Intelligent control system capable of adjusting the speed of wind turbine generators

Abstract

The present invention relates to the field of speed control technology, and specifically to an intelligent control system capable of adjusting the speed of a wind turbine, comprising: monitoring wind field environmental data of an entire asynchronous wind field; collecting operating data of each wind turbine; generating a regional wind field difference model, wherein the regional wind field difference model reflects the dynamic distribution of wind resources in each region; a generator collaborative control demand generation module: based on the regional wind field difference model and the generator operating data, a nonlinear control algorithm is applied to calculate the optimal adjustment strategy for the generator operating data, and a collaborative control demand signal between generators is generated; based on the generated collaborative control demand signal between generators, distributed control of the speed, blade angle, and yaw angle is achieved between multiple generators in different wind speed areas. The present invention calculates the optimal adjustment strategy for the generator to ensure that when the wind speed in different regions varies greatly, the generators can operate in a collaborative and synchronous manner.

Description

Technical Field

[0001] The present invention relates to the technical field of rotational speed control, and in particular to an intelligent control system capable of adjusting the rotational speed of a wind turbine generator. Background Art

[0002] With the increasing demand for renewable energy, wind power generation has become an indispensable part of the energy sector. However, in practical applications, wind power generation faces many challenges, especially in asynchronous wind farms. Due to the significant differences in wind speed and direction in different areas, the operating status of wind turbines cannot be synchronized, affecting the power generation efficiency of the entire wind farm and the operating life of the equipment.

[0003] In large-scale wind farms, wind turbines are usually distributed in different wind conditions, and wind speeds and directions may be inconsistent. How to maximize the power generation efficiency of the entire wind farm by coordinating the speed control of multiple generators in such asynchronous wind farms, and how to avoid system instability caused by speed asynchrony among the generators, are key issues that require in-depth research.

[0004] In existing technologies, although some centralized control systems are used to adjust the speed and blade angle of wind turbines, most of these systems rely on unified environmental parameters and fail to fully consider the differences in wind speed and direction in different areas of an asynchronous wind farm. This approach not only reduces power generation efficiency, but may also cause speed asynchrony between wind turbines, further exacerbating mechanical wear and energy loss. In addition, existing control algorithms have a slow response speed when dealing with complex wind conditions and are unable to adapt to dynamic changes within the wind farm in real time. Summary of the Invention

[0005] The invention provides an intelligent control system capable of adjusting the rotation speed of a wind generator.

[0006] The intelligent control system capable of adjusting the speed of a wind turbine generator includes:

[0007] The wind farm environment monitoring module monitors the wind speed and direction of the entire asynchronous wind farm in real time and generates wind farm environment data;

[0008] Generator speed detection module, used to collect the real-time speed, blade angle, and yaw angle of each wind turbine and generate generator operation data;

[0009] Regional wind farm difference analysis module: Based on wind farm environmental data (wind speed, wind direction), it analyzes the wind speed and wind direction differences in different areas of the asynchronous wind farm and generates a regional wind farm difference model. The regional wind farm difference model reflects the dynamic distribution of wind resources in each area and guides the speed adjustment of generators in different areas.

[0010] Generator Coordinated Control Requirement Generation Module: Based on the regional wind field difference model and generator operating data (speed, blade angle, and yaw angle), and taking into account the geographical distribution distance between generators, a nonlinear control algorithm is applied to calculate the optimal adjustment strategy for generator operating data and generate inter-generator coordinated control demand signals to ensure the maximum power generation efficiency of each generator in asynchronous wind conditions;

[0011] Distributed multi-machine group control module: Based on the generated collaborative control demand signal between generators, distributed control of speed, blade angle, and yaw angle is achieved among multiple generators in different wind speed areas. By controlling their respective blade angles, yaw angles, and speeds, coordinated control between generators is achieved, reducing the problem of generator speed asynchrony caused by differences in wind speed and direction in the wind farm.

[0012] Optionally, the wind farm environment monitoring module includes a distributed meteorological sensor network, which is distributed in different areas of the asynchronous wind farm. Each meteorological sensor collects wind speed and wind direction data of the area in real time, and transmits the data to a central control unit via wireless communication. The central control unit performs standardized preprocessing based on meteorological data from multiple areas to form wind farm environment data.

[0013] Optionally, the generator speed detection module includes a multi-sensor combination installed on each wind turbine, including a speed sensor, a blade angle sensor and a yaw angle sensor. The speed sensor detects the speed data of the generator in real time, the blade angle sensor monitors the angle change of each blade, and the yaw angle sensor is used to measure the yaw angle of the generator relative to the wind direction. The generator controller integrates the data from each sensor to generate generator operation data.

[0014] Optionally, the regional wind field difference analysis module uses a spatiotemporal data analysis method to model the wind speed and wind direction changes in different regions based on the wind speed and wind direction data collected by the wind field environment monitoring module to generate a regional wind field difference model. The regional wind field difference model reflects the wind resource distribution characteristics of each region by analyzing the wind speed gradient, wind direction change trend and dynamic changes over time in each region, and is dynamically updated in the central control unit to guide wind turbines in different regions to coordinate speed adjustments according to wind speed and wind direction differences, so as to improve power generation efficiency and reduce the impact of wind imbalance between regions.

[0015] Optionally, the spatiotemporal data analysis method includes using Kriging interpolation to construct a spatial distribution model of the wind field, and combining it with time series analysis to obtain a regional wind field difference model;

[0016] The Kriging interpolation method is used to perform spatial interpolation of wind speed and wind direction in different areas of the asynchronous wind farm to generate a spatial wind speed distribution model, thereby analyzing the differences between regions;

[0017] Based on the Kriging interpolation results, using the known wind speed and wind direction values ​​in all regions, a spatial distribution model of wind speed and wind direction is generated, and the differences in wind speed and wind direction between regions are calculated;

[0018] Based on the calculation of the wind speed and wind direction differences between the regions, a regional wind field difference model M is generated. 风场差异 .

[0019] Optionally, the regional wind field difference model M 风场差异 Expressed as:

[0020] M 风场差异 ={(ΔV A-B ,Δθ A-B )|A,B∈wind farm area}, where ΔV A-B represents the wind speed difference between regions A and B, Δθ A-B Represents the difference in wind direction between areas A and B, where A and B represent any two areas.

[0021] Optionally, the generator collaborative control demand generation module specifically includes:

[0022] Input layer submodule: input current wind speed difference ΔV A-B , wind direction difference Δθ A-B and the speed n of each generator i , blade angle β i , yaw angle γ i ;

[0023] Introducing a nonlinear objective function, expressed as:

[0024] Where J represents the objective function, which reflects the deviation between the actual operating state of the current generator group and the optimal operating state.

[0025] f(n i ,β i ,γ i ) is the output power function of the i-th generator, based on the speed n i , blade angle β i , yaw angle γ i Calculate, f opt (V i ,θ i ) indicates the wind speed V i and wind direction θ i The best output power;

[0026] The constraints are:

[0027] a: The changes in speed, blade angle and yaw angle should comply with the mechanical and electrical limitations: nmin ≤n i ≤n max ,β min ≤β i ≤β max ,γ min ≤γ i ≤γ max ;

[0028] b: The speed difference between the generators is controlled within the allowable standard range to ensure the synchronization of coordinated control:

[0029] Output layer submodule: Calculate the optimal speed of each generator through fuzzy logic control optimization algorithm Blade angle and yaw angle This ensures that all generators operate synchronously in an asynchronous wind farm and generates a coordinated control demand signal between generators to adjust the operating parameters of the generators and maximize power generation efficiency.

[0030] Optionally, the output layer submodule calculates the optimal speed of each generator using a fuzzy logic control optimization algorithm. Blade angle and yaw angle Specifically include:

[0031] Define input and output variables:

[0032] The input variables include:

[0033] Wind speed difference ΔV A-B : represents the wind speed difference between areas A and B;

[0034] Wind direction difference Δθ A-B : Indicates the difference in wind direction between areas A and B;

[0035] Generator speed error Δn i =n ref -n i : Indicates the current speed of generator i and the reference speed n ref differences;

[0036] Blade angle error Δβ i =β ref -β i : represents the current blade angle of generator i and the reference blade angle β ref differences;

[0037] Yaw angle error Δγ i =γ ref -γ i: represents the current yaw angle of generator i and the reference yaw angle γ ref differences;

[0038] Output variables include:

[0039] Optimal speed The optimal speed of generator i;

[0040] Optimal blade angle The optimal blade angle of generator i;

[0041] Optimal yaw angle The optimal yaw angle of generator i;

[0042] Fuzzify input variables: Fuzzify the input variables and map them to fuzzy sets. Each fuzzy set is represented by a linguistic variable. Each variable has a corresponding membership function, which represents the degree of membership of the variable in each fuzzy set. For example, the membership function of wind speed difference can be defined as a triangular or trapezoidal function to represent the fuzzy range of different wind speed differences.

[0043] Build a fuzzy rule base: Based on the wind speed and direction differences and the current operating status of the generator, a set of fuzzy rules is constructed to guide how to adjust the generator speed, blade angle, and yaw angle. Each rule determines the direction and magnitude of the output (speed, blade angle, yaw angle) adjustment based on the current wind speed, wind direction, and generator operating status.

[0044] Fuzzy reasoning: The membership of the input variable is combined with the fuzzy rules through the fuzzy reasoning mechanism to obtain the fuzzy value of the output variable. The reasoning method adopts Mamdani reasoning;

[0045] Defuzzify output variables: Defuzzify the result of fuzzy inference, that is, the fuzzy output value, to obtain specific control output, including the optimal speed Blade angle and yaw angle The defuzzification method adopts the centroid method;

[0046] Generate a coordinated control demand signal: Based on the optimal speed, blade angle, and yaw angle of each generator, a coordinated control demand signal is generated to guide the synchronous operation of the generators. The coordinated control demand signal includes the following information:

[0047] Optimal speed Ensure that the generator i is adjusted to the optimal speed according to the current wind speed;

[0048] Optimal blade angle Ensure that the blade angle of the generator i is adjusted to the optimal state to maximize wind energy capture;

[0049] Optimal yaw angle Make sure the generator is facing the wind direction to improve power generation efficiency.

[0050] Optionally, the Mamdani reasoning:

[0051] For each rule, the minimum value of the input membership calculation result and the membership in the rule is calculated, that is, the membership in the input variable that best matches the rule is selected as the output membership of the rule;

[0052] The maximum output membership of all rules is calculated, that is, the one with the largest membership among multiple rules is selected as the final output membership.

[0053] Optionally, the centroid defuzzification is expressed as: Among them, u * is the defuzzified output value, including the optimal speed Optimal blade angle Optimal yaw angle u i For each possible value of the fuzzy output, μ i Indicates the membership degree corresponding to each output value. Through this method, the fuzzy output result is converted into a specific value to adjust the operating parameters of the generator.

[0054] Beneficial effects of the present invention:

[0055] The present invention uses a wind farm environment monitoring module and a regional wind farm difference analysis module, based on the Kriging interpolation method and spatiotemporal data analysis, to accurately analyze the differences in wind speed and direction in different areas of an asynchronous wind farm, and generate a dynamic regional wind farm difference model. This model can reflect the dynamic distribution of wind resources in real time, provide accurate environmental data input for the operating status of each generator, and through detailed modeling of wind speed and direction differences, ensure that the operating status of the generator in different areas of the asynchronous wind farm accurately matches the actual environment, avoiding the loss of power generation efficiency caused by ignoring regional wind speed differences in the existing technology.

[0056] The present invention introduces a nonlinear control algorithm, combines the generated wind field difference model with the real-time operating data of the generator (including the speed, blade angle and yaw angle), calculates the optimal adjustment strategy of the generator, and ensures that when the wind speed in different areas varies greatly, the generators can operate in a coordinated and synchronous manner. Through the fuzzy logic control method, the speed, blade angle and yaw angle of each generator are intelligently adjusted to maintain the speed difference between the generators within the allowable range. Compared with traditional control methods, the present invention exhibits higher response speed and control accuracy when dealing with complex wind conditions and wind speed fluctuations, effectively improving the power generation efficiency of the entire wind farm. BRIEF DESCRIPTION OF THE DRAWINGS

[0057] 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 only for the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0058] Figure 1 A schematic diagram of system logic of an embodiment of the present invention;

[0059] Figure 2 Schematic diagram of system function modules according to an embodiment of the present invention. DETAILED DESCRIPTION

[0060] The present invention is described in detail below with reference to the accompanying drawings and specific embodiments. It is also noted that, to provide a more detailed description, the following embodiments are best and preferred embodiments, and those skilled in the art may employ alternative methods for implementing certain known technologies. Furthermore, the accompanying drawings are intended only to provide a more detailed description of the embodiments and are not intended to limit the present invention.

[0061] like Figure 1-Figure 2 As shown, the intelligent control system capable of adjusting the speed of a wind turbine generator includes:

[0062] The wind farm environment monitoring module monitors the wind speed and direction of the entire asynchronous wind farm in real time and generates wind farm environment data;

[0063] Generator speed detection module, used to collect the real-time speed, blade angle, and yaw angle of each wind turbine and generate generator operation data;

[0064] Regional wind farm difference analysis module: Based on wind farm environmental data (wind speed, wind direction), it analyzes the wind speed and wind direction differences in different areas of the asynchronous wind farm and generates a regional wind farm difference model. The regional wind farm difference model reflects the dynamic distribution of wind resources in each region and guides the speed adjustment of generators in different regions.

[0065] Generator Coordinated Control Requirement Generation Module: Based on the regional wind field difference model and generator operating data (speed, blade angle, and yaw angle), and taking into account the geographical distribution distance between generators, a nonlinear control algorithm is applied to calculate the optimal adjustment strategy for generator operating data and generate inter-generator coordinated control demand signals to ensure the maximum power generation efficiency of each generator in asynchronous wind conditions;

[0066] Distributed multi-machine group control module: Based on the generated collaborative control demand signal between generators, distributed control of speed, blade angle, and yaw angle is achieved among multiple generators in different wind speed areas. By controlling their respective blade angles, yaw angles, and speeds, coordinated control between generators is achieved, reducing the problem of generator speed asynchrony caused by differences in wind speed and direction in the wind farm.

[0067] The wind farm environment monitoring module includes a distributed meteorological sensor network, which is distributed in different areas of the asynchronous wind farm. Each meteorological sensor collects wind speed and direction data in the area in real time and transmits the data to the central control unit via wireless communication. The central control unit performs standardized preprocessing based on the meteorological data of multiple areas to form wind farm environment data.

[0068] The generator speed detection module includes a multi-sensor combination installed on each wind turbine, including a speed sensor, a blade angle sensor and a yaw angle sensor. The speed sensor detects the speed data of the generator in real time, the blade angle sensor monitors the angle change of each blade, and the yaw angle sensor is used to measure the yaw angle of the generator relative to the wind direction. The generator controller integrates the data from each sensor to generate generator operation data.

[0069] The regional wind field difference analysis module is based on the wind speed and direction data collected by the wind field environment monitoring module. It uses the spatiotemporal data analysis method to model the changes in wind speed and wind direction in different regions and generate a regional wind field difference model. The regional wind field difference model reflects the wind resource distribution characteristics of each region by analyzing the wind speed gradient, wind direction change trend and dynamic changes over time in each region. It is dynamically updated in the central control unit to guide wind turbines in different regions to coordinate speed adjustments according to the differences in wind speed and wind direction, so as to improve power generation efficiency and reduce the impact of wind imbalance between regions.

[0070] The spatiotemporal data analysis method includes using Kriging interpolation to construct a spatial distribution model of the wind field, and combining it with time series analysis to obtain a regional wind field difference model;

[0071] Kriging interpolation is used to perform spatial interpolation of wind speed and direction in different areas of the asynchronous wind farm to generate a spatial wind speed distribution model, thereby analyzing the differences between regions;

[0072] The Kriging interpolation method is expressed as: Among them, x i is the wind speed or wind direction value position of a known point in the wind field, x0 represents the location of the wind speed or wind direction value to be predicted, Represents the wind speed or wind direction value at the predicted point x0, which is used as the representative wind speed or wind direction of a certain area in the regional wind field difference model. i ) represents the known point x iThe wind speed or wind direction value at the location comes from the wind speed and wind direction data in the wind farm environment monitoring module, λ i Is the weighting coefficient, which represents the weight of the predicted point x0 relative to each known point, satisfying

[0073] In order to determine the weighting coefficient λ i , the spatial correlation between wind speed and direction at different locations is calculated by semivariogram, which is expressed as:

[0074] Among them, γ(h) represents the semivariogram, which indicates the degree of difference in wind speed or direction between two points with a distance of h, N(h) represents the number of point pairs with a distance of h, and Z(x i ) and Z(x i +h) are the positions x i and point x at distance h i The wind speed or wind direction value at +h. The semivariogram describes the similarity of wind speed and wind direction at different locations. The smaller the value, the smaller the difference in wind speed and wind direction between two points at a distance of h.

[0075] Based on the Kriging interpolation results, using the known wind speed and direction values ​​in all regions, a spatial distribution model of wind speed and direction is generated to calculate the differences in wind speed and direction between regions;

[0076] The difference in wind speed and direction between any two areas A and B can be calculated using the following expressions:

[0077] Among them, ΔV represents the wind speed gradient between regions, ΔV A-B represents the difference in wind speed between areas A and B, and represents the predicted wind speed in areas A and B after Kriging interpolation. Similarly, the difference in wind direction can be calculated using the following expression:

[0078] Among them, Δθ represents the wind direction change rate between regions, Δθ A-B represents the difference in wind direction between areas A and B, and represents the predicted wind direction of areas A and B obtained after Kriging interpolation;

[0079] Based on the calculation of wind speed and wind direction differences between regions, a regional wind field difference model M is generated. 风场差异 .

[0080] Regional wind field difference model M 风场差异 Expressed as:

[0081] M 风场差异 ={(ΔV A-B,Δθ A-B )|A,B∈wind farm area}, where ΔV A-B represents the wind speed difference between regions A and B, Δθ A-B It represents the wind direction difference between regions A and B, where A and B represent any two regions. This model can be updated dynamically. As the wind speed and wind direction data collected in real time by the wind farm environment monitoring module change, the regional wind speed difference and wind direction difference will also be adjusted accordingly, reflecting the dynamic wind resource distribution in the asynchronous wind farm.

[0082] In order to further capture the wind speed gradient and wind direction change trend within the wind farm, the wind speed change between regions is expressed by the following formula: Where V(A) and V(B) are the wind speeds in regions A and B, respectively. A-B is the physical distance between areas A and B;

[0083] Similarly, the wind direction change trend can be expressed as: By calculating the wind speed gradient and wind direction change rate, the regional wind field difference model can be further refined, providing a more accurate reference for generator speed adjustment in different regions.

[0084] The generator collaborative control demand generation module specifically includes:

[0085] Input layer submodule: input current wind speed difference ΔV A-B , wind direction difference Δθ A-B and the speed n of each generator i , blade angle β i , yaw angle γ i ;

[0086] Introducing a nonlinear objective function, expressed as:

[0087] Where J represents the objective function, which reflects the deviation between the actual operating state of the current generator group and the optimal operating state.

[0088] f(n i ,β i ,γ i ) is the output power function of the i-th generator, based on the speed n i , blade angle β i , yaw angle γ i Calculate, f opt (V i ,θ i ) indicates the wind speed V i and wind direction θ i The best output power;

[0089] The constraints are:

[0090] a: The changes in speed, blade angle and yaw angle should comply with the mechanical and electrical limitations: n min ≤n i ≤n max ,β min ≤β i ≤β max ,γ min ≤γ i ≤γ max ;

[0091] b: The speed difference between the generators is controlled within the allowable standard range to ensure the synchronization of coordinated control:

[0092] Output layer submodule: Calculate the optimal speed of each generator through fuzzy logic control optimization algorithm Blade angle and yaw angle This ensures that all generators operate synchronously in an asynchronous wind farm and generates a coordinated control demand signal between generators to adjust the operating parameters of the generators and maximize power generation efficiency.

[0093] Electrical limitations are primarily related to the electrical performance of the generator, its power output characteristics, and the requirements for connection to the grid, including the maximum output power limit of the generator: the output power of a wind turbine is directly related to the rotational speed and wind speed. To avoid exceeding the design power of the generator, the rotational speed must be kept within a safe range to avoid damaging electrical components. The maximum output power of a wind turbine ranges from 1.5MW to 5MW, depending on the size and design of the unit.

[0094] Mechanical constraints are set based on the physical structure and operating characteristics of the wind turbine, and mainly involve the following aspects:

[0095] Speed ​​limit min ≤n i ≤n max : The speed limit of the generator is determined by the design of the generator and the maximum bearing capacity of the blades. Too high a speed will lead to increased mechanical losses and even cause structural damage to the blades; too low a speed will affect the power generation efficiency. The mechanical speed limit is between 6RPM and 20RPM, depending on the design of the generator. 6RPM is the minimum limit for the generator to start effective power generation, and about 20RPM is the maximum speed of the generator within the safe operating range.

[0096] Blade angle limit β min ≤β i ≤β max: The range of blade angle is set by the rotation mechanism of the wind turbine blades. Usually, the adjustment range of blade angle is 0 degrees (parallel to the wind direction, maximizing wind energy capture) to about 30 degrees (to reduce wind pressure). 0 degrees is the angle that maximizes wind energy capture, and 30 degrees is to avoid the angle that protects the generator in strong or extreme wind conditions.

[0097] Yaw angle limit γ min ≤γ i ≤γ max : The yaw angle refers to the rotation angle of the generator nacelle relative to the wind direction. The yaw angle can rotate within the range of -90 degrees to +90 degrees and is used to adjust the orientation of the generator to better capture wind energy.

[0098] In addition, in order to ensure the coordinated operation of generators in asynchronous wind farms, the speed difference between generators must be limited. Excessive speed difference between generators will lead to inconsistent output power of different generator sets, affecting the overall efficiency of the wind farm and possibly affecting the stability of the power grid. The maximum allowable speed difference is between 1RPM and 3RPM. This range is sufficient to cope with changes in wind speed and direction in asynchronous wind farms, while ensuring that the output power of the generator is within the stability range of the power grid.

[0099] The output layer submodule calculates the optimal speed of each generator through the fuzzy logic control optimization algorithm Blade angle and yaw angle Specifically include:

[0100] Define input and output variables:

[0101] The input variables include:

[0102] Wind speed difference ΔV A-B : represents the wind speed difference between areas A and B;

[0103] Wind direction difference Δθ A-B : Indicates the difference in wind direction between areas A and B;

[0104] Generator speed error Δn i =n ref -n i : Indicates the current speed of generator i and the reference speed n ref differences;

[0105] Blade angle error Δβ i =β ref -β i : represents the current blade angle of generator i and the reference blade angle β ref differences;

[0106] Yaw angle error Δγi =γ ref -γ i : represents the current yaw angle of generator i and the reference yaw angle γ ref differences;

[0107] Output variables include:

[0108] Optimal speed The optimal speed of generator i;

[0109] Optimal blade angle The optimal blade angle of generator i;

[0110] Optimal yaw angle The optimal yaw angle of generator i;

[0111] Fuzzify input variables: Fuzzify input variables and map them to fuzzy sets. Each fuzzy set is represented by a linguistic variable. Each variable has a corresponding membership function, which represents the degree of membership of the variable in each fuzzy set. For example, the membership function of wind speed difference can be defined as a triangular or trapezoidal function to represent the fuzzy range of different wind speed differences, as follows:

[0112] Wind speed difference ΔV A-B Divided into "low variance", "medium variance" and "high variance";

[0113] Wind direction difference Δθ A-B Divided into "small changes", "moderate changes", and "dramatic changes";

[0114] Speed ​​error Δn i Divided into "low speed", "normal speed" and "high speed";

[0115] Blade angle error Δβ i Divided into "small angle", "normal angle" and "large angle";

[0116] Yaw angle error Δγ i It is divided into "Insufficient yaw", "Normal yaw" and "Excessive yaw".

[0117] Construct a fuzzy rule base: Based on the wind speed and direction differences and the current operating status of the generator, a set of fuzzy rules is constructed to guide how to adjust the generator's speed, blade angle, and yaw angle. Each rule determines the adjustment direction and amplitude of the output (speed, blade angle, yaw angle) based on the current wind speed, wind direction, and generator operating status. For example:

[0118] Rule 1: If *Wind Speed ​​Difference* is *High Difference* and *Speed ​​Error* is *Speed ​​is Low, then *Increase the speed.

[0119] Rule 2: If the wind direction difference is drastically changing and the yaw angle error is too large, then reduce the yaw angle.

[0120] Rule 3: If the wind speed difference is medium and the blade angle error is small, increase the blade angle.

[0121] Fuzzy reasoning: The membership of the input variable is combined with the fuzzy rules through the fuzzy reasoning mechanism to obtain the fuzzy value of the output variable. The reasoning method adopts Mamdani reasoning;

[0122] Defuzzify output variables: Defuzzify the result of fuzzy inference, that is, the fuzzy output value, to obtain specific control output, including the optimal speed Blade angle and yaw angle The defuzzification method adopts the centroid method;

[0123] Generate a coordinated control demand signal: Based on the optimal speed, blade angle, and yaw angle of each generator, a coordinated control demand signal is generated to guide the synchronous operation of the generators. The coordinated control demand signal includes the following information:

[0124] Optimal speed Ensure that the generator i is adjusted to the optimal speed according to the current wind speed;

[0125] Optimal blade angle Ensure that the blade angle of the generator i is adjusted to the optimal state to maximize wind energy capture;

[0126] Optimal yaw angle Make sure the generator is facing the wind direction to improve power generation efficiency.

[0127] Mamdani reasoning:

[0128] For each rule, the minimum value of the input membership calculation result and the membership in the rule is calculated, that is, the membership in the input variable that best matches the rule is selected as the output membership of the rule;

[0129] The maximum output membership of all rules is calculated, that is, the one with the largest membership among multiple rules is selected as the final output membership.

[0130] The centroid defuzzification is expressed as: Among them, u * is the defuzzified output value, including the optimal speed Optimal blade angle Optimal yaw angle u i For each possible value of the fuzzy output, μ iIndicates the membership degree corresponding to each output value. Through this method, the fuzzy output result is converted into a specific value to adjust the operating parameters of the generator.

[0131] Based on the generated inter-generator coordinated control demand signal, the distributed multi-machine group control module implements distributed control of the speed, blade angle, and yaw angle of each generator in different wind speed regions through the following steps to ensure coordinated control between generators.

[0132] The generated inter-generator collaborative control demand signal is transmitted to each generator controller through the communication network, and each generator receives a control instruction containing its optimal speed, optimal blade angle and optimal yaw angle.

[0133] Speed ​​control: Each generator gradually adjusts its speed according to the speed control command it receives by adjusting the generator's pitch system or generator current, so that its speed remains within the allowable difference range with other generators to ensure synchronous operation of generators in different wind speed areas.

[0134] Blade angle control: Each generator adjusts the blade's windward angle according to the blade angle control command it receives to optimize wind energy capture efficiency. The blade angle adjustment is achieved through an electric or hydraulic control system to ensure that generators in different wind speed areas can flexibly adjust the blade angle according to wind speed differences to avoid mechanical damage when the wind is too strong.

[0135] Yaw angle control: Each generator adjusts the orientation of the generator nacelle through the yaw system based on the yaw angle control command it receives, so that it is consistent with the wind direction. The yaw system automatically detects changes in wind direction and combines the yaw angle commands between generators to ensure that generators in different areas face their respective optimal wind directions, thereby improving power generation efficiency.

[0136] Distributed feedback regulation: Through the status sensors of each generator (including speed sensors, blade angle sensors and yaw angle sensors), the current status data of the generator is fed back to the central control unit in real time. The central control unit performs dynamic evaluation based on the feedback data and sends adjusted control signals to each generator to achieve distributed real-time optimization and coordinated control.

[0137] Each generator is gradually adjusted to the optimal operating state through distributed speed, blade angle and yaw angle control in different wind speed areas, ensuring synchronous control between generators, reducing operational inconsistencies caused by differences in wind speed and direction, and thereby improving the power generation efficiency of the entire wind farm.

[0138] The present invention encompasses any alternatives, modifications, equivalents, and solutions that fall within the spirit and scope of the present invention. To provide a thorough understanding of the present invention, specific details are described in detail below in connection with the preferred embodiments of the present invention, but those skilled in the art will be able to fully understand the present invention without these detailed descriptions. Furthermore, to avoid unnecessary confusion regarding the essence of the present invention, well-known methods, processes, procedures, components, and circuits have not been described in detail.

[0139] The above is only a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present invention. These improvements and modifications should also be regarded as within the scope of protection of the present invention.

Claims

1. An intelligent control system capable of adjusting the speed of a wind turbine generator, characterized in that: include: The wind farm environment monitoring module monitors the wind speed and direction of the entire asynchronous wind farm in real time and generates wind farm environment data; Generator speed detection module, used to collect the real-time speed, blade angle, and yaw angle of each wind turbine and generate generator operation data; Regional wind farm difference analysis module: Based on wind farm environmental data, it analyzes the differences in wind speed and direction in different areas of the asynchronous wind farm and generates a regional wind farm difference model that reflects the dynamic distribution of wind resources in each area. Generator collaborative control demand generation module: Based on the regional wind farm difference model and generator operating data, it applies nonlinear control algorithms to calculate the optimal adjustment strategy for generator operating data and generates inter-generator collaborative control demand signals; Distributed multi-machine group control module: Based on the generated inter-generator coordinated control demand signal, it realizes distributed control of speed, blade angle, and yaw angle among multiple generators in different wind speed areas. Coordinated control between generators is achieved by controlling their respective blade angles, yaw angles, and speed. The generator collaborative control demand generation module specifically includes: Input layer submodule: input current wind speed difference ΔV A-B , wind direction difference Δθ A-B and the speed n of each generator i , blade angle β i , yaw angle γ i ; Introducing a nonlinear objective function, expressed as: Where J represents the objective function, which reflects the deviation between the actual operating state of the current generator group and the optimal operating state, f(n i ,β i ,γ i ) is the output power function of the i-th generator, based on the speed n i , blade angle β i , yaw angle γ i Calculate, f opt (V i ,θ i ) indicates the wind speed V i and wind direction θ i The best output power; The constraints are: a: The changes in speed, blade angle and yaw angle should comply with the mechanical and electrical limitations: n min ≤n i ≤n max ,β min ≤β i ≤β max ,γ min ≤γ i ≤γ max ; b: The speed difference between the generators is controlled within the allowable standard range to ensure the synchronization of coordinated control: Output layer submodule: Calculate the optimal speed of each generator through fuzzy logic control optimization algorithm Blade angle and yaw angle To ensure that each generator operates synchronously in an asynchronous wind farm and generate a coordinated control demand signal between generators.

2. The intelligent control system capable of adjusting the speed of a wind turbine generator according to claim 1, characterized in that: The wind farm environment monitoring module includes a distributed meteorological sensor network, which is distributed in different areas of the asynchronous wind farm. Each meteorological sensor collects wind speed and wind direction data in the area in real time and transmits the data to a central control unit via wireless communication. The central control unit performs standardized preprocessing based on the meteorological data of multiple areas to form wind farm environment data.

3. The intelligent control system capable of adjusting the speed of a wind turbine generator according to claim 1, characterized in that: The generator speed detection module includes a multi-sensor combination installed on each wind turbine, including a speed sensor, a blade angle sensor and a yaw angle sensor. The speed sensor detects the speed data of the generator in real time, the blade angle sensor monitors the angle change of each blade, and the yaw angle sensor is used to measure the yaw angle of the generator relative to the wind direction. The generator controller integrates the data from each sensor to generate generator operation data.

4. The intelligent control system capable of adjusting the speed of a wind turbine generator according to claim 1, characterized in that: The regional wind field difference analysis module is based on the wind speed and wind direction data collected by the wind field environment monitoring module, and uses the spatiotemporal data analysis method to model the wind speed and wind direction changes in different regions to generate a regional wind field difference model. The regional wind field difference model reflects the wind resource distribution characteristics of each region by analyzing the wind speed gradient, wind direction change trend and dynamic changes over time in each region, and is dynamically updated in the central control unit.

5. The intelligent control system capable of adjusting the speed of a wind turbine generator according to claim 4, characterized in that: The spatiotemporal data analysis method includes using Kriging interpolation to construct a spatial distribution model of the wind field, and combining it with time series analysis to obtain a regional wind field difference model; The Kriging interpolation method is used to perform spatial interpolation of wind speed and wind direction in different areas of the asynchronous wind farm to generate a spatial wind speed distribution model, thereby analyzing the differences between regions; Based on the Kriging interpolation results, using the known wind speed and wind direction values ​​in all regions, a spatial distribution model of wind speed and wind direction is generated, and the differences in wind speed and wind direction between regions are calculated; Based on the calculation of the wind speed and wind direction differences between the regions, a regional wind field difference model M is generated. 风场差异 .

6. The intelligent control system capable of adjusting the speed of a wind turbine generator according to claim 5, characterized in that: The regional wind field difference model M 风场差异 Expressed as: M 风场差异 ={(ΔV A-B ,Δθ A-B )|A,B∈wind farm area}, where ΔV A-B represents the wind speed difference between regions A and B, Δθ A-B Represents the difference in wind direction between areas A and B, where A and B represent any two areas.

7. The intelligent control system capable of adjusting the speed of a wind turbine generator according to claim 1, characterized in that: The output layer submodule calculates the optimal speed of each generator through the fuzzy logic control optimization algorithm Blade angle and yaw angle Specifically include: Define input variables and output variables: Input variables include wind speed difference ΔV A-B , wind direction difference Δθ A-B , generator speed error Δn i , blade angle error Δβ i and the yaw angle error Δγ i ; Output variables include optimal speed Optimal blade angle And the optimal yaw angle Fuzzify input variables: Fuzzify input variables and map them to fuzzy sets. Each fuzzy set is represented by a linguistic variable, and each variable has a corresponding membership function, which represents the degree of membership of the variable in each fuzzy set. Build a fuzzy rule base: Based on wind speed and direction differences and the current operating status of the generator, a set of fuzzy rules is constructed to guide how to adjust the generator's speed, blade angle, and yaw angle. Each rule determines the direction and magnitude of output adjustment based on the current wind speed, wind direction, and generator operating status. Fuzzy reasoning: The membership of the input variable is combined with the fuzzy rules through the fuzzy reasoning mechanism to obtain the fuzzy value of the output variable. The reasoning method adopts Mamdani reasoning; Defuzzify output variables: Defuzzify the result of fuzzy inference, that is, the fuzzy output value, to obtain specific control output, including the optimal speed Blade angle and yaw angle The defuzzification method adopts the centroid method; Generate collaborative control demand signals: Based on the optimal speed, blade angle and yaw angle of each generator, a collaborative control demand signal is generated to guide the synchronous operation of the generators.

8. The intelligent control system capable of adjusting the speed of a wind turbine generator according to claim 7, characterized in that: The Mamdani reasoning: For each rule, the minimum value of the input membership calculation result and the membership in the rule is calculated, that is, the membership in the input variable that best matches the rule is selected as the output membership of the rule; The maximum output membership of all rules is calculated, that is, the one with the largest membership among multiple rules is selected as the final output membership.

9. The intelligent control system capable of adjusting the speed of a wind turbine generator according to claim 7, characterized in that: The centroid defuzzification is expressed as: Among them, u * is the defuzzified output value, including the optimal speed Optimal blade angle Optimal yaw angle u i For each possible value of the fuzzy output, μ i Indicates the membership degree corresponding to each output value.

Images