Real-time correction method for fan power curve

Abstract

The invention belongs to the technical field of wind power generation, and discloses a fan power curve real-time correction method and equipment, and the method comprises the steps: collecting the data and equipment state of a wind generating set; calculating air density and turbulence intensity according to the collected data; a neural network algorithm is adopted, and the wind speed, the equipment state, the air density and the turbulence intensity serve as input layers of a neural network; outputting correction coefficients of the equipment state, the air density and the turbulence intensity; and multiplying the original power curve by the correction coefficient, and outputting a corrected power curve. The method can adapt to different environmental conditions and equipment states, various correction coefficients are calculated in real time, and the corrected power curve is closer to the actual operation working condition.

Description

Technical Field

[0001] The invention belongs to the technical field of wind power generation, and in particular relates to a real-time correction method and device for a wind turbine power curve. Background Art

[0002] Wind power generation is an important part of clean energy, among which the power curve of wind turbines is a key feature to characterize the power generation performance of wind turbines. The power curve describes the output power of wind turbines under different wind speed conditions, and is an important basis for evaluating the power generation efficiency of wind turbines, predicting power generation, and optimizing operation control. The power curve under standard operating conditions is usually obtained through theoretical calculations or experimental measurements during the design and manufacturing stages of wind turbines. At present, a fixed standard power curve is generally used in wind farm operations to evaluate wind turbine performance. However, during the actual operation of wind turbines, their power generation performance will be affected by many factors such as changes in air density, fluctuations in turbulence intensity, wind shear effects, and the state of the equipment itself. These factors lead to significant deviations between the power output in actual operation and the standard power curve, making it impossible for the performance evaluation results based on the standard power curve to accurately reflect the actual operating status of the wind turbine.

[0003] The Chinese patent publication number is CN111828247A, and the name is a patent application for a method, system and device for standardizing and correcting a turbulent power curve. The method obtains the corresponding power of the turbulence intensity to be corrected and the specified corrected turbulence intensity based on the reference power curves of multiple turbulence intensities, obtains a section of actual data, calculates its mean or standard deviation as required, and performs other corrections to obtain the data to be standardized. Based on the data to be standardized and the power curves under a limited number of typical turbulence conditions, the weight of the given data obtained is calculated according to the mean and standard deviation characteristics of the normal distribution, and the power relationship under different turbulence intensities is obtained by the weight method. According to the power relationship, the power under the turbulence intensity to be corrected is standardized to the power of the specified turbulence intensity, which can improve the comparability of the power curve; thereby improving the conformity of the measured power curve with the reference power curve of the wind turbine. This patent application cannot use complete data, and the accuracy of real-time evaluation of the power curve still needs to be improved. Summary of the invention

[0004] In order to overcome the problems existing in the above-mentioned prior art, the purpose of the present invention is to provide a real-time correction method and equipment for the wind turbine power curve, a system that can evaluate the operating conditions of the wind turbine in real time, dynamically correct the power curve and accurately evaluate the power generation efficiency, so as to improve the accuracy of wind turbine performance evaluation and provide reliable data support for wind farm operation optimization.

[0005] To achieve the above object, the technical solution adopted by the present invention is: In a first aspect, the present invention provides a method for real-time correction of a wind turbine power curve, comprising the following steps: Collect data and equipment status of wind turbines; Calculate the air density and turbulence intensity based on the collected data; Adopting neural network algorithm, wind speed, equipment status, air density and turbulence intensity are used as input layer of neural network; correction coefficients of equipment status, air density and turbulence intensity are output; Multiply the original power curve by the correction factor to output the corrected power curve.

[0006] Optionally, after collecting the data of the wind turbine generator set, outlier detection, missing value processing, data standardization and feature extraction are performed on the collected data.

[0007] Optionally, the operating condition is determined based on the equipment status, air density and turbulence intensity calculation results, and the operating condition is divided into a normal operating condition, a high turbulence operating condition, an abnormal density operating condition and an abnormal blade operating condition.

[0008] Optionally, by comparing the theoretical power generation with the actual power generation, corresponding parameter adjustment suggestions are selected according to the classification results of different working conditions through a preset database.

[0009] Optionally, the data collected from the wind turbine generator set includes wind speed data, power output data, wind direction data, pitch angle data, temperature data and air pressure data; the wind speed data adopts a sampling frequency of 10Hz; the power output, wind direction and pitch angle data adopt a sampling frequency of 1Hz; the ambient temperature and air pressure adopt a sampling frequency of 0.1Hz.

[0010] Optionally, the correction calculation formula of the power curve is:

[0011] in, It represents the corrected power output in kW; Indicates the reference power under standard working conditions, in kW; Represents the air density correction factor, which is a dimensionless parameter; represents the turbulence intensity correction coefficient, which is a dimensionless parameter; Represents the equipment status correction coefficient, which is a dimensionless parameter.

[0012] In a second aspect, the present invention provides a wind turbine power curve real-time correction system, comprising: Data acquisition module, used to collect data and equipment status of wind turbine generator sets; A first calculation module is used to calculate air density and turbulence intensity based on the collected data; The second calculation module is used to use the wind speed, equipment status, air density and turbulence intensity as the input layer of the neural network; output the correction coefficients of equipment status, air density and turbulence intensity; The power curve correction module is used to multiply the original power curve by the correction coefficient and output the corrected power curve.

[0013] In a third aspect, the present invention provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the real-time correction method for the wind turbine power curve when executing the computer program.

[0014] In a fourth aspect, the present invention 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 real-time correction method for the wind turbine power curve is implemented.

[0015] In a fifth aspect, the present invention provides a computer program product comprising a computer-readable medium, wherein the computer-readable medium contains a computer-readable program code, and the program code executes the real-time correction method for the wind turbine power curve.

[0016] Compared with the prior art, the present invention has the following beneficial effects: The present invention acquires wind turbine operating status data in real time by constructing a multi-source data collection and fusion mechanism, and uses a deep neural network to realize dynamic correction of the power curve, thereby improving the accuracy of wind turbine performance evaluation. The present invention can adapt to different environmental conditions and equipment conditions, calculate various correction coefficients in real time, and make the corrected power curve closer to the actual operating conditions. By establishing a working condition classification and comprehensive evaluation mechanism, the system can accurately identify the key factors affecting power generation performance and automatically generate targeted optimization suggestions. At the same time, the system has continuous learning and optimization capabilities, and can continuously update the optimization strategy according to the actual operating results to improve the operating efficiency of the wind turbine.

[0017] Furthermore, the modular design of the wind turbine power curve real-time correction system of the present invention facilitates system maintenance and expansion, and the interface standards between the functional modules are unified, which can realize the rapid deployment of different wind farms and provide reliable technical support for the intelligent operation and maintenance of wind farms. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] The drawings described herein are for illustration purposes only and are not intended to limit the scope of the present disclosure in any way.

[0019] In the attached picture: Figure 1 This is an overall architecture diagram of a wind turbine power curve real-time correction system according to an embodiment of the present invention; Figure 2 It is a structural diagram of a data acquisition module according to an embodiment of the present invention; Figure 3 This is a structural diagram of a data preprocessing module according to an embodiment of the present invention; Figure 4 This is a structural diagram of a working condition classification module according to an embodiment of the present invention; Figure 5 This is a structural diagram of a power curve correction module according to an embodiment of the present invention; Figure 6 4 is a structural diagram of a deep neural network according to an embodiment of the present invention. DETAILED DESCRIPTION In order to enable those skilled in the art to better understand the technical solutions in the present invention, 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 only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0020] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art to which the present invention belongs. The terms used herein in the specification of the present invention are only for the purpose of describing specific embodiments and are not intended to limit the present invention. The term "and / or" used herein includes any and all combinations of one or more of the related listed items.

[0021] It should be noted that in the claims, any reference signs placed between brackets shall not be construed as limiting the claims. The word "comprising" does not exclude the presence of components or steps not listed in the claims. The word "a" or "an" preceding a component does not exclude the presence of a plurality of such components. The present application may be implemented by means of hardware comprising several different components and by means of a suitably programmed computer. In a unit claim enumerating several means, several of these means may be embodied by the same item of hardware. The use of the words first, second, and third etc. does not indicate any order. These words may be interpreted as names. In addition, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the features. In the description of this application, the meaning of "plurality" is two or more, unless otherwise clearly and specifically defined. The present invention is described in detail below with reference to the accompanying drawings.

[0022] like Figure 1 As shown, a real-time correction method for a wind turbine power curve of the present invention comprises the following steps: Collect data and equipment status of wind turbines; Calculate the air density and turbulence intensity based on the collected data; The wind speed, equipment status, air density and turbulence intensity are used as the input layer of the neural network; the correction coefficients of equipment status, air density and turbulence intensity are output; Multiply the original power curve by the correction factor to output the corrected power curve.

[0023] Optionally, the performance evaluation module divides power loss factors into: environmental factors; equipment factors; and control strategy factors.

[0024] Optionally, the wind speed data adopts a sampling frequency of 10 Hz; the power output, wind direction and pitch angle adopt a sampling frequency of 1 Hz; the ambient temperature and air pressure adopt a sampling frequency of 0.1 Hz.

[0025] Optionally, outlier detection is performed by screening parameter limits based on the 3σ criterion and expert experience; short-term missing data are supplemented by interpolation methods, and long-term missing data are marked; data standardization converts parameters of different dimensions to a unified scale.

[0026] Optionally, the current air density is calculated based on the ambient temperature and air pressure; the turbulence intensity is calculated based on the wind speed standard deviation and the average wind speed in a specific time period; and the current operating condition type is determined based on the above calculation and evaluation results.

[0027] Optionally, the correction factor is calculated using a deep neural network structure, including: an input layer for receiving characteristic parameters of wind speed, air density, turbulence intensity and equipment status; three hidden layers using a ReLU activation function; and an output layer for outputting the correction coefficient.

[0028] Example 1 like Figure 1 Shown is an overall architecture diagram of a wind turbine power curve real-time correction system of the present invention.

[0029] The system adopts a modular design, including data acquisition module, data preprocessing module, working condition classification module, power curve correction module and performance evaluation module. Each module is connected in sequence through data flow to form a complete analysis and processing link, realizing full-process intelligent analysis from data acquisition to performance evaluation.

[0030] like Figure 2 The following is a detailed structural diagram of the data acquisition module. This module integrates two data sources, the SCADA system and the CMS system, to achieve unified data collection and management.

[0031] Among them, the SCADA system is responsible for collecting wind turbine operating parameters, including wind speed, power, environmental parameters and control parameters; the CMS system is responsible for collecting equipment health status data, including vibration characteristics, temperature characteristics and bearing status.

[0032] A high-frequency sampling of 10 Hz is used for wind speed data to ensure that instantaneous changes in wind conditions can be accurately captured; a sampling frequency of 1 Hz is used for power output, wind direction and pitch angle to meet the real-time requirements of the control system; a sampling frequency of 0.1 Hz is used for parameters such as ambient temperature and air pressure to ensure effective tracking of environmental changes.

[0033] like Figure 3 The figure shows the structure of the data preprocessing module. The module first detects outliers on the original data and screens them using parameter limits set based on the 3σ criterion combined with expert experience.

[0034] For detected outliers, different processing strategies are adopted according to data characteristics: short-term missing data is supplemented by interpolation, and long-term missing data is marked. The data standardization process converts parameters of different dimensions to a unified scale for subsequent analysis. The feature extraction stage calculates key operating condition parameters to provide basic data support for operating condition classification.

[0035] In the data preprocessing stage, the air density is calculated using the ideal gas state equation:

[0036] in, Indicates air density in kg / m³; Indicates atmospheric pressure, in Pa; Represents the air gas constant, with a value of 287.058 J / (kg·K); Represents the ambient temperature in °C. This formula takes into account the combined effects of temperature and air pressure on air density, providing basic parameters for subsequent power correction.

[0037] like Figure 4 The figure shows the structure of the operating condition classification module. This module uses a multi-level feature calculation and comprehensive judgment method to achieve accurate classification of the fan operating conditions. The feature calculation module includes three sub-modules: air density calculation, turbulence intensity calculation, and equipment status. The operating condition characteristics are extracted from the three dimensions of environment, wind conditions, and equipment. The comprehensive judgment of the operating condition determines the current operating condition type of the fan based on the preset classification rules.

[0038] In the calculation of working condition characteristics, turbulence intensity is a key parameter to characterize the fluctuation characteristics of wind conditions, and its calculation formula is:

[0039] in, Represents the turbulence intensity, which is a dimensionless parameter; It represents the standard deviation of wind speed within a specific time period (usually 10 minutes); It represents the average wind speed in the same time period, in m / s.

[0040] The turbulence intensity directly affects the load characteristics and power generation performance of the wind turbine, and is an important basis for power curve correction.

[0041] like Figure 5 The figure shows the structure of the power curve correction module. This module dynamically corrects the reference power curve by calculating the correction factor. The correction process takes into account the combined effects of air density changes, turbulence intensity changes and equipment status on power generation performance, and realizes real-time optimization of the power curve.

[0042] The power curve correction adopts a composite correction model, and its calculation formula is:

[0043] in, It represents the corrected power output in kW; Indicates the reference power under standard working conditions, in kW; Represents the air density correction factor, which is a dimensionless parameter; represents the turbulence intensity correction coefficient, which is a dimensionless parameter; Represents the equipment status correction coefficient, which is a dimensionless parameter.

[0044] Each correction coefficient is calculated through a deep neural network to achieve adaptive correction of the power curve.

[0045] like Figure 6 The figure shows the structure of the deep neural network of the present invention. The network adopts a multi-layer feedforward structure, including an input layer, three hidden layers and an output layer. The input layer receives the normalized operating condition characteristic parameters; the hidden layer uses the ReLU activation function to extract the deep correlation of the operating condition characteristics through multi-layer nonlinear transformation; the output layer generates a correction coefficient for dynamic correction of the power curve.

[0046] The input layer of the neural network includes wind speed, equipment status, air density and turbulence intensity. The training process is as follows: Target variable (correction coefficient) calculation: By comparing the actual power generation with the theoretical power generation, the correction coefficient is calculated as the target variable. The correction formula is:

[0047] The theoretical power generation is calculated based on the standard power curve of the wind turbine and the standard air density (1.225kg / m³).

[0048] Data preprocessing: Normalize the input features, for example, scale the wind speed, air density, turbulence intensity and other features to the [0,1] range.

[0049] Remove outliers and fill in missing values ​​to ensure data quality.

[0050] Data classification: Label the operating condition type based on historical operating data to facilitate further optimization of training.

[0051] Neural Network Training: Model structure: Use a multi-layer feedforward neural network (MLP) or an LSTM model that includes time series features.

[0052] Input layer: wind speed, equipment status, air density, turbulence intensity, and corresponding working condition classification features. The working condition classification results are used as input features of the neural network to help the model capture nonlinear relationships in the data and improve prediction accuracy.

[0053] Output layer: corresponding to air density correction factor, turbulence intensity correction factor and equipment status correction factor.

[0054] Loss function: The mean squared error (MSE) is used to measure the difference between the predicted value and the target value.

[0055] Optimizer: Such as Adam optimizer, combined with learning rate adjustment strategy to improve model convergence speed.

[0056] Training data partitioning: The data is divided into training set, validation set and test set in a ratio of 7:2:1 to ensure the generalization ability of the model on the test set.

[0057] Verification and tuning: The model's hyperparameters (number of hidden layer nodes or activation function) are adjusted using the validation set, and the model performance is evaluated on the test set.

[0058] The root mean square error (RMSE) and coefficient of determination (R²) were used to evaluate the model fit.

[0059] The network is trained using a batch stochastic gradient descent algorithm, and the learning rate uses an adaptive adjustment strategy to ensure the convergence and generalization ability of the model.

[0060] In the performance evaluation phase, the system first calculates the theoretical power generation based on the modified power curve.

[0061] By comparing theoretical power generation with actual power generation, the system quantitatively analyzes power loss and divides the loss factors into three categories: environmental factors, equipment factors and control strategies.

[0062] For the identified efficiency losses, the system automatically generates optimization suggestions based on the preset expert rule base, including operating parameter adjustment suggestions and equipment maintenance suggestions.

[0063] Optionally, under high turbulence conditions, power losses can be reduced by optimizing wind turbine operating parameters (pitch angle).

[0064] After feasibility assessment, these suggestions can be used to guide the optimization of wind turbine control strategies and achieve continuous improvement in power generation efficiency.

[0065] The present invention realizes accurate evaluation and optimization of wind turbine power generation performance by constructing a complete wind turbine power curve correction and efficiency evaluation method. This method has the following advantages: first, multi-source data fusion technology is used to comprehensively collect wind turbine operating status information; second, a multi-level operating condition classification method is used to accurately identify various factors affecting power generation performance; third, the power curve correction model based on deep learning has strong adaptive capabilities; finally, the efficiency evaluation results can directly guide operation and maintenance optimization and have strong practicality. These characteristics enable this method to adapt to the operating environment of different wind farms, and continuously improve the prediction accuracy and evaluation accuracy as data accumulates, providing strong technical support for the intelligent operation and maintenance of wind farms.

[0066] Example 2 Based on the method of Example 1, a wind turbine power curve real-time correction system of this embodiment includes: A data acquisition module, used to collect SCADA system data and CMS system data of the wind turbine generator set; the SCADA system data includes wind speed data, power data, environmental parameter data and control parameter data, and the CMS system data includes vibration data, temperature data and bearing data; A data preprocessing module is used to perform outlier detection, missing value processing, data standardization and feature extraction on the SCADA system data and the CMS system data; an operating condition classification module is used to perform air density calculation, turbulence intensity calculation and equipment status evaluation, and perform a comprehensive operating condition judgment based on the calculation and evaluation results; a power curve correction module is used to calculate the correction factor based on the operating condition characteristics, and perform correction in combination with the reference power curve to output the corrected power curve; an efficiency evaluation module is used to calculate the theoretical power generation based on the corrected power curve, and perform efficiency evaluation and generate optimization suggestions by comparing the theoretical power generation with the actual power generation.

[0067] The optimization effect monitoring unit is used to: continuously monitor the implementation effect of the optimization suggestions; feed back the monitoring results to the rule base; and update the optimization strategy.

[0068] The operating condition types of the operating condition classification module include: normal operating condition; high turbulence operating condition; abnormal density operating condition; abnormal blade operating condition.

[0069] The working condition classification module comprises: An air density calculation unit, used to calculate the current air density based on ambient temperature and air pressure; A turbulence intensity calculation unit, used to calculate the turbulence intensity based on the wind speed standard deviation and the average wind speed in a specific time period; Equipment status evaluation unit, used to evaluate the equipment operation status; The operating condition comprehensive determination unit is used to determine the current operating condition type based on the above calculation and evaluation results.

[0070] The power curve correction module includes: a correction factor calculation unit for calculating an air density correction factor, a turbulence intensity correction factor and an equipment status correction factor; and a curve correction unit for correcting a reference power curve based on the correction factors.

[0071] The correction factor calculation unit adopts a deep neural network structure, including: an input layer for receiving characteristic parameters of wind speed, air density, turbulence intensity and equipment status; three hidden layers using ReLU activation function; and an output layer for outputting the correction coefficient.

[0072] The performance evaluation module includes: a power generation performance evaluation unit, which is used to calculate theoretical power generation and compare it with actual power generation; and an optimization suggestion generation unit, which is used to generate operating parameter adjustment suggestions and equipment maintenance suggestions based on a preset expert rule base.

[0073] Example 3 The purpose of this embodiment is to provide an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the real-time correction method for the wind turbine power curve when executing the computer program.

[0074] Example 4 The purpose of this embodiment is to provide 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 real-time correction method for the wind turbine power curve is implemented.

[0075] Example 5 The purpose of this embodiment is to provide a computer program product including a computer-readable medium, on which a computer-readable program code is contained, and the program code executes the real-time correction method for the wind turbine power curve.

[0076] The steps involved in the devices of the above embodiments 2, 3, 4 and 5 correspond to those of the method embodiment 1. For the specific implementation methods, please refer to the relevant description part of embodiment 1.

[0077] It should be understood by those skilled in the art that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present application may adopt 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 codes. The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes 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 generate 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. 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. 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. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0078] Unless otherwise specified, the working modes or control modes involved in the above embodiments are all conventional working modes or control modes in the art.

[0079] Although the preferred embodiments of the present application have been described, those skilled in the art may make other changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications falling within the scope of the present application. Finally, it should be noted that the above embodiments are only used to illustrate the technical solution of the present invention rather than to limit it. Other modifications or equivalent substitutions made to the technical solution of the present invention by ordinary technicians in the field should be included in the scope of the claims of the present invention as long as they do not depart from the spirit and scope of the technical solution of the present invention.

Claims

1. A real-time correction method for a wind turbine power curve, characterized in that: The following steps are involved: Collect data and equipment status of wind turbines; Calculate the air density and turbulence intensity based on the collected data; Adopting neural network algorithm, wind speed, equipment status, air density and turbulence intensity are used as input layer of neural network; correction coefficients of equipment status, air density and turbulence intensity are output; Multiply the original power curve by the correction factor to output the corrected power curve.

2. A method for real-time correction of wind turbine power curve according to claim 1, characterized in that: After collecting the data of wind turbines, outlier detection, missing value processing, data standardization and feature extraction are performed on the collected data.

3. A real-time correction method for wind turbine power curve according to claim 1, characterized in that: The operating condition is determined based on the equipment status, air density and turbulence intensity calculation results, and is divided into normal operating conditions, high turbulence conditions, abnormal density conditions and abnormal blade conditions.

4. A real-time correction method for wind turbine power curve according to claim 3, characterized in that: By comparing the theoretical power generation with the actual power generation, the corresponding parameter adjustment suggestions are selected according to the classification results of different working conditions through the preset database.

5. A real-time correction method for wind turbine power curve according to claim 1, characterized in that: The data collected from the wind turbine generator set include wind speed data, power output data, wind direction data, pitch angle data, temperature data and air pressure data; the wind speed data adopts a sampling frequency of 10Hz; the power output, wind direction and pitch angle data adopt a sampling frequency of 1Hz; the ambient temperature and air pressure adopt a sampling frequency of 0.1Hz.

6. A real-time correction method for wind turbine power curve according to claim 1, characterized in that: The correction calculation formula of the power curve is: in, It represents the corrected power output in kW; Indicates the reference power under standard working conditions, in kW; Represents the air density correction factor, which is a dimensionless parameter; represents the turbulence intensity correction coefficient, which is a dimensionless parameter; Represents the equipment status correction coefficient, which is a dimensionless parameter.

7. A real-time correction system for wind turbine power curve, characterized in that: include: Data acquisition module, used to collect data and equipment status of wind turbine generator sets; A first calculation module is used to calculate air density and turbulence intensity based on the collected data; The second calculation module is used to use the wind speed, equipment status, air density and turbulence intensity as the input layer of the neural network; output the correction coefficients of equipment status, air density and turbulence intensity; The power curve correction module is used to multiply the original power curve by the correction coefficient and output the corrected power curve.

8. An electronic device, characterized in that: The method comprises a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the processor implements the real-time correction method for the wind turbine power curve as claimed in any one of claims 1 to 6 when executing the computer program.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the real-time correction method for the wind turbine power curve according to any one of claims 1 to 6 is implemented.

10. A computer program product comprising a computer readable medium, characterized in that The computer-readable medium contains computer-readable program code, and the program code executes the real-time correction method for wind turbine power curve according to any one of claims 1-6.

Images