Fan fault prevention and knowledge base integrated management system

Abstract

The invention relates to the field of fan operation and maintenance management, and discloses a fan fault prevention and knowledge base integrated management system, which comprises a data acquisition module, a data preprocessing module, a fault early warning module, a knowledge base module, a decision support module and a man-machine interaction module, the output end of the data acquisition module is electrically connected with the input end of a data preprocessing module; the output end of the data preprocessing module is electrically connected with the input end of a fault early warning module; the output end of the fault early warning module is electrically connected with the input end of a knowledge base module and the input end of a man-machine interaction module. The knowledge base module is bidirectionally and electrically connected with a fault early warning module; and the output end of the decision support module is electrically connected with the input end of a man-machine interaction module. According to the invention, high-quality data is obtained through multi-dimensional pre-processing, intelligent early warning decision making of the linkage module is realized, the period is accurately shortened, and the problems of poor data and early warning lag in the prior art are solved.

Description

Technical Field

[0001] This invention relates to the field of wind turbine operation and maintenance management, specifically a wind turbine fault prevention and knowledge base integrated management system. Background Technology

[0002] With the rapid development of the new energy industry, wind turbines, as core equipment for clean energy power generation, directly affect power generation efficiency and operation and maintenance costs due to their operational stability. Currently, wind turbine fault management mainly relies on manual inspections, regular maintenance, and simple monitoring systems. While these methods can detect faults to some extent, they have significant limitations.

[0003] In existing technologies, data acquisition is often limited to a single dimension, focusing primarily on basic parameters of key components, making it difficult to comprehensively reflect the wind turbine's operating status. Data processing is mostly limited to simple recording, lacking effective noise reduction, outlier removal, and feature extraction, resulting in low data quality and interference with subsequent analysis. Furthermore, fault warnings often rely on single threshold judgments, failing to incorporate historical fault cases and diagnostic rules, leading to low accuracy and significant delays in warnings. In addition, fault handling experience lacks a systematic knowledge base, making it difficult to quickly apply historical solutions when new faults occur, resulting in long maintenance cycles, high costs, and severely impacting the continuous and stable operation of wind turbines. Therefore, this paper proposes an integrated management system for wind turbine fault prevention and knowledge base. Summary of the Invention

[0004] To address the shortcomings of existing technologies, this invention provides a wind turbine fault prevention and knowledge base integrated management system to solve the problems mentioned in the background section.

[0005] To achieve the above objectives, the present invention provides the following technical solution: a wind turbine fault prevention and knowledge base integrated management system, comprising: The system includes a data acquisition module, a data preprocessing module, a fault early warning module, a knowledge base module, a decision support module, and a human-computer interaction module. The output of the data acquisition module is electrically connected to the input of the data preprocessing module. It is used to collect multi-dimensional monitoring data during the operation of the wind turbine and transmit it to the data preprocessing module, ensuring the comprehensiveness and real-time nature of the monitoring of the wind turbine's operating status. The output of the data preprocessing module is electrically connected to the input of the fault early warning module. It is used to perform noise reduction, outlier removal and feature extraction on the monitoring data, thereby improving the quality and effectiveness of the monitoring data and providing a reliable basis for subsequent analysis. The output of the fault early warning module is electrically connected to the input of the knowledge base module and the input of the human-computer interaction module, respectively. It is used to perform fault risk assessment and generate early warning information based on the processed data and historical data in the knowledge base module, thereby improving the accuracy and timeliness of fault early warning and realizing the early identification of potential faults. The knowledge base module and the fault early warning module are bidirectionally electrically connected, and the output end of the knowledge base module is electrically connected to the input end of the decision support module. It is used to store fault cases, diagnostic rules and maintenance experience data, and to provide data support for the fault early warning module. This realizes the systematic accumulation and efficient reuse of fault handling experience and strengthens the data support for early warning analysis. The output of the decision support module is electrically connected to the input of the human-computer interaction module. It is used to generate fault prevention plans and maintenance suggestions based on early warning information and knowledge base data, providing scientific and targeted action guidance for operation and maintenance personnel and improving the professionalism and efficiency of fault handling. The human-computer interaction module is used to realize information interaction between users and the system, optimize the user operation experience, and ensure the smoothness and timeliness of information transmission. The self-learning unit of the fault early warning module periodically extracts features of new fault cases, combines them with the original model parameters, and adjusts the model weights through gradient descent to complete the iterative optimization of the early warning model. The data acquisition module obtains wind turbine operating data from multiple dimensions. After noise reduction, cleaning, and feature extraction by the preprocessing module, it provides high-quality input for fault early warning. The fault early warning module combines historical data from the knowledge base to assess risks and issue tiered warnings, ensuring timeliness. The knowledge base module dynamically updates fault cases, diagnostic rules, and maintenance experience, providing strong data support for early warning and decision-making. The decision support module generates targeted prevention plans and spare parts recommendations, and evaluates the implementation effects, forming a closed-loop management system. The human-machine interaction module enhances user experience and system usability through visualization, interactive operation, and multi-level alarms. The overall system improves the reliability and maintenance efficiency of wind turbine operation.

[0006] Preferably, the data acquisition module includes a vibration sensor, a temperature sensor, a pressure sensor, a speed sensor, and a current sensor, with each sensor installed in key parts of the fan's bearings, motor, impeller, and pipelines. The data acquisition module also includes an adaptive sampling unit, which dynamically adjusts the data acquisition frequency according to the wind turbine's operating conditions. During normal operation, low-frequency sampling is used, and when abnormal fluctuations are detected, it automatically switches to high-frequency sampling. For the specific implementation of the adaptive sampling unit in the data acquisition module, the optimal sampling frequency range corresponding to different operating conditions (such as low wind speed, medium wind speed, high wind speed, etc.) can be preset, the operating parameters of the wind turbine can be monitored in real time to determine the operating conditions, and the matching sampling frequency can be selected from the preset range for dynamic adjustment. Multiple sensors are installed in key parts of the wind turbine to comprehensively acquire multi-dimensional data on wind turbine operation, providing rich evidence for fault analysis. The adaptive sampling unit dynamically adjusts the data acquisition frequency according to the wind turbine's operating conditions, avoiding data redundancy or insufficiency that may be caused by fixed-frequency sampling. While ensuring data validity, it improves data acquisition efficiency and reduces data storage and processing costs. This flexible data acquisition method helps to more accurately capture changes in wind turbine operating status, providing high-quality data support for subsequent data preprocessing, fault early warning, and other stages. This improves the reliability and accuracy of the entire wind turbine fault prevention and knowledge base integrated management system, ensuring stable wind turbine operation.

[0007] Preferably, the data preprocessing module includes a noise filtering unit, a data cleaning unit, and a feature extraction unit; The noise filtering unit uses a wavelet transform algorithm to reduce noise in the original monitoring data; The data cleaning unit identifies and removes outliers using the 3σ criterion. The feature extraction unit extracts time-domain features, frequency-domain features, and time-frequency-domain features from the processed data. The time-domain features include peak value, mean, and variance, while the frequency-domain features include spectral peak value and center frequency. The time-frequency-domain features are obtained through short-time Fourier transform. Specific wavelet basis functions, such as Daubechies wavelets, are used to reduce noise by setting the number of decomposition levels according to the data characteristics; when removing outliers using the 3σ criterion, control limits can be explicitly calculated using the sample mean and standard deviation to identify outliers; during feature extraction, it can be specified that the mean and variance are extracted in the time domain, and the spectral energy is extracted in the frequency domain, and the short-time Fourier transform is used to extract features in the time and frequency domains. The noise filtering unit uses wavelet transform algorithm to effectively remove noise from the original monitoring data and improve data quality. The data cleaning unit identifies and removes outliers using the 3σ criterion to avoid abnormal data interfering with subsequent analysis. The feature extraction unit extracts time-domain, frequency-domain, and time-frequency-domain features from the processed data to comprehensively mine data information. After processing by this module, more accurate and reliable data is provided to the fault early warning module, making fault risk assessment more precise and the generated early warning information more effective. At the same time, high-quality data helps the knowledge base module to better store and utilize data, providing a solid foundation for subsequent decision support, improving the performance and stability of the entire wind turbine fault prevention and knowledge base integrated management system, and ensuring the safe and stable operation of the wind turbine.

[0008] Preferably, the fault early warning module includes a feature matching unit, a risk assessment unit, and an early warning level classification unit; The feature matching unit compares the feature data output by the preprocessing module with the fault feature templates in the knowledge base module; The risk assessment unit calculates the probability of failure based on the matching results, combined with the wind turbine's operating time and environmental parameters. The warning level classification unit divides the warning information into three levels—minor warning, moderate warning, and severe warning—based on the risk assessment results, and triggers the corresponding prompting mechanism for each level. Efficient similarity algorithms (such as cosine similarity) are used to compare the feature data output by the preprocessing module with the fault feature templates in the knowledge base, thereby improving matching accuracy and efficiency. The feature matching unit can quickly locate potential faults by comparing them with fault feature templates in the knowledge base. The risk assessment unit calculates the fault probability by combining the wind turbine's operating time and environmental parameters, making the assessment more scientific and accurate. The early warning level classification unit divides the early warning information into three levels and triggers the corresponding prompt mechanism, enabling users to take timely measures according to the severity of the early warning, enhancing the system's ability to prevent and respond to wind turbine faults, ensuring the stable operation of the wind turbine, and reducing losses caused by faults.

[0009] Preferably, the knowledge base module includes a fault case library, a diagnostic rule library, a maintenance experience library, and a model library; The fault case library stores historical fault phenomena, causes, handling processes, and results data; The diagnostic rule base uses production rules to represent fault diagnosis logic; The maintenance experience database records maintenance methods, tools, and precautions for different types of faults. The model library stores trained fault prediction models; The knowledge base module also includes a knowledge update unit, which supports updating the knowledge base content through manual input or automatic learning by the system. It can periodically collect new fault cases, maintenance feedback and other data from actual operation, and after review and sorting, automatically enter them into the corresponding database in a predetermined format to complete the knowledge update; The fault case library stores historical fault process data to provide a reference for subsequent diagnosis; the diagnosis rule library presents logic with production rules, making diagnosis systematic; the maintenance experience library records maintenance details to help maintenance personnel get started quickly; the model library's predictive models can provide early warnings; the knowledge update unit ensures that knowledge keeps pace with the times. All libraries work together to provide comprehensive, accurate, and dynamic knowledge support for wind turbine fault prevention and handling, assisting the system in providing accurate early warnings and generating reasonable solutions, improving the stability and reliability of wind turbine operation, and reducing the occurrence of faults and losses.

[0010] Preferably, the decision support module includes a solution generation unit, a spare parts recommendation unit, and an effect evaluation unit; The solution generation unit generates targeted fault prevention solutions based on the fault warning type and maintenance experience in the knowledge base, including inspection focus and maintenance cycle adjustment suggestions; The spare parts recommendation unit recommends a list of required spare parts and provides inventory warnings based on the fault type and wind turbine model. The effectiveness evaluation unit tracks the effectiveness of the prevention plan after its implementation and feeds back the evaluation results to the knowledge base module. By pre-setting a mapping rule base of different fault warning types and maintenance experience, combined with the basic parameters of the wind turbine, the system can quickly generate inspection priorities and maintenance cycle adjustment suggestions. For the spare parts recommendation unit, a database linking wind turbine models and spare parts lists is established, and an inventory threshold is set. When the inventory is lower than the threshold, an early warning is triggered. The effect evaluation unit adopts a set evaluation index system, such as failure rate and maintenance time. The effect is evaluated by comparing the index data before and after the implementation of the prevention plan, and the results are fed back to the knowledge base module. The solution generation unit can accurately generate fault prevention solutions based on fault warning types and maintenance experience in the knowledge base, clarifying inspection priorities and adjusting maintenance cycles to improve the pertinence and efficiency of wind turbine maintenance. The spare parts recommendation unit recommends spare parts lists based on fault types and wind turbine models and provides inventory warnings to avoid maintenance delays caused by spare parts shortages, ensuring the normal operation of wind turbines. The effect evaluation unit tracks the implementation effect of the prevention solutions and feeds the results back to the knowledge base module, which helps to continuously improve the knowledge base data, optimize subsequent decisions, and form a virtuous cycle, improving the reliability and practicality of the entire wind turbine fault prevention and management system, and providing users with more scientific and reasonable decision support.

[0011] Preferably, the human-computer interaction module includes a data visualization unit, an operation interaction unit, and an alarm prompt unit; The data visualization unit displays wind turbine operating parameters, fault warning information, and knowledge base data in the form of charts; The operation interaction unit supports users in querying historical data, entering new fault cases, and modifying system parameters. The alarm notification unit outputs different levels of warning information through sound, light and screen pop-ups, and supports manual confirmation of alarm information. Data visualization can be achieved by using open-source visualization libraries such as ECharts and configuring the corresponding chart types (such as line charts to display the trend of operating parameters, bar charts to display the number of fault warnings, etc.). The data visualization unit presents wind turbine operating parameters, fault warnings, and knowledge base data in intuitive charts, enabling users to quickly grasp the wind turbine status. The operation interaction unit gives users the ability to query historical data, enter new cases, and modify parameters, enhancing the system's flexibility and scalability, and facilitating user adjustments based on actual conditions. The alarm notification unit outputs different levels of warning information through sound, light, and screen pop-ups, ensuring that users receive critical warnings in a timely and accurate manner, respond quickly, effectively improve the timeliness and accuracy of fault handling, and ensure stable wind turbine operation.

[0012] Preferably, it also includes a data storage module, the input end of which is electrically connected to the output end of the data preprocessing module, and the output end of which is electrically connected to the input ends of the fault early warning module and the knowledge base module, respectively. The data storage module adopts a distributed database architecture to store raw monitoring data, preprocessed feature data, and system operation logs, and supports long-term archiving and fast querying of data. This can be achieved through distributed file systems or databases such as Hadoop HDFS or Cassandra, ensuring high availability and scalability of data, and storing raw monitoring data, preprocessed feature data, and system operation logs; The data storage module adopts a distributed database architecture, which greatly enhances the system's reliability and scalability. Through distributed storage, the system can effectively distribute data storage pressure, avoid single points of failure, and ensure the continuous availability and integrity of data. At the same time, this architecture supports the storage and management of massive amounts of data, meeting the storage needs of multi-dimensional monitoring data generated during wind turbine operation. In addition, the close connection between the data storage module and the data preprocessing module, fault early warning module, and knowledge base module enables seamless data flow and sharing, providing a solid data foundation for fault early warning and decision support. Overall, this design improves the overall performance and stability of the system, providing a strong guarantee for the long-term stable operation of the wind turbine fault prevention and knowledge base integrated management system.

[0013] Preferably, it also includes a remote communication module, which is electrically connected to the data acquisition module, the fault early warning module and the human-machine interaction module respectively; The remote communication module adopts 5G or industrial Ethernet communication protocol to realize the real-time transmission of field monitoring data to the remote monitoring center, as well as the parameter configuration and command issuance of the field system by the remote monitoring center. Communication interfaces are set in the data acquisition module, fault early warning module and human-machine interaction module. The connection with the remote communication module is realized through hardware devices with 5G or industrial Ethernet communication protocols (such as 5G routers and industrial Ethernet switches) to complete data transmission and command interaction. The benefits of setting up a remote communication module that includes 5G or industrial Ethernet communication protocols are significant. On the one hand, it can transmit on-site monitoring data to the remote monitoring center in real time, allowing managers to keep abreast of the wind turbine's operating status and obtain information even when they are not on-site. On the other hand, the remote monitoring center can configure on-site system parameters and issue commands to achieve remote control and improve management efficiency. Moreover, the high speed and stability of 5G and the high reliability of industrial Ethernet ensure the timeliness and accuracy of data transmission, enabling the rapid transmission of fault warnings and other information, facilitating timely problem handling, enhancing the overall stability and controllability of the system, and improving the practicality and convenience of the wind turbine fault prevention and knowledge base integrated management system.

[0014] Preferably, the fault warning module further includes a self-learning unit, which is bidirectionally electrically connected to the knowledge base module. The self-learning unit periodically iterates and optimizes the warning model based on newly generated fault case data. By comparing the model prediction results with the actual fault situation, the model parameters are corrected so that the fault warning accuracy can be dynamically improved as the system runs. The self-learning unit can be set to a weekly or monthly cycle to extract new fault case data from the knowledge base module, retrain the early warning model using machine learning algorithms such as decision trees and neural networks, update the parameters of the new model to the early warning module, and achieve iterative optimization of the model. On the one hand, it can periodically use new fault case data to iteratively optimize the early warning model, enabling the model to adapt to new operating conditions and changes in fault characteristics of wind turbines, thereby improving the accuracy and timeliness of early warnings. On the other hand, the knowledge base provides data support for the self-learning unit, and the optimized model results of the self-learning unit can enrich the content of the knowledge base, forming a virtuous cycle. This design ensures that the system can continuously learn and evolve, reduce false alarms and missed alarms, assist maintenance personnel in taking measures in advance, reduce the failure rate of wind turbines, extend the service life of equipment, and improve the economy and stability of wind farm operation.

[0015] Compared with existing technologies, this invention provides a wind turbine fault prevention and knowledge base integrated management system, which has the following beneficial effects: This invention achieves the acquisition of high-quality monitoring data through multi-dimensional data collection and professional preprocessing, which has the advantage of providing a precise data foundation for fault early warning and solves the problems of poor data quality and low analysis reliability in traditional methods. By leveraging the two-way linkage between the fault early warning module and the knowledge base, as well as the collaboration of the decision support module, it realizes intelligent early warning and scientific decision-making based on historical experience and real-time data, which has the advantages of improving the accuracy of fault early warning and shortening the maintenance cycle, and solves the problems of lagging early warning and low reuse rate of maintenance experience in traditional methods. Attached Figure Description

[0016] Figure 1 This is a schematic diagram of the wind turbine fault prevention and knowledge base integrated management system architecture of the present invention; Figure 2 This is a schematic diagram of the internal structure of the data preprocessing module of the present invention; Figure 3 This is a schematic diagram of the fault early warning module of the present invention. Detailed Implementation

[0017] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0018] This invention provides a technical solution: a wind turbine fault prevention and knowledge base integrated management system. Please refer to [link / reference]. Figure 1 , Figure 2 and Figure 3 ,include: The system includes a data acquisition module, a data preprocessing module, a fault early warning module, a knowledge base module, a decision support module, and a human-computer interaction module. The output of the data acquisition module is electrically connected to the input of the data preprocessing module, and is used to collect multi-dimensional monitoring data during the operation of the wind turbine and transmit it to the data preprocessing module. The output of the data preprocessing module is electrically connected to the input of the fault early warning module, and is used to perform noise reduction, outlier removal and feature extraction on the monitoring data. The output of the fault early warning module is electrically connected to the input of the knowledge base module and the input of the human-computer interaction module, respectively, and is used to perform fault risk assessment and generate early warning information based on the processed data and historical data in the knowledge base module. The knowledge base module is bidirectionally electrically connected to the fault early warning module, and the output end of the knowledge base module is electrically connected to the input end of the decision support module. It is used to store fault cases, diagnostic rules and maintenance experience data, and to provide data support for the fault early warning module. The output of the decision support module is electrically connected to the input of the human-computer interaction module, and is used to generate fault prevention plans and maintenance suggestions based on early warning information and knowledge base data. The human-computer interaction module is used to enable information interaction between the user and the system; The self-learning unit of the fault early warning module periodically extracts features of new fault cases, combines them with the original model parameters, and adjusts the model weights through gradient descent to complete the iterative optimization of the early warning model. The data acquisition module obtains wind turbine operating data from multiple dimensions. After noise reduction, cleaning, and feature extraction by the preprocessing module, it provides high-quality input for fault early warning. The fault early warning module combines historical data from the knowledge base to assess risks and issue tiered warnings, ensuring timeliness. The knowledge base module dynamically updates fault cases, diagnostic rules, and maintenance experience, providing strong data support for early warning and decision-making. The decision support module generates targeted prevention plans and spare parts recommendations, and evaluates the implementation effects, forming a closed-loop management system. The human-machine interaction module enhances user experience and system usability through visualization, interactive operation, and multi-level alarms. The overall system improves the reliability and maintenance efficiency of wind turbine operation.

[0019] Please see Figure 1 , Figure 2 and Figure 3 The data acquisition module includes a vibration sensor, a temperature sensor, a pressure sensor, a speed sensor, and a current sensor, with each sensor installed in key parts of the fan's bearings, motor, impeller, and pipelines. The data acquisition module also includes an adaptive sampling unit, which dynamically adjusts the data acquisition frequency according to the wind turbine's operating conditions. During normal operation, low-frequency sampling is used, and when abnormal fluctuations are detected, it automatically switches to high-frequency sampling. For the specific implementation of the adaptive sampling unit in the data acquisition module, the optimal sampling frequency range corresponding to different operating conditions (such as low wind speed, medium wind speed, high wind speed, etc.) can be preset, the operating parameters of the wind turbine can be monitored in real time to determine the operating conditions, and the matching sampling frequency can be selected from the preset range for dynamic adjustment. Multiple sensors are installed in key parts of the wind turbine to comprehensively acquire multi-dimensional data on wind turbine operation, providing rich evidence for fault analysis. The adaptive sampling unit dynamically adjusts the data acquisition frequency according to the wind turbine's operating conditions, avoiding data redundancy or insufficiency that may be caused by fixed-frequency sampling. While ensuring data validity, it improves data acquisition efficiency and reduces data storage and processing costs. This flexible data acquisition method helps to more accurately capture changes in wind turbine operating status, providing high-quality data support for subsequent data preprocessing, fault early warning, and other stages. This improves the reliability and accuracy of the entire wind turbine fault prevention and knowledge base integrated management system, ensuring stable wind turbine operation.

[0020] Please see Figure 1 , Figure 2 and Figure 3 The data preprocessing module includes a noise filtering unit, a data cleaning unit, and a feature extraction unit. The noise filtering unit uses a wavelet transform algorithm to reduce noise in the original monitoring data; The data cleaning unit identifies and removes outliers using the 3σ criterion. The feature extraction unit extracts time-domain features, frequency-domain features, and time-frequency-domain features from the processed data. The time-domain features include peak value, mean, and variance, while the frequency-domain features include spectral peak value and center frequency. The time-frequency-domain features are obtained through short-time Fourier transform. Specific wavelet basis functions, such as Daubechies wavelets, are used to reduce noise by setting the number of decomposition levels according to the data characteristics; when removing outliers using the 3σ criterion, control limits can be explicitly calculated using the sample mean and standard deviation to identify outliers; during feature extraction, it can be specified that the mean and variance are extracted in the time domain, and the spectral energy is extracted in the frequency domain, and the short-time Fourier transform is used to extract features in the time and frequency domains. The noise filtering unit uses wavelet transform algorithm to effectively remove noise from the original monitoring data and improve data quality. The data cleaning unit identifies and removes outliers using the 3σ criterion to avoid abnormal data interfering with subsequent analysis. The feature extraction unit extracts time-domain, frequency-domain, and time-frequency-domain features from the processed data to comprehensively mine data information. After processing by this module, more accurate and reliable data is provided to the fault early warning module, making fault risk assessment more precise and the generated early warning information more effective. At the same time, high-quality data helps the knowledge base module to better store and utilize data, providing a solid foundation for subsequent decision support, improving the performance and stability of the entire wind turbine fault prevention and knowledge base integrated management system, and ensuring the safe and stable operation of the wind turbine.

[0021] Please see Figure 1 , Figure 2 and Figure 3 The fault early warning module includes a feature matching unit, a risk assessment unit, and an early warning level classification unit; The feature matching unit compares the feature data output by the preprocessing module with the fault feature templates in the knowledge base module; The risk assessment unit calculates the probability of failure based on the matching results, combined with the wind turbine's operating time and environmental parameters. The warning level classification unit divides the warning information into three levels—minor warning, moderate warning, and severe warning—based on the risk assessment results, and triggers the corresponding prompting mechanism for each level. Efficient similarity algorithms (such as cosine similarity) are used to compare the feature data output by the preprocessing module with the fault feature templates in the knowledge base, thereby improving matching accuracy and efficiency. The feature matching unit can quickly locate potential faults by comparing them with fault feature templates in the knowledge base. The risk assessment unit calculates the fault probability by combining the wind turbine's operating time and environmental parameters, making the assessment more scientific and accurate. The early warning level classification unit divides the early warning information into three levels and triggers the corresponding prompt mechanism, enabling users to take timely measures according to the severity of the early warning, enhancing the system's ability to prevent and respond to wind turbine faults, ensuring the stable operation of the wind turbine, and reducing losses caused by faults.

[0022] Please see Figure 1 , Figure 2 and Figure 3 The knowledge base module includes a fault case library, a diagnostic rule library, a maintenance experience library, and a model library; The fault case library stores historical fault phenomena, causes, handling processes, and results data; The diagnostic rule base uses production rules to represent fault diagnosis logic; The maintenance experience database records maintenance methods, tools, and precautions for different types of faults. The model library stores trained fault prediction models; The knowledge base module also includes a knowledge update unit, which supports updating the knowledge base content through manual input or automatic learning by the system. It can periodically collect new fault cases, maintenance feedback and other data from actual operation, and after review and sorting, automatically enter them into the corresponding database in a predetermined format to complete the knowledge update; The fault case library stores historical fault process data to provide a reference for subsequent diagnosis; the diagnosis rule library presents logic with production rules, making diagnosis systematic; the maintenance experience library records maintenance details to help maintenance personnel get started quickly; the model library's predictive models can provide early warnings; the knowledge update unit ensures that knowledge keeps pace with the times. All libraries work together to provide comprehensive, accurate, and dynamic knowledge support for wind turbine fault prevention and handling, assisting the system in providing accurate early warnings and generating reasonable solutions, improving the stability and reliability of wind turbine operation, and reducing the occurrence of faults and losses.

[0023] Please see Figure 1 , Figure 2 and Figure 3 The decision support module includes a solution generation unit, a spare parts recommendation unit, and an effect evaluation unit. The solution generation unit generates targeted fault prevention solutions based on the fault warning type and maintenance experience in the knowledge base, including inspection focus and maintenance cycle adjustment suggestions; The spare parts recommendation unit recommends a list of required spare parts and provides inventory warnings based on the fault type and wind turbine model. The effectiveness evaluation unit tracks the effectiveness of the prevention plan after its implementation and feeds back the evaluation results to the knowledge base module. By pre-setting a mapping rule base of different fault warning types and maintenance experience, combined with the basic parameters of the wind turbine, the system can quickly generate inspection priorities and maintenance cycle adjustment suggestions. For the spare parts recommendation unit, a database linking wind turbine models and spare parts lists is established, and an inventory threshold is set. When the inventory is lower than the threshold, an early warning is triggered. The effect evaluation unit adopts a set evaluation index system, such as failure rate and maintenance time. The effect is evaluated by comparing the index data before and after the implementation of the prevention plan, and the results are fed back to the knowledge base module. The solution generation unit can accurately generate fault prevention solutions based on fault warning types and maintenance experience in the knowledge base, clarifying inspection priorities and adjusting maintenance cycles to improve the pertinence and efficiency of wind turbine maintenance. The spare parts recommendation unit recommends spare parts lists based on fault types and wind turbine models and provides inventory warnings to avoid maintenance delays caused by spare parts shortages, ensuring the normal operation of wind turbines. The effect evaluation unit tracks the implementation effect of the prevention solutions and feeds the results back to the knowledge base module, which helps to continuously improve the knowledge base data, optimize subsequent decisions, and form a virtuous cycle, improving the reliability and practicality of the entire wind turbine fault prevention and management system, and providing users with more scientific and reasonable decision support.

[0024] Please see Figure 1 , Figure 2 and Figure 3 The human-computer interaction module includes a data visualization unit, an operation interaction unit, and an alarm prompt unit; The data visualization unit displays wind turbine operating parameters, fault warning information, and knowledge base data in the form of charts; The operation interaction unit supports users in querying historical data, entering new fault cases, and modifying system parameters. The alarm notification unit outputs different levels of warning information through sound, light and screen pop-ups, and supports manual confirmation of alarm information. Data visualization can be achieved by using open-source visualization libraries such as ECharts and configuring the corresponding chart types (such as line charts to display the trend of operating parameters, bar charts to display the number of fault warnings, etc.). The data visualization unit presents wind turbine operating parameters, fault warnings, and knowledge base data in intuitive charts, enabling users to quickly grasp the wind turbine status. The operation interaction unit gives users the ability to query historical data, enter new cases, and modify parameters, enhancing the system's flexibility and scalability, and facilitating user adjustments based on actual conditions. The alarm notification unit outputs different levels of warning information through sound, light, and screen pop-ups, ensuring that users receive critical warnings in a timely and accurate manner, respond quickly, effectively improve the timeliness and accuracy of fault handling, and ensure stable wind turbine operation.

[0025] Please see Figure 1 , Figure 2 and Figure 3 It also includes a data storage module, the input end of which is electrically connected to the output end of the data preprocessing module, and the output end of which is electrically connected to the input ends of the fault early warning module and the knowledge base module, respectively. The data storage module adopts a distributed database architecture to store raw monitoring data, preprocessed feature data, and system operation logs, and supports long-term archiving and fast querying of data. This can be achieved through distributed file systems or databases such as Hadoop HDFS or Cassandra, ensuring high availability and scalability of data, and storing raw monitoring data, preprocessed feature data, and system operation logs; The data storage module adopts a distributed database architecture, which greatly enhances the system's reliability and scalability. Through distributed storage, the system can effectively distribute data storage pressure, avoid single points of failure, and ensure the continuous availability and integrity of data. At the same time, this architecture supports the storage and management of massive amounts of data, meeting the storage needs of multi-dimensional monitoring data generated during wind turbine operation. In addition, the close connection between the data storage module and the data preprocessing module, fault early warning module, and knowledge base module enables seamless data flow and sharing, providing a solid data foundation for fault early warning and decision support. Overall, this design improves the overall performance and stability of the system, providing a strong guarantee for the long-term stable operation of the wind turbine fault prevention and knowledge base integrated management system.

[0026] Please see Figure 1 , Figure 2 and Figure 3 It also includes a remote communication module, which is electrically connected to the data acquisition module, the fault early warning module and the human-machine interaction module respectively; The remote communication module adopts 5G or industrial Ethernet communication protocol to realize the real-time transmission of field monitoring data to the remote monitoring center, as well as the parameter configuration and command issuance of the field system by the remote monitoring center. Communication interfaces are set in the data acquisition module, fault early warning module and human-machine interaction module. The connection with the remote communication module is realized through hardware devices with 5G or industrial Ethernet communication protocols (such as 5G routers and industrial Ethernet switches) to complete data transmission and command interaction. The benefits of setting up a remote communication module that includes 5G or industrial Ethernet communication protocols are significant. On the one hand, it can transmit on-site monitoring data to the remote monitoring center in real time, allowing managers to keep abreast of the wind turbine's operating status and obtain information even when they are not on-site. On the other hand, the remote monitoring center can configure on-site system parameters and issue commands to achieve remote control and improve management efficiency. Moreover, the high speed and stability of 5G and the high reliability of industrial Ethernet ensure the timeliness and accuracy of data transmission, enabling the rapid transmission of fault warnings and other information, facilitating timely problem handling, enhancing the overall stability and controllability of the system, and improving the practicality and convenience of the wind turbine fault prevention and knowledge base integrated management system.

[0027] Please see Figure 1 , Figure 2 and Figure 3The fault warning module also includes a self-learning unit, which is bidirectionally electrically connected to the knowledge base module. It periodically iterates and optimizes the warning model based on newly generated fault case data. By comparing the model prediction results with the actual fault situation, the model parameters are corrected so that the fault warning accuracy can be dynamically improved as the system runs. The self-learning unit can be set to a weekly or monthly cycle to extract new fault case data from the knowledge base module, retrain the early warning model using machine learning algorithms such as decision trees and neural networks, update the parameters of the new model to the early warning module, and achieve iterative optimization of the model. On the one hand, it can periodically use new fault case data to iteratively optimize the early warning model, enabling the model to adapt to new operating conditions and changes in fault characteristics of wind turbines, thereby improving the accuracy and timeliness of early warnings. On the other hand, the knowledge base provides data support for the self-learning unit, and the optimized model results of the self-learning unit can enrich the content of the knowledge base, forming a virtuous cycle. This design ensures that the system can continuously learn and evolve, reduce false alarms and missed alarms, assist maintenance personnel in taking measures in advance, reduce the failure rate of wind turbines, extend the service life of equipment, and improve the economy and stability of wind farm operation.

[0028] This solution employs a data acquisition module that uses various sensors, including vibration and temperature sensors, to collect operational data from key components of the wind turbine. After the adaptive sampling unit dynamically adjusts the acquisition frequency, the data is transmitted to the data preprocessing module. The preprocessing module uses wavelet transform for noise reduction and the 3σ criterion to remove outliers, extracting time-domain, frequency-domain, and time-frequency-domain features. The fault early warning module compares the feature data with fault templates in the knowledge base, calculates the fault probability based on runtime and environmental parameters, and classifies the fault into three levels: minor, moderate, and severe. The self-learning unit periodically optimizes the early warning model with new cases. The knowledge base module stores fault cases, diagnostic rules, and other data, dynamically updating it through a knowledge update unit and providing support for the decision support module. The decision support module generates prevention plans and recommends spare parts based on the early warning information, evaluates the implementation effects, and feeds back to the knowledge base. The human-machine interaction module displays data using visual charts, supports user operation, and provides multiple alarm prompts. The system also stores data through a distributed database and utilizes 5G or industrial Ethernet for remote data transmission and control.

[0029] It should be noted that, in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or apparatus.

[0030] Although embodiments of the invention have been shown and described, it will be understood by those skilled in the art that various changes, modifications, substitutions and alterations can be made to these embodiments without departing from the principles and spirit of the invention, the scope of which is defined by the appended claims and their equivalents.

Claims

1. A wind turbine fault prevention and knowledge base integrated management system, characterized in that, include: The system includes a data acquisition module, a data preprocessing module, a fault early warning module, a knowledge base module, a decision support module, and a human-computer interaction module. The output of the data acquisition module is electrically connected to the input of the data preprocessing module, and is used to collect multi-dimensional monitoring data during the operation of the wind turbine and transmit it to the data preprocessing module. The output of the data preprocessing module is electrically connected to the input of the fault early warning module, and is used to perform noise reduction, outlier removal and feature extraction on the monitoring data. The output of the fault early warning module is electrically connected to the input of the knowledge base module and the input of the human-computer interaction module, respectively, and is used to perform fault risk assessment and generate early warning information based on the processed data and historical data in the knowledge base module. The knowledge base module is bidirectionally electrically connected to the fault early warning module, and the output end of the knowledge base module is electrically connected to the input end of the decision support module. It is used to store fault cases, diagnostic rules and maintenance experience data, and to provide data support for the fault early warning module. The output of the decision support module is electrically connected to the input of the human-computer interaction module, and is used to generate fault prevention plans and maintenance suggestions based on early warning information and knowledge base data. The human-computer interaction module is used for information interaction between the user and the system.

2. The integrated management system for wind turbine fault prevention and knowledge base according to claim 1, characterized in that: The data acquisition module includes a vibration sensor, a temperature sensor, a pressure sensor, a speed sensor, and a current sensor, with each sensor installed in the bearing, motor, impeller, and pipe of the fan. The data acquisition module also includes an adaptive sampling unit, which dynamically adjusts the data acquisition frequency according to the operating conditions of the wind turbine.

3. The integrated management system for wind turbine fault prevention and knowledge base according to claim 1, characterized in that: The data preprocessing module includes a noise filtering unit, a data cleaning unit, and a feature extraction unit. The noise filtering unit uses a wavelet transform algorithm to reduce noise in the original monitoring data; The data cleaning unit identifies and removes outliers using the 3σ criterion. The feature extraction unit extracts time-domain features, frequency-domain features, and time-frequency-domain features from the processed data.

4. The integrated management system for wind turbine fault prevention and knowledge base according to claim 1, characterized in that: The fault early warning module includes a feature matching unit, a risk assessment unit, and an early warning level classification unit; The feature matching unit compares the feature data output by the preprocessing module with the fault feature templates in the knowledge base module; The risk assessment unit calculates the probability of failure based on the matching results, combined with the wind turbine's operating time and environmental parameters. The warning level classification unit divides the warning information into three levels: minor warning, moderate warning, and severe warning, based on the risk assessment results.

5. The integrated management system for wind turbine fault prevention and knowledge base according to claim 1, characterized in that: The knowledge base module includes a fault case library, a diagnostic rule library, a maintenance experience library, and a model library; The fault case library stores historical fault phenomena, causes, handling processes, and results data; The diagnostic rule base uses production rules to represent fault diagnosis logic; The maintenance experience database records maintenance methods, tools, and precautions for different types of faults. The model library stores trained fault prediction models; The knowledge base module also includes a knowledge update unit.

6. The integrated management system for wind turbine fault prevention and knowledge base according to claim 1, characterized in that: The decision support module includes a solution generation unit, a spare parts recommendation unit, and an effect evaluation unit. The solution generation unit generates targeted fault prevention solutions based on the fault warning type and maintenance experience in the knowledge base, including inspection focus and maintenance cycle adjustment suggestions; The spare parts recommendation unit recommends a list of required spare parts and provides inventory warnings based on the fault type and wind turbine model. The effectiveness evaluation unit tracks the effectiveness of the prevention plan after its implementation and feeds back the evaluation results to the knowledge base module.

7. The integrated management system for wind turbine fault prevention and knowledge base according to claim 1, characterized in that: The human-computer interaction module includes a data visualization unit, an operation interaction unit, and an alarm prompt unit; The data visualization unit displays wind turbine operating parameters, fault warning information, and knowledge base data in the form of charts; The operation interaction unit supports users in querying historical data, entering new fault cases, and modifying system parameters. The alarm notification unit outputs different levels of warning information through sound, light, and screen pop-ups.

8. The integrated management system for wind turbine fault prevention and knowledge base according to claim 1, characterized in that: It also includes a data storage module, the input of which is electrically connected to the output of the data preprocessing module, and the output of which is electrically connected to the input of the fault early warning module and the knowledge base module, respectively. The data storage module adopts a distributed database architecture to store raw monitoring data, preprocessed feature data, and system operation logs.

9. The integrated management system for wind turbine fault prevention and knowledge base according to claim 1, characterized in that: It also includes a remote communication module, which is electrically connected to the data acquisition module, the fault early warning module and the human-machine interaction module respectively; The remote communication module adopts 5G or industrial Ethernet communication protocols to realize the real-time transmission of on-site monitoring data to the remote monitoring center, as well as the parameter configuration and command issuance of the on-site system by the remote monitoring center.

10. The wind turbine fault prevention and knowledge base integrated management system according to claim 1, characterized in that: The fault early warning module also includes a self-learning unit, which is bidirectionally electrically connected to the knowledge base module and periodically iterates and optimizes the early warning model based on newly generated fault case data.

Images