Power optimization control method for wind generating set

Abstract

The invention provides a wind generating set power optimization control method, and belongs to the technical field of optimization control. The method comprises the steps that 1, a sensor is arranged on the wind generating set, and real-time wind speed data of the surrounding environment and real-time rotating speed data of an impeller are obtained; 2, after the real-time wind speed data and the real-time rotating speed data of the impeller are standardized, a performance curve of the wind generating set is constructed; step 3, obtaining the maximum power point of the performance curve by using an MPPT algorithm; 4, according to the maximum power point and the performance curve, the impeller rotating speed is controlled to reach the maximum power in combination with a control algorithm; and step 5, configuring the control algorithm and the MPPT algorithm into the wind generating set control system, and performing optimization feedback on the algorithm according to the error between the adjusted real power and the optimal power. The wind power generation efficiency is improved, power output is optimized, and the stability and reliability of the wind generating set are enhanced.

Description

Technical Field

[0001] The present invention relates to the technical field of optimization control, and in particular to a method for optimizing power control of a wind turbine generator set. Background Art

[0002] At present, with the increasing demand for renewable energy, wind power generation has become one of the important energy sources. As a clean and renewable energy source, wind power generation helps reduce greenhouse gas emissions, reduce dependence on fossil fuels, and promote energy structure transformation. However, wind turbines are affected by wind speed fluctuations, and power output is unstable, resulting in low energy efficiency.

[0003] Therefore, the present invention proposes a method for optimizing the power control of a wind turbine generator set. Summary of the invention

[0004] The present invention provides a power optimization control method for a wind turbine generator set, which is used to obtain wind speed and impeller speed data in real time by configuring sensors, construct a performance curve, find the maximum power point using the MPPT algorithm, and adjust the impeller speed through a control algorithm to optimize the power output of the wind turbine generator set and achieve high-efficiency operation.

[0005] In one aspect, the present invention provides a method for optimizing power control of a wind turbine generator set, comprising: Step 1: equip the wind turbine with sensors to obtain real-time wind speed data of the surrounding environment and real-time rotation speed data of the impeller; Step 2: after standardizing the real-time wind speed data and the real-time impeller speed data, construct a performance curve of the wind turbine generator set; Step 3: Use the MPPT algorithm to obtain the maximum power point of the performance curve; Step 4: According to the maximum power point and performance curve, the impeller speed is controlled to achieve the maximum power in combination with the control algorithm; Step 5: Configure the control algorithm and MPPT algorithm into the wind turbine control system, and optimize the algorithm based on the error between the adjusted real power and the optimal power.

[0006] On the other hand, sensors are configured on the wind turbine generator set to obtain real-time wind speed data of the surrounding environment and real-time rotation speed data of the impeller, including: Obtain the surrounding geographical environment information of the wind turbine generator set, determine the installation location of the wind speed sensor, and configure and install the wind speed sensor; Obtain a schematic diagram of the impeller of the wind turbine generator set, and configure a photoelectric encoder for sensing rotation at the impeller through optical principles; Based on the wind speed sensor and the photoelectric encoder, the real-time wind speed data of the surrounding environment of the wind turbine generator set and the real-time rotation speed data of the impeller are acquired in real time.

[0007] On the other hand, after the real-time wind speed data and the real-time impeller speed data are standardized, the performance curve of the wind turbine generator set is constructed, including: Based on the normal distribution algorithm, the real-time wind speed data and the real-time rotation speed data of the impeller are standardized to obtain the standard wind speed data and the standard rotation speed data; Fit the standard wind speed data and standard rotation speed data to construct a polynomial function of the relationship between wind speed and rotation speed ,in, represents the speed data of the i-th time node in the standard speed data, Represents the wind speed data at the i-th time node in the standard wind speed data, represents the optimal parameter set; represents a set of polynomial parameters, and n represents that the polynomial function has a total of n parameters; Substitute the standard wind speed data and standard rotation speed data into the polynomial function, and regard the fitting parameter group that achieves the minimum error as the optimal parameter group: The process of obtaining the optimal parameter group specifically includes: right According to Find the partial derivative and solve it through the partial derivative polynomial function to get the optimal parameter set ,At the same time, the relationship between wind speed and rotation speed is also obtained.

[0008] On the other hand, it also includes: According to the preset speed index of the wind turbine, the initial function between speed and power is constructed for: ;in, represents the power factor, Indicates the preset starting speed. Indicates the rated speed, Indicates rated power, Indicates the maximum safe speed. Indicates the standard speed data corresponding to the i+1th time node, ( ) represents the exponential function, Indicates the first time the function changes piecewise relative to The control adjustment coefficient, Indicates the second function segment change relative The control adjustment coefficient of Indicates all The variance of Use a multi-layer perceptron to take the initial function as the function layer, the standard speed data as the input layer, the power as the output layer, initialize the weight of each layer, and build the first network; Input the standard speed data into the first network, obtain a first activation value, obtain a predicted power output value in the output layer according to the first activation value, and obtain an actual output value in the function layer according to a preset starting power coefficient and the first activation value; Calculate the second activation value of the predicted power output value and the actual output value based on the loss function, iteratively adjust the weight and power coefficient of each layer, and when the second activation value is at the lowest loss, the power coefficient is the optimal coefficient; A performance curve of rotation speed-wind speed-power of the wind turbine generator set is constructed according to the optimal coefficient and the optimal parameter group.

[0009] On the other hand, the MPPT algorithm is used to obtain the maximum power point of the performance curve, including: Obtain the mean of standard speed data in the wind turbine generator set, and generate an interference speed group based on mean screening and interference speeds whose absolute values ​​of mean differences are less than a preset interference threshold; The interference speed group is input into the performance curve, the interference power is output, and the power change corresponding to the mean of the interference power and the standard speed data is obtained. According to the power change, it is determined whether to increase or decrease the disturbance, and the mean of the standard speed data is adjusted to approach the maximum power point.

[0010] On the other hand, according to the maximum power point and performance curve, the impeller speed is controlled to achieve maximum power in combination with the control algorithm, including: Obtain standard rotation speed data and standard wind speed data, output corresponding power data according to the performance curve, and obtain the power error between the actual power at any time node and the maximum power point; According to the power error at the time node, a control signal is generated based on a control algorithm, and the control signal is used to adjust the fan speed of the impeller.

[0011] On the other hand, the control algorithm and MPPT algorithm are configured in the wind turbine control system, and optimization feedback is performed according to the error between the adjusted real power and the optimal power, including: The control algorithm and the MPPT algorithm are integrated as algorithm parts to obtain an integrated algorithm, and configured into the control system of the wind turbine generator set, and the integrated algorithm is initialized based on a parameter part consisting of a rated speed and an optimal parameter group; Start the wind turbine in a real environment, obtain the real wind speed data and real speed data, and control the wind turbine according to the integrated algorithm to obtain the real power; The error between the real power and the optimal power is calculated, and the parameters of the integrated algorithm are adjusted and optimized according to the error.

[0012] On the other hand, it also includes: The wind speed threshold range of the impeller is obtained. When the wind speed of the environment is lower than the left end value of the wind speed threshold, the impeller is turned off. When the wind speed is higher than or lower than the right end value of the wind speed threshold, the impeller is also turned off.

[0013] Compared with the prior art, the present invention has the following beneficial effects: The present invention provides a power optimization control method for a wind turbine generator set, which is used to obtain wind speed and impeller speed data in real time by configuring sensors, construct a performance curve, find the maximum power point using the MPPT algorithm, and adjust the impeller speed through a control algorithm to optimize the power output of the wind turbine generator set and achieve high-efficiency operation. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0015] Figure 1 It is a flow chart of a wind turbine generator set power optimization control method provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0016] In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be clearly and completely described below in conjunction with the drawings of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0017] Embodiment 1: like Figure 1 As shown, an embodiment of the present invention provides a method for optimizing power control of a wind turbine generator set, comprising: Step 1: equip the wind turbine with sensors to obtain real-time wind speed data of the surrounding environment and real-time rotation speed data of the impeller; Step 2: after standardizing the real-time wind speed data and the real-time impeller speed data, construct a performance curve of the wind turbine generator set; Step 3: Use the MPPT algorithm to obtain the maximum power point of the performance curve; Step 4: According to the maximum power point and performance curve, the impeller speed is controlled to achieve the maximum power in combination with the control algorithm; Step 5: Configure the control algorithm and MPPT algorithm into the wind turbine control system, and optimize the algorithm based on the error between the adjusted real power and the optimal power.

[0018] In this embodiment, the wind turbine generator set is a device that converts wind energy into electrical energy, and is mainly composed of an impeller, a generator, a control system, a sensor, etc.

[0019] In this embodiment, the sensor is a device used to monitor and obtain the wind speed and impeller speed of the surrounding environment of the wind turbine generator set in real time.

[0020] In this embodiment, the surrounding environment refers to the natural environmental conditions around the wind turbine generator set, including: wind speed, temperature, climate conditions, air concentration, etc.

[0021] In this embodiment, the real-time wind speed data refers to the wind speed information of the wind turbine generator set at the time of operation obtained by a sensor installed in the surrounding environment of the wind turbine generator set.

[0022] In this embodiment, the impeller refers to a rotating component in a wind turbine generator set for capturing wind energy and converting it into mechanical energy.

[0023] In this embodiment, the real-time rotation speed data refers to the instantaneous speed data of the blades rotating during the actual operation of the wind turbine impeller.

[0024] In this embodiment, standardization refers to processing the collected real-time wind speed data and the real-time impeller speed data to convert them into a unified scale and time range.

[0025] In this embodiment, the performance curve refers to a function curve of the relationship between the power that can be output by the wind turbine generator set under different wind speeds and impeller speeds and these parameters.

[0026] In this embodiment, the MPPT algorithm is a control strategy for a wind turbine generator set, which finds the maximum power output point of the wind turbine generator set under different wind speed and rotation speed conditions.

[0027] In this embodiment, the maximum power point refers to the point corresponding to the maximum power that the wind turbine generator set can output under given wind speed and impeller speed conditions.

[0028] In this embodiment, the control algorithm is implemented by obtaining feedback signals from the system and adjusting the control input according to the feedback signals.

[0029] In this embodiment, the real power refers to the actual electric power output in real time by the wind turbine generator set during actual operation according to wind speed, impeller speed and other environmental factors.

[0030] In this embodiment, the optimal power refers to the theoretical maximum power of the wind turbine generator set calculated based on the performance curve and the MPPT algorithm under given environmental conditions.

[0031] In this embodiment, the control system refers to an electronic control unit inside the wind turbine generator set for monitoring and adjusting the working state of the set.

[0032] The working principle and beneficial effects of the above technical solution are: by configuring sensors to obtain wind speed and impeller speed data in real time, constructing a performance curve, using the MPPT algorithm to find the maximum power point, and adjusting the impeller speed through a control algorithm, the power output of the wind turbine is optimized to achieve high-efficiency operation.

[0033] Embodiment 2: On the basis of the above-mentioned embodiment 1, a sensor is configured for the wind turbine generator set to obtain real-time wind speed data of the surrounding environment and real-time rotation speed data of the impeller, including: Obtain the surrounding geographical environment information of the wind turbine generator set, determine the installation location of the wind speed sensor, and configure and install the wind speed sensor; Obtain a schematic diagram of the impeller of the wind turbine generator set, and configure a photoelectric encoder for sensing rotation at the impeller through optical principles; Based on the wind speed sensor and the photoelectric encoder, the real-time wind speed data of the surrounding environment of the wind turbine generator set and the real-time rotation speed data of the impeller are acquired in real time.

[0034] In this embodiment, the installation location refers to the specific location where the sensor (such as the wind speed sensor and the photoelectric encoder) is installed.

[0035] In this embodiment, the wind speed sensor is a device used to measure air flow velocity (ie wind speed).

[0036] In this embodiment, the impeller schematic diagram is a schematic diagram of the impeller of the wind turbine generator set, which is used to show the structure, size, shape, relative position and other characteristics of the impeller.

[0037] In this embodiment, the optical principle refers to the principle of using the propagation characteristics and behavior of light to achieve various functions and technologies.

[0038] In this embodiment, the photoelectric encoder is a sensor that uses optical principles to measure rotation or displacement.

[0039] The working principle and beneficial effects of the above technical solution are: by reasonably configuring wind speed sensors and photoelectric encoders, the surrounding wind speed and impeller speed data can be obtained in real time to optimize the operating efficiency of the wind turbine generator set. Through precise control and feedback, power output can be improved, power generation efficiency can be enhanced, and energy loss can be reduced.

[0040] Embodiment 3: On the basis of the above-mentioned embodiment 1, after the real-time wind speed data and the real-time impeller speed data are standardized, the performance curve of the wind turbine generator set is constructed, including: Based on the normal distribution algorithm, the real-time wind speed data and the real-time rotation speed data of the impeller are standardized to obtain the standard wind speed data and the standard rotation speed data; Fit the standard wind speed data and standard rotation speed data to construct a polynomial function of the relationship between wind speed and rotation speed ,in, represents the speed data of the i-th time node in the standard speed data, Represents the wind speed data at the i-th time node in the standard wind speed data, represents the optimal parameter set; represents a set of polynomial parameters, and n represents that the polynomial function has a total of n parameters; Substitute the standard wind speed data and standard rotation speed data into the polynomial function, and regard the fitting parameter group that achieves the minimum error as the optimal parameter group: The process of obtaining the optimal parameter group specifically includes: right According to Find the partial derivative and solve it through the partial derivative polynomial function to get the optimal parameter set ,At the same time, the relationship between wind speed and rotation speed is also obtained.

[0041] In this embodiment, the normal distribution algorithm refers to a statistical method based on normal distribution (also called Gaussian distribution) in data processing.

[0042] In this embodiment, the standard wind speed data refers to the data obtained by standardizing the original wind speed data. In this embodiment, the standard rotation speed data is data obtained by standardizing the original rotation speed data.

[0043] In this embodiment, fitting refers to modeling the data through a certain mathematical model so that the model describes the distribution relationship of the data as accurately as possible.

[0044] In this embodiment, the polynomial function is a function composed of multiple terms, each term including a power of a variable and a coefficient.

[0045] In this embodiment, the optimal parameter group represents the best coefficients in the polynomial function, so that the model can accurately describe the relationship between the standardized wind speed and the standardized rotation speed.

[0046] In this embodiment, the partial derivative polynomial function is the partial derivative of the error function with respect to each parameter, which represents the sensitivity of the error function to the change of the polynomial parameter.

[0047] The working principle and beneficial effects of the above technical solution are: normalizing wind speed and rotation speed data through normal distribution algorithm, and using polynomial fitting to obtain the optimal parameter group, accurately describing the relationship between wind speed and rotation speed. Solving the optimal parameters through partial derivatives, improving the performance of wind turbines, and optimizing power output and efficiency.

[0048] Embodiment 4: Based on the above embodiment 3, it also includes: According to the preset speed index of the wind turbine, the initial function between speed and power is constructed for: ;in, represents the power factor, Indicates the preset starting speed. Indicates the rated speed, Indicates rated power, Indicates the maximum safe speed. Indicates the standard speed data corresponding to the i+1th time node, ( ) represents the exponential function, Indicates the first time the function changes piecewise relative to The control adjustment coefficient, Indicates the second function segment change relative The control adjustment coefficient of Indicates all The variance of Use a multi-layer perceptron to take the initial function as the function layer, the standard speed data as the input layer, the power as the output layer, initialize the weight of each layer, and build the first network; Input the standard speed data into the first network, obtain a first activation value, obtain a predicted power output value in the output layer according to the first activation value, and obtain an actual output value in the function layer according to a preset starting power coefficient and the first activation value; Calculate the second activation value of the predicted power output value and the actual output value based on the loss function, iteratively adjust the weight and power coefficient of each layer, and when the second activation value is at the lowest loss, the power coefficient is the optimal coefficient; A performance curve of rotation speed-wind speed-power of the wind turbine generator set is constructed according to the optimal coefficient and the optimal parameter group.

[0049] In this embodiment, the preset speed index refers to a speed value related to wind speed and power output that is set in advance according to the design requirements and operation requirements of the wind turbine generator set.

[0050] In this embodiment, the power coefficient is an indicator used to describe the efficiency of a wind turbine in converting wind energy into mechanical energy (and then into electrical energy).

[0051] In this embodiment, the preset starting speed refers to the speed corresponding to the lowest wind speed at which the wind turbine starts to rotate and can generate available power.

[0052] In this embodiment, the rated speed refers to the speed at which the wind turbine generator set runs when outputting rated power.

[0053] In this embodiment, the rated power refers to the maximum stable power that the wind turbine can output at the rated wind speed.

[0054] In this embodiment, the maximum safe rotation speed refers to the maximum rotation speed that the fan blades can withstand during operation.

[0055] In this embodiment, a multilayer perceptron is an artificial neural network structure consisting of multiple layers, and is mainly used to process and learn complex nonlinear relationships.

[0056] In this embodiment, the function layer refers to a specific layer in a multi-layer perceptron (MLP), which is responsible for mapping the input data to a reasonable output space after a certain mathematical transformation.

[0057] In this embodiment, the main task of the output layer is to calculate and output the power of the wind turbine generator set based on the input layer (standard speed data) and the processing of each hidden layer.

[0058] In this embodiment, the main task of the input layer is to receive standard rotation speed data from the outside.

[0059] In this embodiment, the first network refers to a neural network model built based on a multi-layer perceptron, and its function is to predict the power output according to the standard speed data of the wind turbine.

[0060] In this embodiment, the weight determines the influence of each input on the output of each layer of neurons (input layer and output layer, etc.).

[0061] In this embodiment, the first activation value refers to the output value calculated at the function layer of the network.

[0062] In this embodiment, predicting the power output value refers to generating a processing result based on the input standard speed data based on the neural network model, weights and loss function.

[0063] In this embodiment, the actual output value is an actual power prediction value calculated based on the neural network.

[0064] In this embodiment, the second activation value is calculated by a multi-layer perceptron and is used to represent an intermediate result in the network training process.

[0065] In this embodiment, the optimal coefficient refers to the power coefficient obtained by optimization during the training process, so that the error between the predicted power output of the model and the actual power output is minimized.

[0066] In this embodiment, the minimum loss refers to a state in which the error (ie, the loss function value) between the predicted power output value and the actual power output value is minimized by optimizing the model parameters (including weights and power coefficients).

[0067] The working principle and beneficial effects of the above technical solution are: optimizing the speed-power relationship through a multi-layer perceptron network, using standard speed data and power output to train the network, adjusting the weights and power coefficients to achieve minimum losses, achieving accurate modeling of the performance curve of the wind turbine generator set, and improving prediction accuracy and energy efficiency.

[0068] Embodiment 5: Based on the above embodiment 1, the maximum power point of the performance curve is obtained by using the MPPT algorithm, including: Obtain the mean of standard speed data in the wind turbine generator set, and generate an interference speed group based on mean screening and interference speeds whose absolute values ​​of mean differences are less than a preset interference threshold; The interference speed group is input into the performance curve, the interference power is output, and the power change corresponding to the mean of the interference power and the standard speed data is obtained. According to the power change, it is determined whether to increase or decrease the disturbance, and the mean of the standard speed data is adjusted to approach the maximum power point.

[0069] In this embodiment, the preset interference threshold is a preset constant value used to interfere with data screening and adjustment.

[0070] In this embodiment, the interference rotation speed refers to a rotation speed whose difference from the mean value is less than a preset interference threshold.

[0071] In this embodiment, the interference speed group refers to a speed data set with interference or disturbance effects, which is screened out from the standard speed data through certain screening and judgment conditions during the control process of the wind turbine generator set.

[0072] In this embodiment, the interference power refers to the power change caused by the disturbance or fluctuation of the rotation speed on the performance of the wind turbine generator set.

[0073] The working principle and beneficial effects of the above technical solution are: by screening the interference speed, generating the interference speed group and inputting the performance curve, analyzing the power change, judging and adjusting the mean of the standard speed data to approach the maximum power point, and improving the power output accuracy and system stability of the wind turbine.

[0074] Embodiment 6: On the basis of the above-mentioned embodiment 1, according to the maximum power point and the performance curve, the impeller speed is controlled to achieve the maximum power in combination with the control algorithm, including: Obtain standard rotation speed data and standard wind speed data, output corresponding power data according to the performance curve, and obtain the power error between the actual power at any time node and the maximum power point; According to the power error at the time node, a control signal is generated based on a control algorithm, and the control signal is used to adjust the fan speed of the impeller.

[0075] In this embodiment, the power error refers to the difference between the actual power and the maximum power point at any given time node.

[0076] In this embodiment, the control signal is a dynamic adjustment signal used in the control system of the fan.

[0077] In this embodiment, the fan speed refers to the rotation speed of the fan main shaft.

[0078] The working principle and beneficial effects of the above technical solution are: by calculating the power error, using the control algorithm to generate a control signal, adjusting the impeller speed, optimizing the fan performance, reducing the power error, improving the output efficiency and response speed of the wind turbine, and improving energy utilization and stability.

[0079] Embodiment 7: On the basis of the above-mentioned embodiment 1, the control algorithm and the MPPT algorithm are configured in the control system of the wind turbine generator set, and optimization feedback is performed according to the error between the adjusted real power and the optimal power, including: The control algorithm and the MPPT algorithm are integrated as algorithm parts to obtain an integrated algorithm, and the integrated algorithm is configured into the control system of the wind turbine generator set, and the integrated algorithm is initialized based on the parameter part composed of the rated speed and the optimal parameter group; Start the wind turbine in a real environment, obtain the real wind speed data and real speed data, and control the wind turbine according to the integrated algorithm to obtain the real power; The error between the real power and the optimal power is calculated, and the parameters of the integrated algorithm are adjusted and optimized according to the error.

[0080] In this embodiment, integration is the merging of the functions of two independent algorithms.

[0081] In this embodiment, initialization refers to the process of setting initial parameters of an integrated algorithm when configuring the integrated algorithm in the control system of the wind turbine generator set.

[0082] In this embodiment, the real environment refers to the physical environment in which the wind turbine generator set actually operates.

[0083] In this embodiment, the real power refers to the power output by the wind turbine generator set under the control of the control system algorithm based on the actual wind speed and rotation speed data in the actual operating environment.

[0084] The working principle and beneficial effects of the above technical solution are: by integrating the control algorithm and the MPPT algorithm, combined with the real wind speed and rotation speed data, the wind turbine control is optimized to reduce power errors. By adjusting the algorithm parameters in real time, the wind turbine efficiency and power output are improved.

[0085] Embodiment 8: Based on the above embodiment 7, it also includes: The wind speed threshold range of the impeller is obtained. When the wind speed of the environment is lower than the left end value of the wind speed threshold, the impeller is turned off. When the wind speed is higher than or lower than the right end value of the wind speed threshold, the impeller is also turned off.

[0086] In this embodiment, the wind speed threshold range refers to the wind speed interval in which the impeller of the wind turbine generator set works or stops working under different wind speed conditions.

[0087] In this embodiment, the left end value is the starting wind speed or the minimum working wind speed.

[0088] In this embodiment, the right end value is the shutdown wind speed or the maximum safe wind speed.

[0089] The working principle and beneficial effects of the above technical solution are: by setting the impeller wind speed threshold range, the impeller is shut down when the wind speed is lower than or higher than the threshold, avoiding operation under inappropriate wind speed conditions, protecting the wind turbine generator set, reducing losses, and improving the safety and reliability of the equipment.

[0090] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for optimizing the power control of a wind turbine generator set, characterized in that: include: Step 1: equip the wind turbine with sensors to obtain real-time wind speed data of the surrounding environment and real-time rotation speed data of the impeller; Step 2: after standardizing the real-time wind speed data and the real-time impeller speed data, construct a performance curve of the wind turbine generator set; Step 3: Use the MPPT algorithm to obtain the maximum power point of the performance curve; Step 4: According to the maximum power point and performance curve, the impeller speed is controlled to achieve the maximum power in combination with the control algorithm; Step 5: Configure the control algorithm and MPPT algorithm into the wind turbine control system, and optimize the algorithm based on the error between the adjusted real power and the optimal power.

2. A wind turbine power optimization control method according to claim 1, characterized in that: Sensors are installed on wind turbines to obtain real-time wind speed data of the surrounding environment and real-time rotation speed data of the impeller, including: Obtain the surrounding geographical environment information of the wind turbine generator set, determine the installation location of the wind speed sensor, and configure and install the wind speed sensor; Obtain a schematic diagram of the impeller of the wind turbine generator set, and configure a photoelectric encoder for sensing rotation at the impeller through optical principles; Based on the wind speed sensor and the photoelectric encoder, the real-time wind speed data of the surrounding environment of the wind turbine generator set and the real-time rotation speed data of the impeller are acquired in real time.

3. The method for optimizing the power control of a wind turbine generator set according to claim 1, characterized in that: After the real-time wind speed data and the real-time impeller speed data are standardized, the performance curve of the wind turbine generator set is constructed, including: Based on the normal distribution algorithm, the real-time wind speed data and the real-time rotation speed data of the impeller are standardized to obtain the standard wind speed data and the standard rotation speed data; Fit the standard wind speed data and standard rotation speed data to construct a polynomial function of the relationship between wind speed and rotation speed ,in, represents the speed data of the i-th time node in the standard speed data, Represents the wind speed data at the i-th time node in the standard wind speed data, represents the optimal parameter set; represents a set of polynomial parameters, and n represents that the polynomial function has a total of n parameters; Substitute the standard wind speed data and standard rotation speed data into the polynomial function, and regard the fitting parameter group that achieves the minimum error as the optimal parameter group: The process of obtaining the optimal parameter group specifically includes: right According to Find the partial derivative and solve it through the partial derivative polynomial function to get the optimal parameter set ,At the same time, the relationship between wind speed and rotation speed is also obtained.

4. A wind turbine power optimization control method according to claim 3, characterized in that: Also includes: According to the preset speed index of the wind turbine, the initial function between speed and power is constructed for: ;in, represents the power factor, Indicates the preset starting speed. Indicates the rated speed, Indicates rated power, Indicates the maximum safe speed. Indicates the standard speed data corresponding to the i+1th time node, ( ) represents the exponential function, Indicates the first time the function changes piecewise relative to The control adjustment coefficient, Indicates the second function segment change relative The control adjustment coefficient of Indicates all The variance of Use a multi-layer perceptron to take the initial function as the function layer, the standard speed data as the input layer, the power as the output layer, initialize the weight of each layer, and build the first network; Input the standard speed data into the first network, obtain a first activation value, obtain a predicted power output value in the output layer according to the first activation value, and obtain an actual output value in the function layer according to a preset starting power coefficient and the first activation value; Calculate the second activation value of the predicted power output value and the actual output value based on the loss function, iteratively adjust the weight and power coefficient of each layer, and when the second activation value is at the lowest loss, the power coefficient is the optimal coefficient; A performance curve of rotation speed-wind speed-power of the wind turbine generator set is constructed according to the optimal coefficient and the optimal parameter group.

5. The method for optimizing the power control of a wind turbine generator set according to claim 1, characterized in that: Use the MPPT algorithm to obtain the maximum power point of the performance curve, including: Obtain the mean of standard speed data in the wind turbine generator set, and generate an interference speed group based on mean screening and interference speeds whose absolute values ​​of mean differences are less than a preset interference threshold; The interference speed group is input into the performance curve, the interference power is output, and the power change corresponding to the mean of the interference power and the standard speed data is obtained. According to the power change, it is determined whether to increase or decrease the disturbance, and the mean of the standard speed data is adjusted to approach the maximum power point.

6. A wind turbine power optimization control method according to claim 1, characterized in that: According to the maximum power point and performance curve, the impeller speed is controlled to achieve maximum power in combination with the control algorithm, including: Obtain standard rotation speed data and standard wind speed data, output corresponding power data according to the performance curve, and obtain the power error between the actual power at any time node and the maximum power point; According to the power error at the time node, a control signal is generated based on a control algorithm, and the control signal is used to adjust the fan speed of the impeller.

7. A wind turbine power optimization control method according to claim 1, characterized in that: The control algorithm and MPPT algorithm are configured in the wind turbine control system, and optimization feedback is performed based on the error between the adjusted real power and the optimal power, including: The control algorithm and the MPPT algorithm are integrated as algorithm parts to obtain an integrated algorithm, and the integrated algorithm is configured into the control system of the wind turbine generator set, and the integrated algorithm is initialized based on the parameter part composed of the rated speed and the optimal parameter group; Start the wind turbine in a real environment, obtain the real wind speed data and real speed data, and control the wind turbine according to the integrated algorithm to obtain the real power; The error between the real power and the optimal power is calculated, and the parameters of the integrated algorithm are adjusted and optimized according to the error.

8. A wind turbine power optimization control method according to claim 7, characterized in that: Also includes: The wind speed threshold range of the impeller is obtained. When the wind speed of the environment is lower than the left end value of the wind speed threshold, the impeller is turned off. When the wind speed is higher than or lower than the right end value of the wind speed threshold, the impeller is also turned off.

Images