Wind generating set operation control method and system based on data analysis

Abstract

The invention discloses a wind generating set operation control method and system based on data analysis, and the method comprises the steps: analyzing the historical environment monitoring data of an environment, determining the environment parameter data affecting the wind speed, extracting the features of the environment parameter data, building a prediction model based on the features and a preset model, and predicting to obtain the environment wind speed prediction data; determining a prediction power curve based on the environment wind speed prediction data, and determining a difference characteristic between the prediction power curve and a theoretical optimal power curve; evaluating a power curve difference state based on the difference characteristics to obtain a performance state evaluation value, and determining an optimization control coefficient matrix based on the performance state evaluation value; and optimizing operation parameters of the wind generating set based on the optimization control coefficient matrix, and then performing operation control. According to the method, the performance state of the wind generating set can be accurately determined, and the optimal control strategy is dynamically generated to adjust the operation parameters in real time, so that the wind energy capture efficiency is maximized, the power output is smoothed, and the service life is effectively prolonged on the premise of guaranteeing the safety of equipment.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of wind power generation, in particular to a wind turbine generator set operation control method and system based on data analysis. BACKGROUND

[0002] In the face of the urgent need for global energy transformation, wind energy, as an important part of clean and renewable energy, is crucial to its efficient development and utilization. However, the strong potential of wind power generation is constrained by the inherent intermittency, randomness and volatility of wind energy, posing great challenges to grid stability and wind turbine safety.

[0003] The operation control method of traditional wind turbine generators mainly relies on preset logic controllers based on physical models, which is essentially a "passive reaction" to the current environmental state. This method can cope with stable conditions, but it is difficult to adapt to complex and variable wind conditions, resulting in suboptimal wind energy capture efficiency, high mechanical load, and increased equipment wear and tear, which seriously affects the power generation benefit and economy of its entire life cycle. SUMMARY

[0004] To solve the above technical problems, the present application provides a wind turbine generator set operation control method and system based on data analysis, comprising: Obtain historical environmental monitoring data of the environment where the wind turbine generator set is located, and analyze the historical environmental monitoring data to determine the environmental parameter data affecting wind speed; Extract the features of the environmental parameter data, and construct an environmental wind speed prediction model based on the features and a preset neural network model to predict the environmental wind speed prediction data; Determine the predicted power curve of the wind turbine generator set based on the environmental wind speed prediction data, and determine the difference features between the predicted power curve and the theoretical optimal power curve; Evaluate the power curve difference state based on the difference features to obtain the performance state evaluation value of the wind turbine generator set, and determine the optimization control coefficient matrix based on the performance state evaluation value; Optimize the operating parameters of the wind turbine generator set based on the optimization control coefficient matrix, and control the operation of the wind turbine generator set according to the optimized operating parameters.

[0005] Further, the obtaining of the historical environmental monitoring data of the environment where the wind turbine generator set is located, and the analysis of the historical environmental monitoring data to determine the environmental parameter data affecting wind speed, comprises: Obtain historical environmental monitoring data of the environment where the wind turbine generator set is located, and preprocess the historical environmental monitoring data, which includes removing outliers, noise and missing values in the data, and standardizing the data; The pre-processed historical environmental monitoring data is divided according to the types of environmental parameters to obtain a plurality of environmental parameter data; The environmental wind speed data is determined from the environmental parameter data, and the correlation between each environmental parameter data and the environmental wind speed data is determined respectively; The environmental parameter corresponding to the environmental parameter data with a correlation greater than a preset threshold is determined as the environmental parameter data affecting the wind speed.

[0006] Further, the features of the environmental parameter data are extracted, and an environmental wind speed prediction model is constructed based on the features and a preset neural network model to perform prediction, to obtain environmental wind speed prediction data, including: The features of the environmental parameter data are extracted, and a data set is constructed based on the environmental parameter data and the corresponding features; The data set is input into a preset neural network model to construct an environmental wind speed prediction initial model; The data set is divided into a training set and a test set according to a preset ratio, and the training set and the test set are input into the environmental wind speed prediction initial model; The environmental wind speed prediction initial model is trained and tested until the environmental wind speed prediction initial model meets a preset convergence condition, to obtain an environmental wind speed prediction model; Real-time environmental monitoring data is obtained, and the real-time environmental monitoring data is input into the environmental wind speed prediction model to perform prediction, to obtain environmental wind speed prediction data in a future period of time.

[0007] Further, the predicted power curve of the wind turbine generator is determined based on the environmental wind speed prediction data, and the difference feature between the predicted power curve and the theoretical optimal power curve is determined, including: The predicted power of the wind turbine generator is obtained based on the environmental wind speed prediction data, and the predicted power curve of the wind turbine generator is constructed based on the environmental wind speed prediction data and the predicted power; The theoretical optimal power curve of the wind turbine generator is determined, and the predicted power curve and the theoretical optimal power curve are aligned and projected into the same coordinate system to obtain a power curve comparison graph; The power curve comparison graph is divided into a plurality of interval segments according to a preset wind speed interval, and the difference between the predicted power curve and the theoretical optimal power curve in each interval segment is analyzed to obtain the difference feature corresponding to each interval segment.

[0008] Further, the difference between the predicted power curve and the theoretical optimal power curve in each interval segment is analyzed to obtain the difference feature corresponding to each interval segment, including: The power sum value and the slope value of the predicted power curve and the theoretical optimal power curve in each interval segment are determined respectively, and the time length of each interval segment is determined; The power loss of each interval is calculated by the power sum value of the theoretical optimal power curve and the power sum value of the predicted power curve in each interval and the time length of each interval. The slope ratio of each interval is calculated by the slope value of the theoretical optimal power curve and the slope value of the predicted power curve in each interval. The power loss and the slope ratio of each interval are determined as the difference characteristics corresponding to each interval.

[0009] Further, the calculation formula of the power loss of each interval is: Z= (P t -P a ) *T, wherein Z is the power loss of each interval, P t is the power sum value of the theoretical optimal power curve in each interval, P a is the power sum value of the predicted power curve in each interval, and T is the time length of each interval.

[0010] Further, the performance state evaluation value of the wind turbine is obtained by evaluating the difference characteristics, including: The slope ratio of each interval is normalized to obtain the weight of each interval, and the power loss of each interval is evaluated to obtain the power loss evaluation value of each interval. The performance state evaluation value of the wind turbine is obtained by weighted addition calculation based on the power loss evaluation value of each interval and the corresponding weight.

[0011] Further, the optimization control coefficient matrix is determined based on the performance state evaluation value, including: The preset optimization control coefficient matrix-performance state evaluation value interval corresponding relationship is preset, and the preset optimization control coefficient matrix-performance state evaluation value interval corresponding relationship is associated with the corresponding preset optimization control coefficient matrix for each performance state evaluation value interval. The performance state evaluation value of the wind turbine is obtained, and the preset optimization control coefficient matrix corresponding to the performance state evaluation value interval is selected as the optimization control coefficient matrix of the wind turbine based on the mapping relationship of the performance state evaluation value interval in the preset optimization control coefficient matrix-performance state evaluation value interval corresponding relationship.

[0012] Further, the operation parameters of the wind turbine are optimized based on the optimization control coefficient matrix, and the wind turbine is controlled according to the optimized operation parameters, including: The initial operating parameters of the wind turbine generator are determined, and each operating parameter in the initial operating parameters of the wind turbine generator is optimized one by one based on the optimized control coefficient matrix to obtain the optimized operating parameters. The wind turbine generator is then controlled to operate based on the optimized operating parameters.

[0013] The present invention also provides a data analysis-based wind turbine generator operation control system, comprising: The acquisition module is used to acquire historical environmental monitoring data of the environment where the wind turbine is located, and to analyze the historical environmental monitoring data to determine the environmental parameters that affect wind speed. The prediction module is used to extract features from environmental parameter data and construct an environmental wind speed prediction model based on the features and a preset neural network model to make predictions and obtain environmental wind speed prediction data. The determination module is used to determine the predicted power curve of the wind turbine generator based on environmental wind speed prediction data, and to determine the difference characteristics between the predicted power curve and the theoretical optimal power curve. The evaluation module is used to evaluate the power curve difference status based on the difference characteristics, obtain the performance status evaluation value of the wind turbine generator, and determine the optimal control coefficient matrix based on the performance status evaluation value. The control module is used to optimize the operating parameters of the wind turbine generator set based on the optimized control coefficient matrix, and to control the operation of the wind turbine generator set according to the optimized operating parameters.

[0014] Compared with existing technologies, the wind turbine generator operation control method and system based on data analysis of this invention have the following advantages: This invention analyzes historical environmental monitoring data to accurately identify parameters affecting wind speed and establishes a high-precision wind speed prediction model based on neural networks. This enables wind turbines to anticipate future wind changes, achieving a leap from passive response to active prediction and providing forward-looking information for subsequent control strategies. This invention, by comparing the differences between the predicted power curve and the theoretical optimal power curve, and by evaluating based on these differences, can quantitatively determine the wind turbine status, achieving a refined perception of the wind turbine's performance status and providing data support for subsequent control. This invention transforms the state assessment results into an optimized control coefficient matrix and dynamically adjusts the operating parameters. This not only compensates for power generation losses caused by equipment performance degradation, but also optimizes control actions in advance based on predicted wind conditions. Under the premise of ensuring safety, it maximizes wind energy capture efficiency, smooths power output, and significantly reduces mechanical load, effectively extending the service life of the equipment. Attached Figure Description

[0015] Figure 1This is a schematic diagram of the flow structure of the wind turbine generator operation control method based on data analysis in an embodiment of the present invention; Figure 2 This is a schematic diagram of the composition of the wind turbine generator operation control system based on data analysis in an embodiment of the present invention. Detailed Implementation

[0016] The specific embodiments of this application will be described in further detail below with reference to the accompanying drawings and examples. The following examples are for illustrative purposes only and are not intended to limit the scope of the invention.

[0017] In the description of this application, it should be understood that the terms "center", "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", etc., indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings, and are only for the convenience of describing this application and simplifying the description, and do not indicate or imply that the platform or element referred to must have a specific orientation, or be constructed and operated in a specific orientation, and therefore should not be construed as a limitation of this application.

[0018] The terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Therefore, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature. In the description of this application, unless otherwise stated, "a plurality of" means two or more.

[0019] like Figure 1 As shown in the embodiments of this application, a wind turbine generator operation control method based on data analysis is provided, including: S100: acquiring historical environmental monitoring data of the environment where the wind turbine generator is located, and analyzing the historical environmental monitoring data to determine environmental parameter data affecting wind speed; S200: extracting features of the environmental parameter data, and constructing an environmental wind speed prediction model based on the features and a preset neural network model to predict the environmental wind speed, thereby obtaining environmental wind speed prediction data; S300: determining the predicted power curve of the wind turbine generator based on the environmental wind speed prediction data, and determining the difference features between the predicted power curve and the theoretical optimal power curve; S400: evaluating the power curve difference state based on the difference features to obtain the performance state evaluation value of the wind turbine generator, and determining the optimized control coefficient matrix based on the performance state evaluation value; S500: optimizing the operating parameters of the wind turbine generator based on the optimized control coefficient matrix, and controlling the operation of the wind turbine generator according to the optimized operating parameters.

[0020] Furthermore, this invention analyzes historical environmental monitoring data to accurately identify parameters affecting wind speed and establishes a high-precision wind speed prediction model based on neural networks. This enables wind turbines to anticipate future wind condition changes, achieving a leap from passive response to active prediction and providing forward-looking information for subsequent control strategies. By comparing the differences between the predicted power curve and the theoretical optimal power curve and evaluating these differences, this invention can quantitatively determine the wind turbine's state, achieving refined perception of its performance status and providing data support for subsequent control. This invention transforms the state evaluation results into an optimized control coefficient matrix and dynamically adjusts operating parameters. This not only compensates for power generation losses caused by equipment performance degradation but also optimizes control actions in advance based on predicted wind conditions. Under the premise of ensuring safety, it maximizes wind energy capture efficiency, smooths power output, significantly reduces mechanical load, and effectively extends equipment lifespan.

[0021] In the embodiments of this application, a wind turbine generator operation control method based on data analysis is provided. The step of acquiring historical environmental monitoring data of the environment where the wind turbine generator is located and analyzing the historical environmental monitoring data to determine environmental parameter data affecting wind speed includes: acquiring historical environmental monitoring data of the environment where the wind turbine generator is located, and preprocessing the historical environmental monitoring data, including removing outliers and noise from the data, filling in missing values ​​in the data, and standardizing the data; dividing the preprocessed historical environmental monitoring data according to environmental parameter types to obtain multiple environmental parameter data; determining environmental wind speed data from the environmental parameter data, and determining the correlation between each environmental parameter data and the environmental wind speed data; and determining the environmental parameters corresponding to the environmental parameter data with a correlation greater than a preset threshold as environmental parameter data affecting wind speed.

[0022] Specifically, comprehensive historical monitoring data of the environment where the wind turbine generators are located is acquired, including multi-dimensional environmental parameters such as temperature, air pressure, humidity, wind direction, and rainfall. Through refined preprocessing of this raw data, including outlier removal, noise filtering, missing value imputation, and data standardization, data quality is effectively improved, eliminating unreliable data points caused by sensor malfunctions, transmission interference, and other factors, laying a solid data foundation for subsequent analysis. After data preprocessing, the integrated environmental monitoring data is divided into multiple structured environmental parameter datasets according to parameter type. Correlation analysis algorithms (such as Pearson correlation coefficient and mutual information) are used to accurately calculate the correlation strength between each environmental parameter and wind speed data, quantitatively assessing the significance of different environmental factors' impact on wind speed. By setting scientifically reasonable correlation thresholds, key environmental parameters with significant statistical correlations to wind speed changes are selected. This step avoids the limitations of traditional wind speed prediction, which only considers a single historical wind speed sequence, and reveals the complex mechanism of wind speed formation more comprehensively through multi-parameter collaborative analysis. On the other hand, feature selection effectively reduces the data dimensionality and eliminates the interference of irrelevant parameters, providing the optimal input feature set for the subsequent construction of a high-precision wind speed prediction model. This significantly improves the accuracy and reliability of wind speed prediction and provides key data support for the predictive control and optimized operation of wind turbine generators.

[0023] In the embodiments of this application, a wind turbine generator operation control method based on data analysis is provided. The method involves extracting features from environmental parameter data and constructing an environmental wind speed prediction model based on these features and a preset neural network model to obtain environmental wind speed prediction data. The method includes: extracting features from environmental parameter data and constructing a dataset based on the environmental parameter data and corresponding features; inputting the dataset into a preset neural network model to construct an initial environmental wind speed prediction model; dividing the dataset into a training set and a test set according to a preset ratio and inputting the training set and test set into the initial environmental wind speed prediction model; training and testing the initial environmental wind speed prediction model until it meets a preset convergence condition to obtain an environmental wind speed prediction model; acquiring real-time environmental monitoring data and inputting the real-time environmental monitoring data into the environmental wind speed prediction model for prediction to obtain environmental wind speed prediction data for a future period.

[0024] Specifically, key features are extracted from the preprocessed multi-dimensional environmental parameters. These features include not only the instantaneous values ​​of the parameters themselves, but also predictive temporal features, such as average values ​​within a specific time window, trends, periodic patterns (e.g., diurnal temperature range), and lagged correlations with wind speed. These features together constitute the model's dataset, ensuring that the input information comprehensively reflects the dynamic processes of atmospheric motion. A pre-defined neural network structure is used to construct an initial model for environmental wind speed prediction. This neural network model, due to its powerful nonlinear fitting ability and advantage in capturing time-series dependencies, is specifically designed for learning complex environments. This study explores the deep, nonlinear mapping relationship between factors and wind speed. To train and validate the model, the dataset is divided into training and test sets chronologically to prevent future information leakage and ensure model generalization ability. The model is iteratively optimized using the training set and its predictive performance is evaluated using the test set. Once the model's prediction error reaches a preset convergence criterion, a usable environmental wind speed prediction model is obtained. During the model's practical application, the latest environmental monitoring data is acquired in real-time, processed using the same feature engineering methods, and then input into the trained wind speed prediction model to output high-precision environmental wind speed prediction data for a future period. This step significantly improves the accuracy of wind speed prediction by leveraging the ability of neural networks to handle complex nonlinear relationships and integrating multi-dimensional environmental features, overcoming the limitations of traditional physical models or single time-series models. It provides wind speed predictions for specific future time scales, laying a core data foundation for wind turbines to shift from a "passive response" to an "active look-ahead" control mode. This allows the control system to adjust its operating strategies in advance. Rigorous dataset partitioning and convergence testing ensure the model's stability and reliability when facing new data, enabling it to adapt to different climatic conditions and seasonal changes. In summary, this accurate wind speed forecast data provides crucial preliminary information for subsequent optimization of wind turbine control strategies, smoothing power output, reducing mechanical loads, and improving power generation efficiency.

[0025] In the embodiments of this application, a data analysis-based wind turbine generator operation control method is provided. The method for determining the predicted power curve of the wind turbine generator based on environmental wind speed prediction data and determining the difference characteristics between the predicted power curve and the theoretical optimal power curve includes: estimating the predicted power of the wind turbine generator based on environmental wind speed prediction data, and constructing the predicted power curve of the wind turbine generator based on the environmental wind speed prediction data and the predicted power; determining the theoretical optimal power curve of the wind turbine generator, aligning the predicted power curve with the theoretical optimal power curve, and projecting them onto the same coordinate system to obtain a power curve comparison chart; dividing the power curve comparison chart into multiple intervals according to a preset wind speed range, and analyzing the difference between the predicted power curve and the theoretical optimal power curve in each interval to obtain the difference characteristics corresponding to each interval.

[0026] Specifically, based on high-precision environmental wind speed prediction data, combined with the aerodynamic model and conversion efficiency characteristics of the wind turbine generator, the expected power generation corresponding to different wind speed points in the future is estimated, thereby drawing a complete predicted power curve. This predicted power curve is then aligned with the theoretical optimal power curve set at the time of the wind turbine's manufacture to ensure that both have the same scale and benchmark in the wind speed-power coordinate system, generating an intuitive power curve comparison chart. The entire wind speed range is divided into multiple continuous intervals according to preset rules. This step realizes the transformation of wind turbine performance evaluation from a general, extensive approach to a detailed, localized one, enabling precise location of the specific operating conditions where performance deviations occur.

[0027] In embodiments of this application, a data analysis-based wind turbine generator operation control method is provided. The method involves analyzing the difference between the predicted power curve and the theoretical optimal power curve in each interval segment to obtain the difference characteristics corresponding to each interval segment. This includes: determining the sum of power and slope of the predicted power curve and the theoretical optimal power curve in each interval segment, and determining the time length of each interval segment; calculating the power loss of each interval segment by combining the sum of power of the theoretical optimal power curve and the sum of power of the predicted power curve, along with the time length of each interval segment; calculating the ratio of the slope of the theoretical optimal power curve to the slope of the predicted power curve in each interval segment to obtain the slope ratio of each interval segment; and determining the power loss and slope ratio of each interval segment as the difference characteristics corresponding to each interval segment.

[0028] Specifically, for each defined wind speed interval, the sum of the predicted power curve and the theoretical optimal power curve within that interval is calculated. Simultaneously, the average slope of the two curves within that interval is calculated, and the total duration of that wind speed interval in actual operation is recorded. The sum of the theoretical optimal power and the predicted power for each interval is subtracted, and then multiplied by the duration of that interval to obtain the specific power generation loss value within that wind speed interval, quantifying the energy loss caused by performance deviations. The ratio of the slope of the theoretical optimal power curve to the slope of the predicted power curve is calculated to obtain the slope ratio characteristic. This ratio can sensitively reflect the change in wind energy capture efficiency of the wind turbine in different wind speed intervals; when the ratio is less than 1, it indicates a decrease in aerodynamic conversion efficiency. This step transforms the abstract curve differences into two quantitative features with clear physical meaning and economic value: power generation loss and slope ratio. The power generation loss feature directly assesses the severity of performance deviation from an economic perspective, providing a basis for prioritization in operation and maintenance decisions. The slope ratio feature, on the other hand, reveals the technical root cause of performance deviation from an aerodynamic efficiency perspective, effectively distinguishing different fault types such as blade contamination and wind misalignment. This dual-feature analysis method achieves a comprehensive and accurate diagnosis of wind turbine performance status, providing precise data support for the subsequent development of differentiated optimization control strategies, thereby achieving precise improvement in wind turbine operating efficiency and optimized allocation of operation and maintenance resources.

[0029] In an embodiment of this application, a wind turbine generator operation control method based on data analysis is provided, wherein the calculation formula for the power generation loss of each interval segment is: Z = (P) t -P a )*T, Where Z represents the power generation loss for each interval, and P represents the power generation loss for each interval. t P is the sum of the power values ​​of the theoretically optimal power curves in each interval. a The sum of the predicted power curves for each interval is given by T, where T is the time length of each interval.

[0030] In the embodiments of this application, a wind turbine generator operation control method based on data analysis is provided. The method for evaluating the power curve difference status based on difference characteristics to obtain the performance status evaluation value of the wind turbine generator includes: normalizing the slope ratio of each interval segment to obtain the weight of each interval segment, and evaluating the power generation loss of each interval segment to obtain the power generation loss evaluation value of each interval segment; and performing a weighted summation calculation based on the power generation loss evaluation value of each interval segment and the corresponding weight to obtain the performance status evaluation value of the wind turbine generator.

[0031] Specifically, the slope ratios calculated for each wind speed interval are normalized and converted into weighting coefficients between 0 and 1. This process ensures that intervals with more severe aerodynamic efficiency losses (smaller slope ratios) receive higher weights, highlighting the importance of critical problem areas. The power generation loss for each interval is standardized and evaluated, converting absolute losses into relative evaluation scores to eliminate the influence of dimensions. Based on the obtained weights and evaluation values, a weighted summation algorithm is used to multiply the power generation loss evaluation value for each interval by its corresponding weighting coefficient and then sum them to obtain a comprehensive performance status evaluation value. This value considers both the economic impact of power generation losses in different wind speed intervals and the technical severity of aerodynamic efficiency losses. This innovative step transforms the aerodynamic efficiency index (slope ratio) into a weighting coefficient, achieving an organic integration of technical and economic parameters. Through a weighted evaluation mechanism, it avoids the subtle problems in the high-efficiency range that may be ignored by simply relying on power generation losses, and also prevents the deviation of focusing only on aerodynamic efficiency while ignoring the actual operating frequency. The final performance status evaluation value is a comprehensive and highly comparable quantitative indicator that can accurately reflect the overall health status of the wind turbine, providing a scientific basis for operation and maintenance decisions. It achieves a leap from "qualitative analysis" to "quantitative evaluation," significantly improving the accuracy of wind turbine status assessment and the pertinence of operation and maintenance strategy formulation.

[0032] In an embodiment of this application, a wind turbine generator operation control method based on data analysis is provided. The step of determining the optimized control coefficient matrix based on performance status evaluation values ​​includes: pre-setting a preset correspondence between the optimized control coefficient matrix and performance status evaluation value intervals, wherein each performance status evaluation value interval is associated with a corresponding preset optimized control coefficient matrix; obtaining the performance status evaluation value of the wind turbine generator, and based on the mapping relationship between the performance status evaluation value interval to which the performance status evaluation value belongs and the preset optimized control coefficient matrix corresponding to the performance status evaluation value interval, selecting the preset optimized control coefficient matrix corresponding to the performance status evaluation value interval as the optimized control coefficient matrix of the wind turbine generator.

[0033] Specifically, a complete "performance status assessment value interval - optimized control coefficient matrix" correspondence table is pre-constructed. This correspondence is associated with optimized control coefficient matrices for different performance status assessment value intervals, which include the best combination of key control parameters such as pitch rate, torque gain, and yaw sensitivity. In actual application, the comprehensive performance status assessment value of the wind turbine generator is calculated and obtained in real time. The specific status interval to which the assessment value belongs is determined by the interval matching algorithm. Based on the preset mapping relationship, the optimized control coefficient matrix corresponding to the status interval is automatically retrieved and selected, and it is determined as the optimal set of control parameters to guide the operation of the wind turbine in the current stage. This step constructs a closed-loop bridge from performance diagnosis to control optimization, achieving precise matching between control strategies and equipment status. When the wind turbine performance status assessment value indicates that the equipment is in a healthy state, an aggressive control coefficient matrix is ​​automatically adopted to maximize wind energy capture efficiency. When the assessment value detects performance degradation, it switches to a conservative control matrix to prioritize equipment safety and lifespan. This adaptive optimization mechanism effectively solves the pain point that traditional fixed parameter control strategies cannot adapt to changes in equipment status. It not only ensures the optimal operating efficiency of the wind turbine under different health states, but also significantly improves operational safety and reliability, achieving the best balance between power generation revenue and equipment lifespan.

[0034] In the embodiments of this application, a wind turbine generator operation control method based on data analysis is provided. The method optimizes the operating parameters of the wind turbine generator based on an optimized control coefficient matrix and controls the operation of the wind turbine generator based on the optimized operating parameters. The method includes: determining the initial operating parameters of the wind turbine generator; optimizing each operating parameter in the initial operating parameters of the wind turbine generator based on the optimized control coefficient matrix to obtain optimized operating parameters; and controlling the wind turbine generator to operate based on the optimized operating parameters.

[0035] Specifically, the initial set of operating parameters for the wind turbine is obtained, including core operating setpoints such as pitch control parameters, torque control parameters, and yaw control parameters. Based on the optimized control coefficient matrix calculated in the early stage, each parameter in the initial operating parameters is optimized and adjusted one by one: for the pitch system, the pitch angle response curve and action rate are adjusted; for the power generation system, the torque-speed characteristic curve is optimized; for the yaw system, the yaw error tolerance and wind response strategy are corrected. These optimizations are not simple parameter replacements, but rather fine-grained parameter reconstruction and sensitivity calibration based on the adjustment direction and magnitude provided by the coefficient matrix, ultimately generating a set of optimized operating parameters that perfectly match the current performance state of the wind turbine. This step enables real-time adaptation of wind turbine control parameters to the actual equipment status, overcoming the limitations of traditional fixed-parameter control strategies. Through dynamic optimization based on performance status, it can maximize power generation efficiency by employing an aggressive control strategy when the wind turbine is performing well, and automatically switch to a conservative mode to prioritize equipment safety when performance deteriorates. This adaptive optimization not only improves wind energy capture efficiency, but more importantly, it effectively extends the service life of key components by reducing mechanical stress caused by improper control, achieving an optimal balance between power generation efficiency and equipment safety. This provides technical support for the intelligent operation and maintenance of wind turbine units and the maximization of their full life-cycle value.

[0036] like Figure 2 As shown in the embodiments of this application, a data analysis-based wind turbine generator operation control system is provided, comprising: an acquisition module for acquiring historical environmental monitoring data of the environment in which the wind turbine generator is located, analyzing the historical environmental monitoring data, and determining environmental parameter data affecting wind speed; a prediction module for extracting features from the environmental parameter data, constructing an environmental wind speed prediction model based on the features and a preset neural network model, and obtaining environmental wind speed prediction data; a determination module for determining the predicted power curve of the wind turbine generator based on the environmental wind speed prediction data, and determining the difference features between the predicted power curve and the theoretical optimal power curve; an evaluation module for evaluating the difference status of the power curve based on the difference features, obtaining a performance status evaluation value of the wind turbine generator, and determining an optimized control coefficient matrix based on the performance status evaluation value; and a control module for optimizing the operating parameters of the wind turbine generator based on the optimized control coefficient matrix, and controlling the operation of the wind turbine generator according to the optimized operating parameters.

[0037] In summary, this invention provides a data analysis-based wind turbine generator operation control method and system, comprising: analyzing historical environmental monitoring data to determine environmental parameter data affecting wind speed, extracting their features, and constructing a prediction model based on the features and a preset model to predict environmental wind speed data; determining a predicted power curve based on the environmental wind speed prediction data, and identifying the difference features between the predicted power curve and the theoretical optimal power curve; evaluating the power curve difference state based on the difference features to obtain a performance state evaluation value, and determining an optimized control coefficient matrix based on it; and optimizing the operating parameters of the wind turbine generator based on the optimized control coefficient matrix before performing operation control. This invention can accurately determine the performance state of the wind turbine generator and dynamically generate an optimal control strategy to adjust operating parameters in real time, thereby maximizing wind energy capture efficiency, smoothing power output, and effectively extending service life while ensuring equipment safety.

[0038] Finally, it should be noted that those skilled in the art can obviously make various modifications and variations to this invention without departing from its spirit and scope. Therefore, if these modifications and variations fall within the scope of the claims and their equivalents, this invention also intends to include these modifications and variations.

[0039] The above description is merely one embodiment of the present invention, and should not be construed as limiting the scope of the invention. Any structural changes made based on the present invention, as long as they do not depart from the essence of the invention, should be considered as falling within the protection scope of the present invention and subject to its restrictions. Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working process and related descriptions of the platform described above can be referred to the corresponding processes in the foregoing platform embodiments, and will not be repeated here.

[0040] The term "comprising" or any other similar term is intended to cover non-exclusive inclusion, such that a process, platform, article, or device / platform that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to those processes, platforms, articles, or devices / platforms.

[0041] The technical solutions of the present invention have been described in conjunction with the accompanying drawings and further embodiments. However, it will be readily understood by those skilled in the art that the scope of protection of the present invention is obviously not limited to these specific embodiments. Without departing from the principles of the present invention, those skilled in the art can make equivalent changes or substitutions to closely related technical features, and the technical solutions resulting from such changes or substitutions will all fall within the scope of protection of the present invention.

[0042] The above description is merely a preferred embodiment of the present invention and is not intended to limit the scope of protection of the present invention.

Claims

1. A wind turbine generator operation control method based on data analysis, characterized in that, include: Historical environmental monitoring data of the environment where the wind turbine is located is obtained and analyzed to determine the environmental parameters that affect wind speed. Features of environmental parameter data are extracted, and an environmental wind speed prediction model is constructed based on the features and a preset neural network model to make predictions and obtain environmental wind speed prediction data. The predicted power curve of the wind turbine generator is determined based on environmental wind speed prediction data, and the difference characteristics between the predicted power curve and the theoretical optimal power curve are determined. The power curve difference status is evaluated based on the difference characteristics to obtain the performance status evaluation value of the wind turbine generator set, and the optimal control coefficient matrix is ​​determined based on the performance status evaluation value. The operating parameters of the wind turbine generator are optimized based on the optimized control coefficient matrix, and the wind turbine generator is then controlled based on the optimized operating parameters.

2. A wind turbine generator operation control method based on data analysis as described in claim 1, characterized in that, The process of acquiring historical environmental monitoring data of the environment where the wind turbine is located, and analyzing the historical environmental monitoring data to determine environmental parameters affecting wind speed, includes: Historical environmental monitoring data of the environment where the wind turbine generator is located is acquired, and the historical environmental monitoring data is preprocessed. The preprocessing includes removing outliers and noise from the data, filling in missing values ​​in the data, and standardizing the data. The preprocessed historical environmental monitoring data is divided according to the type of environmental parameter to obtain multiple environmental parameter data. Determine the environmental wind speed data from the environmental parameter data, and determine the correlation between each environmental parameter data and the environmental wind speed data; Environmental parameters with a correlation greater than a preset threshold are identified as environmental parameters that affect wind speed.

3. A wind turbine generator operation control method based on data analysis as described in claim 2, characterized in that, The process of extracting features from environmental parameter data and constructing an environmental wind speed prediction model based on these features and a preset neural network model to obtain environmental wind speed prediction data includes: Extract features from environmental parameter data and construct a dataset based on the environmental parameter data and the corresponding features; Input the dataset into the preset neural network model to build an initial model for environmental wind speed prediction; The dataset is divided into training and testing sets according to a preset ratio, and the training and testing sets are input into the initial model for environmental wind speed prediction. The initial model for environmental wind speed prediction is trained and tested until it meets the preset convergence conditions, thus obtaining the environmental wind speed prediction model. Real-time environmental monitoring data is acquired and input into an environmental wind speed prediction model to obtain environmental wind speed prediction data for a future period of time.

4. A wind turbine generator operation control method based on data analysis as described in claim 3, characterized in that, The process of determining the predicted power curve of the wind turbine generator based on environmental wind speed prediction data, and identifying the difference characteristics between the predicted power curve and the theoretical optimal power curve, includes: The predicted power of the wind turbine is estimated based on the environmental wind speed prediction data, and the predicted power curve of the wind turbine is constructed based on the environmental wind speed prediction data and the predicted power. The theoretical optimal power curve of the wind turbine generator is determined, and the predicted power curve is aligned with the theoretical optimal power curve and projected onto the same coordinate system to obtain a power curve comparison chart. The power curve comparison chart is divided into multiple segments based on the preset wind speed range. The difference between the predicted power curve and the theoretical optimal power curve in each segment is analyzed to obtain the difference characteristics corresponding to each segment.

5. A wind turbine generator operation control method based on data analysis as described in claim 4, characterized in that, The analysis of the difference between the predicted power curve and the theoretical optimal power curve in each interval segment yields the difference characteristics corresponding to each interval segment, including: Determine the sum of power and slope of the predicted power curve and the theoretical optimal power curve in each interval, and determine the time length of each interval. The power generation loss for each interval is calculated by combining the sum of the theoretical optimal power curves and the sum of the predicted power curves in each interval with the time length of each interval. Calculate the ratio of the slope of the theoretical optimal power curve to the slope of the predicted power curve in each interval segment to obtain the slope ratio of each interval segment; The power generation loss and slope ratio of each interval are determined as the difference characteristics corresponding to each interval.

6. A wind turbine generator operation control method based on data analysis as described in claim 5, characterized in that, The formula for calculating the power generation loss in each interval segment is as follows: Z=(P t -P a )*T, Where Z represents the power generation loss for each interval, and P represents the power generation loss for each interval. t P is the sum of the power values ​​of the theoretically optimal power curves in each interval. a The sum of the predicted power curves for each interval is given by T, where T is the time length of each interval.

7. A wind turbine generator operation control method based on data analysis as described in claim 5, characterized in that, The evaluation of the power curve difference status based on the difference characteristics to obtain the performance status evaluation value of the wind turbine generator set includes: The slope ratio of each interval is normalized to obtain the weight of each interval, and the power generation loss of each interval is evaluated to obtain the power generation loss evaluation value of each interval. The performance status assessment value of the wind turbine generator is obtained by weighted summation of the power generation loss assessment value of each interval segment and the corresponding weight.

8. A wind turbine generator operation control method based on data analysis as described in claim 7, characterized in that, The determination of the optimized control coefficient matrix based on performance status evaluation values ​​includes: A pre-defined correspondence between the preset optimization control coefficient matrix and the performance status evaluation value interval is established. For each performance status evaluation value interval, a corresponding preset optimization control coefficient matrix is ​​associated with it. Obtain the performance status assessment value of the wind turbine generator set, and based on the mapping relationship between the performance status assessment value interval to which the performance status assessment value belongs and the corresponding relationship between the preset optimization control coefficient matrix and the performance status assessment value interval, select the preset optimization control coefficient matrix corresponding to the performance status assessment value interval as the optimization control coefficient matrix of the wind turbine generator set.

9. A wind turbine generator operation control method based on data analysis as described in claim 8, characterized in that, The optimization of the operating parameters of the wind turbine generator based on the optimized control coefficient matrix, and the operation control of the wind turbine generator based on the optimized operating parameters, includes: The initial operating parameters of the wind turbine generator are determined, and each operating parameter in the initial operating parameters of the wind turbine generator is optimized one by one based on the optimized control coefficient matrix to obtain the optimized operating parameters. The wind turbine generator is then controlled to operate based on the optimized operating parameters.

10. A wind turbine generator operation control system based on data analysis, characterized in that, include: The acquisition module is used to acquire historical environmental monitoring data of the environment where the wind turbine is located, and to analyze the historical environmental monitoring data to determine the environmental parameters that affect wind speed. The prediction module is used to extract features from environmental parameter data and construct an environmental wind speed prediction model based on the features and a preset neural network model to make predictions and obtain environmental wind speed prediction data. The determination module is used to determine the predicted power curve of the wind turbine generator based on environmental wind speed prediction data, and to determine the difference characteristics between the predicted power curve and the theoretical optimal power curve. The evaluation module is used to evaluate the power curve difference status based on the difference characteristics, obtain the performance status evaluation value of the wind turbine generator, and determine the optimal control coefficient matrix based on the performance status evaluation value. The control module is used to optimize the operating parameters of the wind turbine generator set based on the optimized control coefficient matrix, and to control the operation of the wind turbine generator set according to the optimized operating parameters.

Images