Self-adaptive optimization method for fan control strategy

Abstract

The invention discloses a self-adaptive optimization method for a fan control strategy. The method comprises the following steps: acquiring real-time data of a fan, health state data of equipment in the fan and meteorological data around the fan; performing data preprocessing and fusion on the acquired real-time data, the equipment health state data and the meteorological data to generate processed data; based on the processing data, constructing a deep neural network model, and correcting a power curve of the traditional fan according to the real-time working condition through the constructed deep neural network model; adjusting control parameters of the fan according to the corrected power curve by using a particle swarm optimization algorithm; through a machine learning algorithm, real-time analysis is carried out on the operation data of the fan, and early warning is carried out on potential faults; according to the actual operation effect and the potential fault early warning information of the draught fan, the feedback mechanism is combined, the draught fan control strategy is optimized, the draught fan control strategy can be accurately and dynamically adjusted, and it is ensured that the draught fan is always kept in the optimal working state.

Description

Technical Field

[0001] The invention belongs to the technical field of fan control, and in particular relates to a self-adaptive optimization method for a fan control strategy. Background Art

[0002] As a renewable energy source, wind power has been widely used around the world in recent years due to its environmental friendliness and extensive resources. The core equipment of the wind power generation system, the wind turbine (fan), is usually composed of a wind wheel, a generator, a control system and a monitoring system. The main function of a fan is to convert wind energy into electrical energy. However, the randomness and instability of wind energy make the operating efficiency and power generation capacity of the fan easily affected by many factors. In order to improve the power generation efficiency of the fan, the optimization of the control strategy and the fault warning mechanism become crucial.

[0003] At present, the control strategy of wind turbines usually relies on a predetermined power curve, which is predicted by a relationship model with parameters such as wind speed and rotation speed. However, the traditional power curve correction method is too simple and often cannot accurately reflect the actual performance of the wind turbine under complex working conditions. For example, meteorological conditions (such as wind speed, temperature, humidity) and the operating status of the wind turbine itself (such as rotation speed, blade angle, equipment aging, etc.) will have a great impact on the power curve during actual operation. Existing control strategies often cannot achieve real-time adaptive adjustment, resulting in the failure to fully utilize the power generation efficiency.

[0004] The current wind turbine control systems and optimization methods have the following limitations: First, the traditional wind turbine control algorithm cannot correct the power curve in real time, resulting in inefficient operation of the wind turbine under certain conditions. Second, the existing wind turbine control strategies mostly rely on static parameters and simple rules, lacking consideration of complex environmental factors and equipment health status. Finally, the existing fault diagnosis methods are mostly based on empirical rule judgments, which cannot achieve efficient and intelligent early warning and fault diagnosis. Summary of the invention

[0005] The present invention provides an adaptive optimization method for a fan control strategy, which is used to solve the technical defects of the existing fan control strategy, such as the inability to adapt to real-time changing working conditions and environmental conditions, inaccurate power curve correction and insufficient fan fault diagnosis capability.

[0006] In order to achieve the above object, the present invention adopts the following technical solutions: An adaptive optimization method for a fan control strategy, comprising: Obtain real-time data of the wind turbine, health status data of the equipment in the wind turbine, and meteorological data around the wind turbine; Preprocessing and fusing the acquired real-time data, equipment health status data and meteorological data to generate processed data; Based on the processed data, a deep neural network model is constructed, and the power curve of the traditional wind turbine is corrected according to the real-time working conditions through the constructed deep neural network model; Using a particle swarm optimization algorithm, according to the modified traditional wind turbine power curve, the control parameters of the wind turbine are adjusted; Through machine learning algorithms, the operating data of the wind turbine is analyzed in real time to provide early warning of potential failures; According to the actual operation effect of the fan and the potential fault warning information, the fan control strategy is optimized in combination with the feedback mechanism.

[0007] Furthermore, the acquisition of real-time data of the wind turbine, health status data of equipment in the wind turbine, and meteorological data around the wind turbine specifically includes: Use the wind turbine SCADA system to obtain wind turbine speed and blade angle data; Use a meteorological monitoring system to obtain temperature and humidity data around the fan; Use the equipment health monitoring system to obtain vibration and temperature data of the equipment in the fan.

[0008] Furthermore, the acquired real-time data, equipment health status data and meteorological data are preprocessed and integrated to generate processed data, specifically including: The acquired real-time data, equipment health status data and meteorological data are denoised, and a weighted fusion algorithm is used to integrate the real-time data, equipment health status data and meteorological data.

[0009] Furthermore, based on the processed data, a deep neural network model is constructed, and the power curve of the traditional wind turbine is corrected according to the real-time working conditions through the constructed deep neural network model, which specifically includes: Based on the processed data, a deep neural network model is constructed, the speed of the fan, the temperature around the fan, the humidity around the fan, and the state of the fan are used as input conditions, and the power curve of the traditional fan is corrected according to the real-time working conditions; The corrected power curve includes the rotation speed of the fan, the air temperature around the fan, the humidity around the fan and the fan status curve.

[0010] Furthermore, the particle swarm optimization algorithm is used to adjust the control parameters of the wind turbine according to the corrected power curve, specifically including: By using a particle swarm optimization algorithm, the speed of the fan and the blade angle control parameters of the fan are adjusted according to the corrected power curve, so that the fan can maintain an optimal operating state under various working conditions.

[0011] Furthermore, the operation data of the wind turbine is analyzed in real time through a machine learning algorithm to warn of potential failures, including: Analyze the vibration, temperature and pressure status data of the fan, identify the potential failure type of the fan, and issue an early warning signal.

[0012] Furthermore, according to the actual operation effect of the fan and the potential fault warning information, combined with the feedback mechanism, the fan control strategy is optimized, specifically including: By using the feedback mechanism, the fan control strategy is adjusted and optimized based on the actual operation effect of the fan and the fault warning information.

[0013] Compared with the prior art, the present invention has the following beneficial effects: 1. By combining the deep learning model with the particle swarm optimization algorithm, the fan control strategy can be dynamically adjusted according to real-time wind speed, rotation speed, temperature and other parameters to ensure that the fan always maintains the optimal working state. At the same time, through real-time analysis, intelligent diagnosis and early warning of fan failures are achieved, potential problems are identified in advance and early warnings are issued, thereby reducing the risk of failures and reducing operation and maintenance costs. In addition, through the feedback mechanism, the fan control strategy can be continuously optimized during operation to ensure long-term stable and efficient operation.

[0014] 2. The speed and blade angle are key parameters for the operation of the fan, which directly affect the power generation efficiency and stability of the fan. By obtaining these data in real time through the SCADA system, the operating status of the fan can be accurately grasped, providing an accurate basis for the subsequent optimization of the control strategy; secondly, the temperature and humidity are important factors affecting the performance and life of the fan. By obtaining these data through the meteorological monitoring system, the changes in the operating environment of the fan can be evaluated, providing a basis for adjusting the control strategy to adapt to different environmental conditions. Vibration and temperature are important indicators of the health status of the equipment. By obtaining these data in real time through the equipment health monitoring system, abnormal vibration and overheating of the equipment can be discovered in time, providing a reliable basis for fault warning.

[0015] 3. Real-time data, equipment health status data and meteorological data may be interfered by various noises during the collection process. De-noising can effectively eliminate or reduce these noises and improve the accuracy and reliability of data. Through weighted fusion algorithms, these multi-source information can be integrated to generate more comprehensive and accurate processing data.

[0016] 4. By correcting the power curve, the wind turbine can operate in a more optimal state under different working conditions, thereby improving power generation efficiency and avoiding the decrease in power generation efficiency due to power curve mismatch.

[0017] 5. By optimizing the control parameters through the PSO algorithm, the wind turbine can maintain the optimal operating state under various operating conditions, thereby improving the power generation efficiency.

[0018] 6. Through machine learning algorithms, real-time analysis of wind turbine operation data can be performed to provide early warning before a fault occurs, helping maintenance personnel to take timely measures to intervene and repair, and avoid serious losses caused by the expansion of the fault. At the same time, the early warning signal can guide maintenance personnel to quickly locate the fault point, reduce troubleshooting time, improve maintenance efficiency, and reduce maintenance costs. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for use in the embodiments are briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present invention and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without creative work.

[0020] Figure 1 A flow chart of the adaptive optimization method of the fan control strategy provided by the present invention; Figure 2 Schematic diagram of the adaptive optimization system of the fan control strategy provided by the present invention. DETAILED DESCRIPTION

[0021] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Generally, the components of the embodiments of the present invention described and shown in the drawings here can be arranged and designed in various different configurations.

[0022] Therefore, the following detailed description of the embodiments of the present invention provided in the accompanying drawings is not intended to limit the scope of the invention claimed for protection, but merely represents selected embodiments of the present invention. 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.

[0023] It should be noted that similar reference numerals and letters denote similar items in the following drawings, and therefore, once an item is defined in one drawing, further definition and explanation thereof is not required in subsequent drawings.

[0024] As a renewable energy source, wind power has been widely used around the world in recent years due to its environmental friendliness and extensive resources. The core equipment of the wind power generation system, the wind turbine (fan), is usually composed of a wind wheel, a generator, a control system and a monitoring system. The main function of a fan is to convert wind energy into electrical energy. However, the randomness and instability of wind energy make the operating efficiency and power generation capacity of the fan easily affected by many factors. In order to improve the power generation efficiency of the fan, the optimization of the control strategy and the fault warning mechanism become crucial.

[0025] At present, the control strategy of wind turbines usually relies on a predetermined power curve, which is predicted by a relationship model with parameters such as wind speed and rotation speed. However, the traditional power curve correction method is too simple and often cannot accurately reflect the actual performance of the wind turbine under complex working conditions. For example, meteorological conditions (such as wind speed, temperature, humidity) and the operating status of the wind turbine itself (such as rotation speed, blade angle, equipment aging, etc.) will have a great impact on the power curve during actual operation. Existing control strategies often cannot achieve real-time adaptive adjustment, resulting in the failure to fully utilize the power generation efficiency.

[0026] The current wind turbine control systems and optimization methods have the following limitations: First, the traditional wind turbine control algorithm cannot correct the power curve in real time, resulting in inefficient operation of the wind turbine under certain conditions. Second, the existing wind turbine control strategies mostly rely on static parameters and simple rules, lacking consideration of complex environmental factors and equipment health status. Finally, the existing fault diagnosis methods are mostly based on empirical rule judgments, which cannot achieve efficient and intelligent early warning and fault diagnosis.

[0027] In order to solve the above technical defects, the inventor provides an adaptive optimization method for fan control strategy.

[0028] The embodiment of the present invention provides an adaptive optimization method for a fan control strategy, such as Figure 1 As shown, including: S101, obtain the real-time data of the fan, the health status data of the equipment in the fan and the meteorological data around the fan; illustratively, use the fan SCADA system to obtain the rotation speed and blade angle data of the fan; use the meteorological monitoring system to obtain the temperature and humidity data around the fan; use the equipment health monitoring system to obtain the vibration and temperature data of the equipment in the fan; after obtaining these data, transmit them to the data processing module for further processing.

[0029] S102, preprocess and fuse the acquired real-time data, equipment health status data and meteorological data to generate processed data; illustratively, firstly perform denoising on the acquired real-time data, equipment health status data and meteorological data, and then standardize the data from different data sources to ensure the uniformity and consistency of the data. In the data fusion stage, the real-time data of the wind turbine (SCADA system), the data of the meteorological monitoring system and the equipment health monitoring system are synthesized through a weighted fusion algorithm to provide support for subsequent analysis and modeling, and the fused data will enter the power curve correction stage.

[0030] S103. Based on the processed data, a deep neural network model is constructed, and the power curve of the traditional fan is corrected according to the real-time working conditions through the constructed deep neural network model; illustratively, the traditional fan power curve only depends on the relationship between wind speed and rotation speed, ignoring the influence of environmental factors and equipment health status. In order to improve the accuracy of the power curve, a deep neural network model is constructed based on the processed data. The model not only considers traditional factors such as wind speed and rotation speed, but also takes into account factors such as air temperature, humidity, and fan status, and automatically learns the operation mode of the fan through data training. Specifically, the speed of the fan, the air temperature around the fan, the humidity around the fan, and the fan status are used as input conditions, and the power curve of the traditional fan is corrected according to the real-time working conditions; wherein the corrected power curve includes the speed of the fan, the air temperature around the fan, the humidity around the fan, and the fan status curve. During the correction process, the power curve is dynamically adjusted to better reflect the power generation capacity of the fan under different working conditions. The corrected power curve is expressed as:

[0031] in, is the corrected wind turbine power generation; is the wind speed; is the temperature; for humidity; is the fan speed; is the blade angle. The deep learning model can be continuously optimized through training data and automatically adjust the power curve of the wind turbine according to real-time working conditions in actual applications.

[0032] S104. Using a particle swarm optimization algorithm, adjust the control parameters of the fan according to the modified traditional wind turbine power curve; illustratively, after the power curve is modified, the control strategy of the fan needs to be dynamically adjusted according to the modified power curve to maximize the power generation efficiency of the fan. To this end, using a particle swarm optimization algorithm, according to the modified power curve, adjust the fan speed and the fan blade angle control parameters so that the fan maintains the optimal operating state under various operating conditions. By simulating the movement process of the particle group in the solution space, the optimal solution is gradually approached. In this process, the particle swarm optimization algorithm adjusts the fan speed, blade angle and other control parameters so that the actual power generation power of the fan is as close as possible to the modified target power. The objective function of the particle swarm optimization algorithm is expressed as:

[0033] in, For the The actual fan output power at the moment, is the corrected target power, is the number of data points. The particle swarm optimization algorithm can efficiently find the optimal control parameters by adjusting the position of particles in the solution space, so that the wind turbine always maintains the optimal working state under various working conditions, thereby improving the overall power generation efficiency.

[0034] S105. Through machine learning algorithms, the operating data of the fan is analyzed in real time to warn of potential faults. For example, during the operation of the fan, early diagnosis of faults is crucial to avoid long-term downtime and reduce maintenance costs. To this end, a machine learning method is used to diagnose fan faults, analyze the vibration, temperature and pressure status data of the fan, identify the potential fault types of the fan, and combine algorithms such as support vector machines (SVM) or random forests (RF) to analyze the operating status of the fan in real time. When the system detects abnormal data or potential fault signals, it will issue a warning in advance. The decision function of fault judgment is expressed as:

[0035] in, It is the fault judgment result, indicating whether there is a fault in the fan; is the kernel function, representing the sample With training samples similarity; is the weight of the support vector; is the bias term.

[0036] Through machine learning algorithms, the system can quickly identify potential failure modes of wind turbines and issue early warnings to avoid serious failures of wind turbines.

[0037] S106. Optimize the fan control strategy based on the actual operation effect of the fan and the potential fault warning information, combined with the feedback mechanism. Exemplarily, the feedback mechanism is used to adjust the fan control strategy based on the actual operation effect of the fan and the fault warning information, and optimize the fan control strategy. Specifically, all fan control operations and fault diagnosis results will be returned to the optimization module of the system through the feedback control module. Adaptive adjustments are made based on the feedback information to further optimize the control strategy. The function of the feedback control module is to adjust the control strategy based on the actual operating status of the fan and the fault warning information to ensure that the fan always operates in the best state. The feedback mechanism enables the system to continuously adjust the control strategy in actual operation to adapt to different operating conditions and environmental conditions.

[0038] Through the above steps, the present invention can realize adaptive optimization of wind turbine control strategy under different wind conditions, meteorological conditions and equipment health conditions. The core innovation of this method is to dynamically correct the power curve of the wind turbine through the combination of deep learning and particle swarm optimization algorithm, and improve the power generation efficiency and reliability of the wind turbine by adjusting the control parameters in real time.

[0039] In summary, the present invention realizes adaptive optimization of wind turbine control strategy by comprehensively using advanced technologies such as deep learning, particle swarm optimization, and machine learning. This method can correct the wind turbine power curve in real time, dynamically optimize the wind turbine control strategy, and perform intelligent fault diagnosis and early warning for the wind turbine. Through this series of technical means, the power generation efficiency of the wind turbine is significantly improved, the probability of failure is reduced, and a more efficient and reliable intelligent operation and maintenance solution is provided for the wind power generation industry.

[0040] The embodiment of the present invention also provides a knowledge base construction system for intelligent early warning of fan failure, such as Figure 2 As shown, including: A data acquisition module is used to obtain real-time data of the wind turbine, health status data of the equipment in the wind turbine, and meteorological data around the wind turbine; A data processing module is used to pre-process the real-time data of the wind turbine, the health status data of the equipment in the wind turbine, and the meteorological data around the wind turbine; Data fusion module, used to fuse wind turbine real-time data, equipment health status data in the wind turbine, and meteorological data around the wind turbine; Model building module, used to build deep neural network models; Correction module, used to correct the power curve of traditional wind turbines; An adjustment module, used to adjust the control parameters of the fan; Early warning module, used to warn of potential failures of the fan; Optimization module, used to optimize the fan control strategy.

[0041] Among them, the data acquisition module can be a data acquisition node, which is responsible for obtaining multi-dimensional operation data from the SCADA system, meteorological monitoring system and equipment health monitoring system of the wind turbine. Specifically, the SCADA system provides real-time operation data of the wind turbine, including speed, blade angle and power generation; the meteorological system collects environmental data such as temperature, humidity and wind speed; the equipment health monitoring system provides operation status data such as vibration, temperature and pressure inside the wind turbine. All collected data are pre-processed through standardization and denoising modules to eliminate data noise. The data processing module receives raw data from different data sources and fuses and processes the data. The data fusion module uses data fusion technology, combines external environmental factors such as wind speed, temperature and humidity with the internal operation data of the wind turbine, and uses a deep learning model to integrate multi-dimensional data to obtain more accurate wind turbine power curve correction and control parameters. The core function of the model building module, the deep neural network model constructed after data processing, is to correct and predict the wind turbine power curve. Through the training of historical data, the model can automatically learn the operation mode of the wind turbine and its response to different environments and working conditions, so as to realize the dynamic correction of the wind turbine power curve. During the correction process, the deep neural network (DNN) can consider a variety of factors, including wind speed, rotation speed, temperature, humidity, wind turbine status, etc., to ensure that the control strategy has high precision. The correction module, that is, the particle swarm optimization module, uses the particle swarm optimization algorithm (PSO) to dynamically adjust the control strategy of the wind turbine according to the power curve corrected by the deep learning model. The particle swarm optimization algorithm can continuously optimize the control parameters according to real-time data during the operation of the wind turbine to ensure that the wind turbine always operates in the optimal working state. This module is responsible for optimizing the key control parameters such as the speed and blade angle of the wind turbine to improve the power generation efficiency and reduce the risk of failure. The adjustment module adjusts the operating parameters of the wind turbine according to the control strategy output by the particle swarm optimization module. The control system can control the speed, blade angle and other important control variables of the fan in real time, so that the fan can adapt to different meteorological conditions and working conditions and always maintain the optimal operating state. The early warning module uses machine learning and pattern recognition technology to analyze the operating status of the fan in real time and identify potential fault signals. Based on the temperature, vibration, pressure and other data of the fan, combined with historical fault data, this module predicts faults through support vector machine (SVM) or random forest (RF) algorithm, and issues fault warnings in advance. This early warning mechanism can help operation and maintenance personnel intervene before the fan fails, reducing downtime and maintenance costs. The optimization module monitors the operating status of the fan in real time and feeds back the control effect to the system for further optimization of the control strategy. This module ensures the adaptability and continuous optimization of the system, so that the fan can dynamically adjust the control parameters according to real-time data under different working conditions and always maintain the best operating efficiency.

[0042] In summary, the system architecture of the present invention realizes adaptive optimization of wind turbine control strategy by combining a variety of advanced technical means, such as deep learning, particle swarm optimization algorithm and machine learning. By real-time monitoring and analysis of wind turbine operation data, environmental data and equipment health data, the system can dynamically adjust the control strategy, correct the power curve and perform fault diagnosis and early warning, thereby significantly improving the power generation efficiency and reliability of the wind turbine, providing strong technical support for the wind power industry.

[0043] An embodiment of the present invention further provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable in the processor, wherein the processor implements the steps of the adaptive optimization method of the wind turbine control strategy as described above when executing the computer program.

[0044] An embodiment of the present invention further provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the adaptive optimization method of the wind turbine control strategy as described above is implemented.

[0045] The above embodiments are preferred implementation modes of the present invention, but the implementation modes of the present invention are not limited to the above embodiments. Any other changes, modifications, substitutions, combinations, and simplifications that do not deviate from the spirit and principles of the present invention should be equivalent replacement methods and are included in the protection scope of the present invention.

[0046] It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0047] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0048] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0049] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process in the computer or other programmable device. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0050] The above are only preferred embodiments of the present invention and are not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. An adaptive optimization method for a fan control strategy, characterized in that: include: Obtain real-time data of the wind turbine, health status data of the equipment in the wind turbine, and meteorological data around the wind turbine; Preprocessing and fusing the acquired real-time data, equipment health status data and meteorological data to generate processed data; Based on the processed data, a deep neural network model is constructed, and the power curve of the traditional wind turbine is corrected according to the real-time working conditions through the constructed deep neural network model; Using a particle swarm optimization algorithm, according to the modified traditional wind turbine power curve, the control parameters of the wind turbine are adjusted; Through machine learning algorithms, the operating data of the wind turbine is analyzed in real time to provide early warning of potential failures; According to the actual operation effect of the fan and the potential fault warning information, the fan control strategy is optimized in combination with the feedback mechanism.

2. The adaptive optimization method of wind turbine control strategy according to claim 1, characterized in that: The real-time data of the wind turbine, the health status data of the equipment in the wind turbine, and the meteorological data around the wind turbine are obtained, specifically including: Use the wind turbine SCADA system to obtain wind turbine speed and blade angle data; Use a meteorological monitoring system to obtain temperature and humidity data around the fan; Use the equipment health monitoring system to obtain vibration and temperature data of the equipment in the fan.

3. The adaptive optimization method of wind turbine control strategy according to claim 1, characterized in that: The acquired real-time data, equipment health status data and meteorological data are preprocessed and integrated to generate processed data, specifically including: The acquired real-time data, equipment health status data and meteorological data are denoised, and a weighted fusion algorithm is used to integrate the real-time data, equipment health status data and meteorological data.

4. The adaptive optimization method of wind turbine control strategy according to claim 1, characterized in that: The method of constructing a deep neural network model based on the processed data and correcting the power curve of the traditional wind turbine according to the real-time working conditions through the constructed deep neural network model specifically includes: Based on the processed data, a deep neural network model is constructed, the speed of the fan, the temperature around the fan, the humidity around the fan, and the state of the fan are used as input conditions, and the power curve of the traditional fan is corrected according to the real-time working conditions; The corrected power curve includes the rotation speed of the fan, the air temperature around the fan, the humidity around the fan and the fan status curve.

5. The adaptive optimization method of wind turbine control strategy according to claim 1, characterized in that: The use of the particle swarm optimization algorithm to adjust the control parameters of the fan according to the corrected power curve specifically includes: By using a particle swarm optimization algorithm, the speed of the fan and the blade angle control parameters of the fan are adjusted according to the corrected power curve, so that the fan can maintain an optimal operating state under various working conditions.

6. The adaptive optimization method for wind turbine control strategy according to claim 1, characterized in that: Through machine learning algorithms, the operating data of the wind turbine is analyzed in real time to warn of potential failures, including: Analyze the vibration, temperature and pressure status data of the fan, identify the potential failure type of the fan, and issue an early warning signal.

7. The adaptive optimization method for fan control strategy according to claim 1, characterized in that: According to the actual operation effect of the fan and the potential fault warning information, combined with the feedback mechanism, the fan control strategy is optimized, including: By using the feedback mechanism, the fan control strategy is adjusted and optimized based on the actual operation effect of the fan and the fault warning information.

Images