Intelligent monitoring system for blade state of wind generating set

Abstract

The invention discloses a wind generating set blade state intelligent monitoring system which comprises a plurality of sensors installed on a wind generating set blade, and the sensors are used for collecting stress, vibration and temperature data of the blade; the data processing module is used for receiving and processing data acquired by the sensor; the invention relates to the technical field of wind power generation. According to the method, the blade state can be monitored in real time, the fault features of the blade can be recognized in time, shutdown and maintenance cost caused by blade damage is reduced, the accuracy and timeliness of fault early warning can be effectively improved through fault prediction based on the artificial intelligence algorithm, and the fault early warning efficiency is improved through fault classification and early warning signals of different levels. According to the wind generating set remote monitoring system, workers can carry out maintenance in a more targeted mode, the overall maintenance cost is reduced, the remote monitoring platform can achieve unified monitoring and management on the multiple wind generating sets, and the overall operation efficiency is improved.

Description

Technical Field

[0001] The invention relates to the technical field of wind power generation, and in particular to an intelligent monitoring system for blade states of a wind generator set. Background Art

[0002] With the rapid development of wind power generation technology, wind turbines have been widely used around the world. As the core components, the operating conditions of wind turbine blades directly affect the power generation efficiency and the safety of the unit. Since wind turbine blades are exposed to harsh environments such as wind, rain, and snow for a long time, they are easily affected by external factors such as climate and wind, leading to problems such as wear, cracks, ice accumulation, and corrosion. If these problems cannot be monitored and warned in time, they may cause damage or even fall off of the blades, thus affecting the safe operation of the entire wind turbine.

[0003] Traditional blade monitoring methods usually rely on manual inspection or regular maintenance work, which has problems such as low detection efficiency, long cycle, and untimely fault warning. In addition, the blades of wind turbines are running at high altitudes, making manual inspection difficult and dangerous. Therefore, there is an urgent need for an intelligent system that can monitor the status of blades in real time and automatically issue fault warnings to improve the safety and operating efficiency of wind turbines. Summary of the invention

[0004] In view of the deficiencies in the prior art, the present invention provides an intelligent monitoring system for blade status of a wind turbine generator set, which solves the above-mentioned problems.

[0005] To achieve the above objectives, the present invention is implemented through the following technical solutions: A wind turbine blade status intelligent monitoring system, comprising:

[0006] A plurality of sensors installed on the blades of the wind turbine, wherein the sensors are used to collect stress, vibration and temperature data of the blades;

[0007] A data processing module, the data processing module is used to receive and process the data collected by the sensor;

[0008] An artificial intelligence analysis module, which analyzes the processed data based on a machine learning or deep learning algorithm to identify potential faults of the blades;

[0009] A real-time warning module, which is used to issue a fault warning signal when a potential fault is identified;

[0010] The remote monitoring platform is used to receive fault warning signals from the real-time warning module and display the status information of the blades.

[0011] Preferably, the sensor comprises a strain sensor, a vibration sensor and a temperature sensor, which are used to monitor the stress change, vibration frequency and temperature change of the blade respectively.

[0012] Preferably, the artificial intelligence analysis module includes:

[0013] A data preprocessing unit, which is used to perform denoising, normalization and outlier processing on the collected data;

[0014] A model training unit, the model training unit is used to train a machine learning model based on historical monitoring data to generate a normal operating state model of the blade;

[0015] A real-time monitoring unit, the real-time monitoring unit is used to analyze the real-time data, compare it with the normal operating state model, and identify potential fault characteristics;

[0016] The fault classification unit is used to classify the faults according to the type and severity of the faults.

[0017] Preferably, the artificial intelligence analysis module further includes a data feature extraction unit, which is used to extract feature data from the multi-dimensional data collected by the sensor, including stress features, vibration features and temperature features, as a basis for fault analysis.

[0018] Preferably, the model training unit adopts a machine learning algorithm, including but not limited to a support vector machine, a decision tree, a random forest or a deep learning algorithm, to generate a health status model of the blade by learning the historical operation data of the blade.

[0019] Preferably, the fault classification unit classifies the faults into minor faults, moderate faults and major faults based on the extracted fault features in combination with a preset fault classification model, and triggers warning signals of different levels respectively.

[0020] Preferably, the artificial intelligence analysis module can self-update and optimize the fault prediction model during system operation through an online learning algorithm to improve the accuracy of fault prediction.

[0021] Preferably, the real-time warning module can issue warning signals of different levels according to the severity of the fault.

[0022] Preferably, the remote monitoring platform includes a historical data storage module, which is used to store historical monitoring data of the blades and is available for staff to retrieve and analyze at any time.

[0023] Preferably, the system transmits data from the sensor to the data processing module and the remote monitoring platform via wireless communication.

[0024] Beneficial Effects

[0025] The present invention provides an intelligent monitoring system for blade status of a wind turbine generator set. Compared with the prior art, it has the following beneficial effects:

[0026] The present invention can realize real-time monitoring of blade status, can promptly identify blade fault characteristics, and reduce downtime and maintenance costs caused by blade damage. Fault prediction based on artificial intelligence algorithm can effectively improve the accuracy and timeliness of fault warning. Through fault classification and different levels of warning signals, staff can perform maintenance more targetedly and reduce overall maintenance costs. The remote monitoring platform can realize unified monitoring and management of multiple wind turbines and improve overall operating efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] Figure 1 It is the overall structural diagram of the present invention;

[0028] Figure 2 It is a structural block diagram of the sensor of the present invention;

[0029] Figure 3 It is a structural block diagram of the artificial intelligence analysis module of the present invention.

[0030] In the figure, 1. sensor; 11. strain sensor; 12. vibration sensor; 13. temperature sensor; 2. data processing module; 3. artificial intelligence analysis module; 31. data preprocessing unit; 32. model training unit; 33. real-time monitoring unit; 34. fault classification unit; 35. data feature extraction unit; 4. real-time warning module; 5. remote monitoring platform; 51. historical data storage module. DETAILED DESCRIPTION

[0031] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0032] Embodiment 1:

[0033] See also Figure 1-3 , wind turbine blade status intelligent monitoring system, including:

[0034] A plurality of sensors 1 installed on the blades of the wind turbine generator, the sensors 1 are used to collect stress, vibration and temperature data of the blades;

[0035] Data processing module 2, data processing module 2 is used to receive and process data collected by sensor 1;

[0036] Artificial intelligence analysis module 3, which analyzes the processed data based on machine learning or deep learning algorithms to identify potential faults of the blades;

[0037] The real-time warning module 4 is used to send out a fault warning signal when a potential fault is identified;

[0038] The remote monitoring platform 5 is used to receive the fault warning signal from the real-time warning module 4 and display the status information of the blade.

[0039] The sensor 1 comprises a strain sensor 11, a vibration sensor 12 and a temperature sensor 13, which are used to monitor the stress change, vibration frequency and temperature change of the blade respectively.

[0040] The remote monitoring platform 5 includes a historical data storage module 51, which is used to store the historical monitoring data of the blades and provide the staff with access and analysis at any time.

[0041] The system transmits data from the sensor 1 to the data processing module 2 and the remote monitoring platform 5 via wireless communication.

[0042] In this embodiment, the strain sensor 11 is arranged at the key stress point of the blade to monitor the stress change of the blade under wind load in real time. The data output by the strain sensor 11 can be used to analyze the stress condition of the blade and evaluate whether there is structural fatigue or other stress problems. The vibration sensor 12 is installed at the root and middle section of the blade to monitor the vibration frequency and vibration amplitude of the blade in real time. Abnormal vibration data may mean that the blade is damaged or unbalanced, and timely detection and maintenance are required. The temperature sensor 13 is used to monitor the temperature change of the blade, especially the overheating under high temperature conditions. Abnormal temperature usually means that the material performance is degraded or the environment is problematic. The data collected by the sensor 1 is sent to the data processing module 2 via wireless transmission. The wireless communication technology can use LoRa, Wi-Fi or cellular network. The sampling frequency of the sensor 1 can be adjusted according to the actual operation of the blade, and is usually set to collect data once per second to ensure the real-time nature of the data. The data processing module 2 performs preliminary processing on the data collected by the sensor 1. The processed data is stored in the local buffer and sent to the artificial intelligence analysis module 3 via wireless communication. During the processing, the data processing module 2 also has an adaptive adjustment function, which can dynamically adjust the sampling frequency and transmission rate according to different environmental conditions to save energy and communication bandwidth. The remote monitoring platform 5 is equipped with a historical data storage module 51 for storing historical monitoring data of the blades, including stress, vibration and temperature data. Through these historical data, the operation and maintenance personnel can track the long-term operation trend of the blades and analyze the performance of the blades under different climatic conditions. In addition, the historical data can also be used for continuous training and optimization of the artificial intelligence model to improve the accuracy of fault prediction. The remote monitoring platform 5 can display the operating status of the wind turbine in real time through the user interface, and automatically send out notifications when a fault occurs. The notification methods include email, SMS or mobile application push. The operation and maintenance personnel can quickly respond and take corresponding measures according to the level of the early warning signal. The remote monitoring platform 5 also supports the centralized management of multiple wind turbines, connects the intelligent monitoring system of each unit through the network, and provides a full range of operation monitoring. The operation and maintenance personnel can remotely diagnose blade problems, retrieve historical data for detailed analysis, and even remotely optimize the operating parameters of the wind turbine. The artificial intelligence analysis module 3 based on the online learning algorithm can self-update and optimize the fault prediction model during the system operation. When the system operates in different climatic environments or wind conditions, the fault prediction model will be dynamically adjusted to improve the model's adaptability to actual working conditions. In strong wind conditions, the stress and vibration characteristics of the blades may change significantly. Through online learning algorithms, the system can quickly adapt to these changes and avoid false alarms. At the same time, when the operating status of the blades deviates significantly from historical records, the system automatically triggers maintenance optimization suggestions.For example, the system may suggest that the operation and maintenance team adjust the rotation angle of the blades or change the operating strategy of the generator set to extend the service life of the blades and improve power generation efficiency.

[0043] Embodiment 2:

[0044] See also Figure 3 This embodiment provides a technical solution based on the first embodiment:

[0045] Artificial intelligence analysis module 3 includes:

[0046] The data preprocessing unit 31 is used to denoise, normalize and process outliers on the collected data; for example, when the wind is strong or the sensor is subject to external interference, spikes or noise signals may appear in the collected data. The unit removes the noise signal through a filtering algorithm (such as Kalman filtering or median filtering), thereby improving the accuracy of subsequent analysis.

[0047] Model training unit 32, model training unit 32 is used to train a machine learning model based on historical monitoring data to generate a normal operating state model of the blade; historical data is imported through the remote monitoring platform 5 or other data sources, and trained using a machine learning algorithm (such as a support vector machine, random forest or deep neural network). The trained model is stored in the system and used as a benchmark for real-time monitoring. The model can be updated adaptively to cope with changes in operating conditions caused by long-term operation of the wind turbine.

[0048] The real-time monitoring unit 33 is used to analyze the real-time data, compare it with the normal operating status model, and identify potential fault characteristics; when it is found that the stress, vibration or temperature data of the blade deviates from the normal range, the real-time monitoring unit 33 identifies the potential fault characteristics and passes the abnormal information to the fault classification unit 34.

[0049] The fault classification unit 34 is used to classify faults according to the type and severity of the faults. Combined with multi-dimensional sensor data, the system can determine the type of fault (such as cracks, fatigue damage, ice accumulation, etc.) and classify the faults into minor faults, moderate faults and major faults. The system triggers corresponding early warning signals according to different levels of faults. For example, in the case of minor faults, the system prompts the maintenance team to conduct regular inspections; in the case of serious faults, the system recommends stopping operation and performing emergency repairs.

[0050] The artificial intelligence analysis module 3 further includes a data feature extraction unit 35, which is used to extract feature data from the multi-dimensional data collected by the sensor 1, including stress features, vibration features and temperature features, as a basis for fault analysis.

[0051] The fault classification unit 34 classifies the faults into minor faults, moderate faults and major faults based on the extracted fault features and in combination with a preset fault classification model, and triggers warning signals of different levels respectively.

[0052] The artificial intelligence analysis module 3 can self-update and optimize the fault prediction model during system operation through online learning algorithms to improve the accuracy of fault prediction.

[0053] Meanwhile, the contents not described in detail in this specification belong to the prior art known to those skilled in the art.

[0054] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device.

[0055] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. The intelligent monitoring system for blade status of wind turbine generator set is characterized by: include: A plurality of sensors (1) mounted on the blades of a wind turbine, wherein the sensors (1) are used to collect stress, vibration and temperature data of the blades; A data processing module (2), the data processing module (2) being used to receive and process data collected by the sensor (1); An artificial intelligence analysis module (3), wherein the artificial intelligence analysis module (3) analyzes the processed data based on a machine learning or deep learning algorithm to identify potential faults of the blade; A real-time warning module (4), the real-time warning module (4) being used to issue a fault warning signal when a potential fault is identified; The remote monitoring platform (5) is used to receive the fault warning signal from the real-time warning module (4) and display the status information of the blade.

2. The wind turbine blade status intelligent monitoring system according to claim 1 is characterized in that: The sensor (1) comprises a strain sensor (11), a vibration sensor (12) and a temperature sensor (13), which are used to respectively monitor the stress change, vibration frequency and temperature change of the blade.

3. The wind turbine blade status intelligent monitoring system according to claim 1 is characterized in that: The artificial intelligence analysis module (3) comprises: A data preprocessing unit (31), the data preprocessing unit (31) is used to perform denoising, normalization and outlier processing on the collected data; A model training unit (32), the model training unit (32) being used to train a machine learning model based on historical monitoring data to generate a normal operating state model of the blade; A real-time monitoring unit (33), the real-time monitoring unit (33) is used to analyze the real-time data, compare it with the normal operating state model, and identify potential fault characteristics; A fault classification unit (34) is used to classify the fault according to the type and severity of the fault.

4. The wind turbine blade status intelligent monitoring system according to claim 3 is characterized in that: The artificial intelligence analysis module (3) further comprises a data feature extraction unit (35), wherein the data feature extraction unit (35) is used to extract feature data from the multi-dimensional data collected by the sensor (1), including stress features, vibration features and temperature features, as a basis for fault analysis.

5. The wind turbine blade status intelligent monitoring system according to claim 3 is characterized by: The model training unit (32) uses a machine learning algorithm, including but not limited to a support vector machine, a decision tree, a random forest or a deep learning algorithm, to generate a health status model of the blade by learning the historical operation data of the blade.

6. The wind turbine blade status intelligent monitoring system according to claim 3 is characterized by: The fault classification unit (34) classifies the faults into minor faults, moderate faults and major faults based on the extracted fault features and in combination with a preset fault classification model, and triggers warning signals of different levels respectively.

7. The wind turbine blade status intelligent monitoring system according to claim 1 is characterized in that: The artificial intelligence analysis module (3) can self-update and optimize the fault prediction model during system operation through an online learning algorithm to improve the accuracy of fault prediction.

8. The wind turbine blade status intelligent monitoring system according to claim 1 is characterized by: The real-time warning module (4) can issue warning signals of different levels according to the severity of the fault.

9. The wind turbine blade status intelligent monitoring system according to claim 1, characterized in that: The remote monitoring platform (5) comprises a historical data storage module (51), which is used to store historical monitoring data of the blades for staff to retrieve and analyze at any time.

10. The wind turbine blade status intelligent monitoring system according to claim 1, characterized in that: The system transmits data from a sensor (1) to a data processing module (2) and a remote monitoring platform (5) by wireless communication.

Images