations of the current fan from multiple dimensions, and outputting visual charts and health assessment results. It should be noted that the file management module 12 also provides an online document viewing function, and on-site operation and maintenance personnel can view documents such as ledger information, drawings, and reports online. In addition, due to the high reuse rate of drawings, to avoid duplicate data upload, the file management module 12 also provides a unified upload and management entry for the drawings of each part of the fan equipment for the equipment file and fault guidance parts to call and view.

[0055] In the embodiment of the present application, the health assessment module 13 selects a fan identifier from the health assessment queue, sends a data acquisition request to the file management module 12 based on the fan identifier, and receives the work order data sent by the file management module 12. The work order data includes fault work orders, inspection work orders, defect work orders, warning work orders, operation tickets, and work tickets. The fault work order records the fault occurrence time, fault end time, equipment name, fault code, treatment method (such as component replacement), etc. The key fields include fault type, impact degree, maintenance personnel feedback, etc. The inspection work order contains regular / temporary inspection records, such as equipment appearance inspection results, vibration test data, infrared thermography images, etc. The key fields include anomaly marks, detected values, and recommended measures. The defect work order records non-fault equipment hidden dangers (such as loose bolts, peeling coatings), and treatment priorities (high / medium / low). The warning work order records automatic alarms from the SCADA system (such as temperature overrun, abnormal vibration), including threshold trigger records. The operation ticket records equipment start / stop, operation steps, executor, and timestamp. The work ticket records the safety measures for maintenance tasks, tool lists, and acceptance results. Further, in order to quantitatively predict the health status of the fan, it is necessary to construct a health assessment model according to historical work order data using a hybrid neural network. Specifically, the health assessment module 13 needs to align the work order timestamps in the work order data with the SCADA sensor data according to the equipment ID to generate a unified time series. For example, for a gearbox fault work order at 12:33 on May 16, 2024, the vibration and oil temperature data one hour before and after this time point are associated. Further, the health assessment module 13 uses the BERT+BiLSTM-CRF model to extract work order data features from the work order data, and associates the operations in the work order data with the maintenance effects of historical similar faults to construct a knowledge graph. For example, the operation of "filter element replacement" in the work order is associated with the maintenance effects of historical similar faults to quantify its contribution to the health status. Further, the health assessment module 13 also extracts time series features from the SCADA sensor data. The extracted time series features are statistical quantities (mean, variance, FFT spectrum peak) of the SCADA sensor data (vibration, temperature, power). Further, the health assessment module 13 uses the LSTM network to process the SCADA time series features, and uses the Sentence-BERT model to encode the work order data features into 768-dimensional text vectors. And uses the CNN network to process the text vectors, fuses the outputs of the LSTM network and the CNN network through a fully connected layer to generate a health feature vector, and predicts the health score of the fan equipment based on the health feature vector, and generates a health assessment result according to the health score.

[0056] Furthermore, the health assessment module 13 also needs to train and optimize the constructed health assessment model. Specifically, the health assessment module 13 needs to define labels, that is, reverse-define the current health status based on whether a failure occurs within the next 30 days (e.g., no failure = 100 points, severe failure = 0 points). And for devices with frequent warnings recently, increase their sample weights (e.g., the number of warnings in the past 7 days × 2). Next, the health assessment module 13 uses the pre-trained LSTM layer in the general device failure dataset (such as NASA turbofan degradation data) to accelerate convergence, and adds gradient penalty (WGAN-GP) to improve the robustness of the model to noisy work order data (such as missing fields). In addition, as Figure 10 shown, the health assessment module 13 also provides a health trend dashboard, which is used to display the real-time health score of the fan (in the form of a dashboard) and the historical change curve. The health trend dashboard is also associated with work order event markers (such as the score rising from 40 to 75 after a certain repair), and based on the health score analysis, displays the key factors affecting the health score.

[0057] In the embodiment of the present application, the health assessment module 13 compares the health score in the health assessment result with the first score threshold and the second score threshold respectively. When the health assessment result is lower than the first score threshold and higher than or equal to the second score threshold, an inspection work order is generated to prompt the key inspection items. When the health assessment result is lower than the second score threshold, a defect work order is generated and requires processing within 48 hours. It should be noted that the first score threshold can be set to 70, and the second score threshold can be set to 50. In addition, it can also be adjusted according to actual needs. The present application does not specifically limit the values of the first score threshold and the second score threshold. Furthermore, the health assessment module 13 also recommends a maintenance time window based on the reinforcement learning (such as DQN) algorithm according to spare part inventory, personnel scheduling, and weather prediction, and optimizes the execution time of the inspection work order or the defect work order using the maintenance time window. For example, avoid the high wind periods in the next 3 days and select a low wind speed day for blade maintenance.

[0058] The system provided by the embodiments of the present application, the fault analysis module determines the target wind turbine according to the to-be-processed fault work order uploaded by the operation and maintenance terminal, and initiates a data acquisition request to the file query module according to the wind turbine identifier corresponding to the target wind turbine. The file management module receives the data acquisition request, queries the corresponding equipment file according to the wind turbine identifier in the data acquisition request, and sends the equipment file to the fault analysis module. The fault analysis module receives the equipment file sent by the file query module, queries the fault guidance manual corresponding to the equipment file in the fault guidance library, sends the fault guidance manual to the operation and maintenance terminal, adds the to-be-processed fault work order and the work tickets and operation tickets generated during the fault handling process to the equipment file, and adds the wind turbine identifier of the target wind turbine to the health assessment queue. The health assessment module continuously selects the wind turbine identifier in the health assessment queue, conducts a health assessment on the target wind turbine corresponding to the wind turbine identifier, and generates an operation and maintenance work order according to the health assessment result. The embodiments of the present application automatically identify the target wind turbine through the fault analysis module and associate the equipment file, reducing the manual query and matching time and shortening the fault handling cycle. By continuously monitoring the wind turbine identifiers in the queue through the health assessment module, predicting potential risks based on equipment status data (such as historical faults, maintenance records), and generating preventive operation and maintenance work orders, the risk of sudden fault shutdown is reduced.

[0059] The embodiments of the present application provide a method for guiding wind turbine faults, as Figure 11 shown, the method includes:

[0060] 201. The fault analysis module determines the target wind turbine according to the to-be-processed fault work order uploaded by the operation and maintenance terminal, and initiates a data acquisition request to the file query module according to the wind turbine identifier corresponding to the target wind turbine.

[0061] 202. The file management module receives the data acquisition request, queries the corresponding equipment file according to the wind turbine identifier in the data acquisition request, and sends the equipment file to the fault analysis module.

[0062] 203. The fault analysis module receives the equipment file sent by the file query module, queries the fault guidance manual corresponding to the equipment file in the fault guidance library, sends the fault guidance manual to the operation and maintenance terminal, adds the to-be-processed fault work order and the work tickets and operation tickets generated during the fault handling process to the equipment file, and adds the wind turbine identifier of the target wind turbine to the health assessment queue.

[0063] 204. The health assessment module continuously selects the wind turbine identifier in the health assessment queue, conducts a health assessment on the target wind turbine corresponding to the wind turbine identifier, and generates an operation and maintenance work order according to the health assessment result.

[0064] According to the method provided by the embodiment of the present application, the fault analysis module determines the target wind turbine based on the pending fault work order uploaded by the operation and maintenance terminal, and initiates a data acquisition request to the archive query module based on the wind turbine identifier corresponding to the target wind turbine. The archive management module receives the data acquisition request, queries the corresponding equipment archive based on the wind turbine identifier in the data acquisition request, and sends the equipment archive to the fault analysis module. The fault analysis module receives the equipment archive sent by the archive query module, queries the fault guidance manual corresponding to the equipment archive in the fault guidance library, sends the fault guidance manual to the operation and maintenance terminal, and adds the pending fault work order and the work ticket and operation ticket generated during the fault handling process to the equipment archive, and adds the wind turbine identifier of the target wind turbine to the health assessment queue. The health assessment module continuously selects the wind turbine identifier in the health assessment queue, performs a health assessment on the target wind turbine corresponding to the wind turbine identifier, and generates an operation and maintenance work order based on the health assessment results. The embodiment of the present application automatically identifies the target wind turbine and associates the equipment archive through the fault analysis module, reduces manual query and matching time, and shortens the fault handling cycle. The health assessment module continuously monitors the turbine identification in the queue, predicts potential risks based on equipment status data (such as historical failures and maintenance records), generates preventive operation and maintenance work orders, and reduces the risk of sudden failure and downtime.

[0065] To solve the above technical problems, the embodiment of the present invention also provides a computer device. Figure 12 , Figure 12 This is a basic structural block diagram of the computer device in this embodiment.

[0066] like Figure 12 As shown, a schematic diagram of the internal structure of a computer device. The computer device includes a processor, a non-volatile storage medium, a memory and a network interface connected via a system bus. Among them, the non-volatile storage medium of the computer device stores an operating system, a database and computer-readable instructions, and the database may store a control information sequence. When the computer-readable instructions are executed by the processor, the processor can implement a data relationship reconstruction method. The processor of the computer device is used to provide computing and control capabilities to support the operation of the entire computer device. The memory of the computer device may store computer-readable instructions. When the computer-readable instructions are executed by the processor, the processor can execute a data relationship reconstruction method. The network interface of the computer device is used to connect and communicate with the terminal. Those skilled in the art will understand that Figure 4 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than shown in the figure, or combine certain components, or have a different component arrangement.

[0067] In this embodiment, the memory stores program codes and various types of data required to execute the above modules. The network interface is used for data transmission between the user terminal and the server. The memory in this embodiment stores the program codes and data required to execute all sub-modules in the data relationship reconstruction device, and the server can call the program codes and data of the server to execute the functions of all sub-modules.

[0068] The present invention also provides a storage medium storing computer-readable instructions, which, when executed by one or more processors, cause the one or more processors to execute the steps of the data relationship reconstruction method in any of the above embodiments.

[0069] Those of ordinary skill in the art can understand that all or part of the processes of implementing the methods in the above embodiments can be completed by instructing relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium, and when the program is executed, it can include the processes of the embodiments of the above methods. Among them, the aforementioned storage medium can be a non-volatile storage medium such as a magnetic disk, an optical disk, a read-only memory (ROM), or a random access memory (RAM), etc.

[0070] The present invention also provides a storage medium storing computer-readable instructions, which, when executed by one or more processors, cause the one or more processors to execute the steps of the data relationship reconstruction method in any of the above embodiments.

[0071] Those of ordinary skill in the art can understand that all or part of the processes of implementing the methods in the above embodiments can be completed by instructing relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium, and when the program is executed, it can include the processes of the embodiments of the above methods. Among them, the aforementioned storage medium can be a non-volatile storage medium such as a magnetic disk, an optical disk, a read-only memory (ROM), or a random access memory (RAM), etc.

[0072] Those skilled in the art of this technology can understand that the steps, measures, and solutions in the various operations, methods, and processes discussed in this application can be alternated, changed, combined, or deleted. Further, the other steps, measures, and solutions in the various operations, methods, and processes discussed in this application can also be alternated, changed, rearranged, decomposed, combined, or deleted. Further, the steps, measures, and solutions in the prior art that are the same as those disclosed in this application can also be alternated, changed, rearranged, decomposed, combined, or deleted.

[0073] The above are only some embodiments of the present application. It should be noted that for those of ordinary skill in the art, without departing from the principle of the present application, several improvements and refinements can be made, and these improvements and refinements should also be regarded as the protection scope of the present application.

Claims

1. A fan fault guidance system, characterized in that, The system includes: a fault analysis module, an archive management module, and a health assessment module; The fault analysis module is used to determine a target wind turbine according to the to-be-processed fault work order uploaded by the operation and maintenance terminal, send a data acquisition request to the archive query module according to the wind turbine identifier corresponding to the target wind turbine, receive the equipment archive sent by the archive query module, query the fault guidance manual corresponding to the equipment archive in the fault guidance library, send the fault guidance manual to the operation and maintenance terminal, add the to-be-processed fault work order and the work tickets and operation tickets generated during the fault handling process to the equipment archive, and add the wind turbine identifier of the target wind turbine to the health assessment queue, waiting for the health assessment module to select the target wind turbine from the health assessment queue for health assessment; The archive management module is used to receive the data acquisition request initiated by the fault analysis module, query the corresponding equipment archive according to the wind turbine identifier in the data acquisition request, and send the equipment archive to the fault analysis module; The health assessment module is used to continuously select wind turbine identifiers from the health assessment queue, perform health assessment on the target wind turbines corresponding to the wind turbine identifiers, and generate operation and maintenance work orders according to the health assessment results.

2. The system according to claim 1, wherein The system further includes: a construction module; The construction module is used to obtain operation and maintenance data from the power production management system, delete redundant information in the operation and maintenance data and correct error entries by comparing the operation and maintenance data of the same fault, and unify the date and field formats in the operation and maintenance data to complete data standardization. The operation and maintenance data includes, but is not limited to, structured data such as fault work orders, work tickets of wind turbine generator sets, and the wind turbine standard fault code library; The construction module is further used to parse the standardized operation and maintenance data by using natural language processing technology NLP, extract target fields from the operation and maintenance data based on semantic similarity algorithms and causal reasoning algorithms, define entity types and relationships between entities according to the extracted target fields, and construct a knowledge graph model based on the entity types and the relationships between entities. The target fields include, but are not limited to, fault codes, fault names, wind turbine brands, model series, applicable wind turbine models, fault descriptions, fault causes, safety measures, tool lists, material preparations, maintenance steps, and maintenance instructions.

3. The system according to claim 2, wherein The construction module is used to determine the confidence level of the extraction result when extracting the target fields from the operation and maintenance data. If the confidence level is lower than the preset confidence threshold, an artificial review process is generated, so that the review personnel can review the target fields based on the artificial review process and upload the review results based on the review terminal; The construction module is used to receive the review results uploaded by the review personnel and delete or modify the target fields according to the review results.

4. The system according to claim 3, wherein The construction module is also used to identify the fault name corresponding to the work order data, the fault cause and the maintenance steps corresponding to the fault name when it detects that the power production management system receives new work order data, and query the fault cause set and the maintenance step set corresponding to the fault name in the fault guidance library. If the fault cause does not exist in the fault cause set or the maintenance step does not exist in the maintenance step set, the fault guidance library is updated, and the fault cause is added to the fault cause set or the maintenance step is added to the maintenance step set; The construction module is also used to receive the feedback report uploaded by the operation and maintenance personnel, update the fault guidance library according to the entities and the relationships between the entities recorded in the feedback report, and respond to the maintenance request uploaded by the audit terminal to update the fault guidance library according to the entities and the relationships between the entities carried in the maintenance request.

5. The system according to claim 1, characterized in that, The file management module is also used to mark the fan icons of the commissioned fans on the home page map according to the corresponding real-time geographical locations, and when it detects that the fan icon on the home page map is clicked, display the device details page corresponding to the fan icon. The details page is used to display the operation and maintenance information and device drawings of the fan corresponding to the fan icon. The operation and maintenance information includes, but is not limited to, fan equipment technical parameters, recent work, unit list, unit test list, unit pile foundation list, offshore engineering list, work record, work statistics, and fault statistics. Among them, the fault statistics include visual charts and health assessment results.

6. The system according to claim 1, wherein The health assessment module is used to select a fan identifier in the health assessment queue, send a data acquisition request to the file management module based on the fan identifier, and receive the work order data sent by the data acquisition request. The work order data includes fault work orders, inspection work orders, defect work orders, warning work orders, operation tickets and work tickets; The health assessment module is used to align the work order timestamps in the work order data with the SCADA sensor data according to the device ID to generate a unified time series, extract key entities from the work order data using the BERT+BiLSTM-CRF model, and construct a knowledge graph to associate the operations in the work order data with the repair effects of historical similar faults; The health assessment module is also used to extract the time series features of the SCADA sensor data, process the SCADA time series features using the LSTM network, encode the work order data into text vectors using the Sentence-BERT model, process the text vectors using the CNN network, fuse the outputs of the LSTM network and the CNN network through a fully connected layer to generate a health feature vector, and predict the health score of the fan equipment based on the health feature vector, and generate the health assessment result according to the health score.

7. The system according to claim 6, characterized in that, The health assessment module is configured to compare the health score in the health assessment result with a first scoring threshold and a second scoring threshold, respectively, and generate an inspection work order when the health assessment result is lower than the first scoring threshold and higher than or equal to the second scoring threshold; and generate a defect work order when the health assessment result is lower than the second scoring threshold; The health assessment module is further used to determine a maintenance time window based on a reinforcement learning algorithm, according to spare parts inventory, personnel scheduling and weather forecast, and use the maintenance time window to optimize the execution time of the inspection work order or the defect work order.

8. A fan fault guidance method applied to a fan fault guidance system, characterized in that, include: The fault analysis module determines the target wind turbine according to the pending fault work order uploaded by the operation and maintenance terminal, and initiates a data acquisition request to the file query module according to the wind turbine identifier corresponding to the target wind turbine; The file management module receives the data acquisition request, searches for a corresponding device file according to the wind turbine identifier in the data acquisition request, and sends the device file to the fault analysis module; The fault analysis module receives the equipment file sent by the file query module, searches for a fault guidance manual corresponding to the equipment file in the fault guidance library, sends the fault guidance manual to the operation and maintenance terminal, adds the pending fault work order and the work ticket and operation ticket generated during the fault handling process to the equipment file, and adds the fan identifier of the target fan to the health assessment queue; The health assessment module continuously selects wind turbine identifiers from the health assessment queue, performs health assessment on target wind turbines corresponding to the wind turbine identifiers, and generates an operation and maintenance work order according to the health assessment results.

9. A computer device, comprising a memory and a processor, the memory storing a computer program, characterized in that, When the processor executes the computer program, the steps of the method according to claim 8 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, the steps of the method according to claim 8 are implemented.

Images