Torque control method, system and computer-readable medium for variable-speed and variable-pitch wind turbine generator set

Abstract

The present invention provides a torque control method, system and computer-readable medium for a variable-speed and variable-pitch wind turbine generator set. Based on the construction of a discrete model including aerodynamics, a transmission chain and a pitch mechanism, the method designs a rolling optimization method for torque and pitch commands based on model predictive control (MPC) and sliding surface constraints, combines adaptive sliding surface design to enhance robustness, dynamically adjusts the control gain through fuzzy logic, and further takes into account power tracking accuracy and mechanical loss suppression; at the same time, it is supplemented by wind speed prediction feedforward compensation to reduce delay, has high robustness and adaptability, can effectively cope with wind speed fluctuations and time-varying parameters, protects equipment while ensuring power generation efficiency, and provides an efficient and reliable solution for wind power generation control.

Description

Technical Field

[0001] The present invention relates to the technical field of wind power generation control, in particular to torque control of a generator set, and more particularly to a method, system and computer-readable medium for torque control of a variable-speed and variable-pitch wind generator set. Background Art

[0002] The variable pitch system of a wind turbine is the core part of the wind turbine control system and plays a key role in the safe, stable and efficient operation of the unit. Stable variable pitch control is a difficult point in the research of control technology for large wind turbines. Variable speed pitch regulation combines the advantages of variable speed fixed pitch control and constant speed variable pitch control and is the mainstream pitch control strategy. The main goal of a variable speed variable pitch unit is to maximize energy capture at different wind speeds, so that the unit operates on the ideal power curve of the wind speed model, while ensuring the safe and stable operation of the unit. Current typical control strategies include PID-based control, model predictive control (MPC), sliding mode control (SMC), fuzzy logic or neural network control methods.

[0003] Traditional PID control was the first control strategy proposed. Its control system structure is simple and easy to implement. It adjusts torque error through proportional, integral, and differential steps to maintain power tracking. However, PID parameters struggle to maintain optimality under conditions of large wind speed variations or rate of change, resulting in insufficient dynamic response, overshoot, or oscillation. Furthermore, PID lacks adaptability to nonlinear systems, especially with sudden wind speed changes or turbulence, and its control effectiveness is suboptimal. Traditional model predictive control (MPC) strategies utilize precise models to predict future states and optimize control inputs. However, uncertainties in wind turbine models, such as changes in aerodynamic parameters, often degrade the performance of MPC's precise model, leading to deficiencies in the accuracy and robustness of predictive control. Sliding mode control (SMC) offers strong adaptability and robustness. By designing a sliding surface, it forces the system trajectory to converge to the desired state, effectively suppressing parameter changes and external disturbances. However, sliding mode control can introduce chattering, which, particularly in practical systems, can affect the life of mechanical components, such as increased wear of the pitch mechanism. Designing an appropriate sliding surface and control law requires considerable experience, making implementation and tuning difficult, thus impacting control effectiveness. Summary of the Invention

[0004] In view of the defects and shortcomings of the existing technology, the purpose of the present invention is to provide a torque control method and system for a variable-speed and variable-pitch wind turbine generator set. Through a hierarchical control architecture and multi-technology integration, a full closed-loop system from data acquisition, model identification to intelligent control is constructed to achieve the dual goals of efficient and stable power generation and equipment protection.

[0005] According to a first aspect of the present invention, a method for controlling torque of a variable-speed and variable-pitch wind turbine generator set is provided, wherein the method comprises the following steps:

[0006] Step 1: Obtain state sampling signals of the wind turbine generator set, including wind speed signal, unit speed, torque and pitch angle, align the unit speed, torque and pitch angle with the wind speed signal, and calculate the tip speed ratio λ;

[0007] Step 2: Construct an improved blade element momentum model Pmech = f(C p ,β,λ), used to characterize the wind energy capture efficiency C p The dynamic relationship between the tip speed ratio λ and the pitch angle β is calculated, and the parameter estimation value is updated in real time based on the recursive least squares method to achieve online identification and update C p ;

[0008] Step 3: constructing a multi-objective prediction model based on the improved blade element momentum model, the generator set drive chain dynamic model, and the pitch actuator model, and using the forward Euler method for discretization to obtain a discretized state space model;

[0009] Step 4: Based on the power tracking error, an adaptive sliding surface with an integral term is designed to eliminate the steady-state error through the integral term, and fuzzy logic dynamic adjustment is achieved through time-varying gain;

[0010] Step 5: Using the dynamically adjusted sliding surface as the core constraint, optimize the objective function of the discretized state-space model and convert it into a convex optimization method for solution. Based on the continuous reaching law design, use the hyperbolic tangent function to approximate the sign function to achieve continuous chattering suppression, and output the optimal control sequence for the next N steps; and

[0011] Step 6: Perform coordinated control of pitch and torque according to the optimal control sequence.

[0012] According to a second aspect of the present invention, a computer system is provided, comprising:

[0013] one or more processors;

[0014] The memory stores operable instructions, which, when executed by the one or more processors, enable the one or more processors to perform operations, including the process of executing the aforementioned variable-speed and variable-pitch wind turbine torque control method.

[0015] According to a third aspect of the present invention, a computer-readable medium storing software is proposed, wherein the software includes instructions that can be executed by one or more computers, and when the instructions are executed by the one or more computers, the process of the aforementioned variable-speed and variable-pitch wind turbine torque control method is performed.

[0016] The torque control method of the variable-speed and variable-pitch wind turbine generator set according to the above embodiment of the present invention realizes the coordinated action of torque and pitch angle based on the predictive control strategy of adaptive sliding mode, utilizes the rolling optimization of MPC to process multivariable constraints, improves the dynamic response speed, and reduces overshoot and oscillation; at the same time, an adaptive sliding mode is adopted to compensate for model uncertainty and disturbance, and a robust control kernel with both steady-state accuracy and dynamic adaptability is constructed through integral term compensation, fuzzy logic dynamic gain adjustment, and continuous convergence law optimization to suppress the jitter influence of random fluctuations in wind speed, time-varying characteristics of blade aerodynamic parameters (such as power coefficient attenuation caused by aging and icing), and uncertainty of transmission chain damping on the control algorithm; further introduces wind speed prediction information to drive feedforward control, adjusts the control strategy in advance, and adjusts the torque set value in advance when the wind speed change is predicted to compensate for disturbances and smooth power output and mechanical load in advance, thereby improving control accuracy.

[0017] It should be understood that all combinations of the foregoing concepts and the additional concepts described in more detail below, as long as such concepts are not mutually inconsistent, can be considered part of the inventive subject matter of this disclosure. In addition, all combinations of the claimed subject matter are considered part of the inventive subject matter of this disclosure.

[0018] The foregoing and other aspects, embodiments, and features of the present invention will be more fully understood from the following description in conjunction with the accompanying drawings. Other additional aspects of the present invention, such as features and / or beneficial effects of the exemplary embodiments, will become apparent from the following description or through practice of specific embodiments according to the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] The accompanying drawings are not intended to be drawn to scale. In the accompanying drawings, each identical or nearly identical component shown in various figures may be represented by the same reference numeral. For clarity, not every component is labeled in every figure. Embodiments of various aspects of the present invention will now be described by way of example and with reference to the accompanying drawings.

[0020] Figure 1 1 is a flow chart of a torque control method for a variable speed and variable pitch wind turbine generator set according to an embodiment of the present invention.

[0021] Figure 2 4 is a schematic diagram of a torque control method for a variable speed and variable pitch wind turbine generator set according to an embodiment of the present invention. DETAILED DESCRIPTION

[0022] In order to better understand the technical content of the present invention, specific embodiments are given and described below with reference to the accompanying drawings.

[0023] Various aspects of the present invention are described in this disclosure with reference to the accompanying drawings, in which a number of illustrative embodiments are shown. The embodiments of the present disclosure are not necessarily intended to include all aspects of the present invention. It should be understood that the various concepts and embodiments introduced above, as well as those described in more detail below, can be implemented in any of many ways, because the concepts and embodiments disclosed herein are not limited to any embodiment. In addition, some aspects of the present disclosure may be used alone or in any appropriate combination with other aspects disclosed herein.

[0024] {Example 1}

[0025] According to the torque control method of a variable-speed and variable-pitch wind turbine generator set in an embodiment of the present invention, on the basis of constructing a discrete model including aerodynamics, transmission chain and pitch mechanism, a rolling optimization method of torque and pitch instructions based on model predictive control (MPC) and sliding surface constraints is designed, and the robustness is enhanced by combining the adaptive sliding surface design. The control gain is dynamically adjusted through fuzzy logic to further take into account the power tracking accuracy and mechanical loss suppression; at the same time, wind speed prediction feedforward compensation is used to reduce delay. It has high robustness and adaptability, can effectively cope with wind speed fluctuations and time-varying parameters, protect equipment while ensuring power generation efficiency, and provide an efficient and reliable solution for wind power generation control.

[0026] Combined with attachment Figure 1 、 Figure 2 The torque control method of the variable speed and variable pitch wind turbine generator set of the embodiment shown includes the following steps:

[0027] Step 1: Obtain state sampling signals of the wind turbine generator set, including wind speed signal, unit speed, torque and pitch angle, align the unit speed, torque and pitch angle with the wind speed signal, and calculate the tip speed ratio λ;

[0028] Step 2: Construct an improved blade element momentum model Pmech = f(C p ,β,λ), used to characterize the wind energy capture efficiency (also known as power coefficient) C p The dynamic relationship between the tip speed ratio λ and the pitch angle β is calculated, and the parameter estimation value is updated in real time based on the recursive least squares method to achieve online identification and update C p ;

[0029] Step 3: constructing a multi-objective prediction model based on the improved blade element momentum model, the generator set drive chain dynamic model, and the pitch actuator model, and using the forward Euler method for discretization to obtain a discretized state space model;

[0030] Step 4: Based on the power tracking error, an adaptive sliding surface with an integral term is designed to eliminate the steady-state error through the integral term, and fuzzy logic dynamic adjustment is achieved through time-varying gain;

[0031] Step 5: Using the dynamically adjusted sliding surface as the core constraint, optimize the objective function of the discretized state-space model and convert it into a convex optimization method for solution. Based on the continuous reaching law design, use the hyperbolic tangent function to approximate the sign function to achieve continuous chattering suppression, and output the optimal control sequence for the next N steps; and

[0032] Step 6: Perform coordinated control of pitch and torque according to the optimal control sequence.

[0033] As an optional implementation, in step 1, the turbine speed, torque, and pitch angle are aligned with the wind speed signal to calculate the tip speed ratio λ, including:

[0034] Based on the wind speed signal timestamp, the sampling frequency is unified to 100 Hz, that is, the time step Δt = 0.01s, and the unit speed ω(t), torque τ(t) and pitch angle β(t) are linearly interpolated so that the collected signals are at the same time point t i =i·Δt alignment; ω(t), τ(t), β(t) represent the sampling values ​​at the corresponding time t respectively;

[0035] Calculate the tip speed ratio λ, λ = ω(t)*R / v(t), where R is the radius of the wind turbine blade in meters; v(t) is the wind speed at time i in meters per second.

[0036] It should be understood that in an optional embodiment of the present invention, based on the collected data, the sensor raw signals (such as ω(t), τ(t), β(t), and v(t)) can be further preprocessed, especially denoising. For example, a wavelet threshold denoising algorithm (sym4 wavelet basis, 5-layer decomposition, with approximate symmetry, suitable for transient signals) is used to perform a 5-layer wavelet decomposition on the raw signal to obtain high-frequency coefficients (noise is mainly concentrated in the high frequency). A soft threshold function is then applied to the high-frequency coefficients (the threshold is set to 3 times the standard deviation of the noise) to retain the low-frequency trend components; the signal is then reconstructed to obtain a smooth signal sequence. Thus, by separating noise and valid signals through multi-resolution analysis and combining hard threshold processing to retain low-frequency components, noise removal and signal detail retention (true wind speed trend) are achieved.

[0037] Based on the denoised data, data synchronization and resampling are further performed. That is, synchronization is performed according to the sampling frequency of 100 Hz. With the wind speed signal timestamp as the benchmark, linear interpolation is performed on ω(t), τ(t), and β(t) to ensure that all signals are aligned at the same time point.

[0038] Thus, obtaining a unified data set is beneficial for subsequent modeling and data processing.

[0039] As an optional implementation, in step 2, an improved blade element momentum model is constructed:

[0040] Pmech=f(C p ,β,λ);

[0041] Used to characterize the wind energy capture efficiency C p The dynamic relationship between the tip speed ratio λ and the pitch angle β is calculated, and the parameter estimation value is updated in real time based on the recursive least squares method to achieve online identification and update C p ,include:

[0042] Step 2-1: Construct an improved blade element momentum model Pmech = f(Cp, β, λ) and establish a direct mapping between the wind energy capture efficiency Cp and the input variables λ and β. The specific expression is as follows:

[0043] Pmech(t)=ρπR 2 v(t) 3 Cp

[0044] Where ρ represents the air density, ρ = 1.225 kg / m 3 , the standard air density is taken (can be corrected according to temperature and altitude);

[0045] Step 2-2: Wind energy capture efficiency C p Approximately in polynomial form:

[0046] Cp=k1λ+k2β+k3λ 2 +k4β 2 +k5λβ

[0047] Where k1, k2, k3, k4, and k5 are the coefficients of the polynomials, respectively, reflecting the coupled effects of the tip speed ratio λ and the pitch angle β on the aerodynamic efficiency. This simplifies the complex Cp(λ,β) curve into a linear combination that can be identified online.

[0048] Step 2-3, according to C p The polynomial expression and measured power Pmech(t)=ρπR 2 v(t) 3 C p , construct a linear regression model: Y = Φ(t)θ+∈(t);

[0049] Output Y(t) = Pmech(t), representing the measured mechanical power, calculated from the measured τ(t) * ω(t) (based on the core formula of BEM theory, with Cp calculated from the measured value substituted in real time);

[0050] Special vector Φ(t)=[λ(t),β(t),λ(t) 2 ,β(t),λ(t)β(t)];

[0051] Parameter vector θ = [k1, k2, k3, k4, k5] T ;

[0052] Where, ∈(t) represents the modeling error, which obeys the normal distribution;

[0053] Step 2-4: Use the recursive least squares method to update the calculation in real time at a frequency of 10 Hz to obtain the parameter vector θ that is updated in real time, and then dynamically update C p Model parameters are adjusted to avoid characteristic changes caused by factors such as blade contamination and aging, and priority is given to tracking the latest operating conditions.

[0054] As an optional implementation, in step 3, a multi-objective prediction model is constructed based on the improved blade element momentum model, the generator set drive chain dynamic model, and the pitch actuator model, and the forward Euler method is used for discretization processing to obtain a discretized state space model, including:

[0055] Step 3-1: Based on the Newton-Euler equation to describe the mechanical dynamics, a dynamic model of the generator set transmission chain is constructed, which is expressed as follows:

[0056]

[0057] Among them, T aero =P mech / ω, represents the aerodynamic torque, the unit is N·m; T gen =K τ u T , represents the electromagnetic torque, K τ is the generator torque coefficient, u T is the torque control input; J is the moment of inertia (including blades, gearbox, and generator), in kg·m 2 ; B is the viscous damping coefficient, unit is N·m·s / rad;

[0058] Step 3-2: Establish a pitch actuator model based on the first-order inertia link, which is expressed as follows:

[0059]

[0060] Among them, T β Represents the pitch time constant, which is used to characterize the mechanical response speed; K β Indicates gain, which is used to characterize the input-output ratio; u β is the pitch control input; in this example, the pitch time constant T can be selected β =0.2s, gain K β =1.2, used to control the input-output ratio;

[0061] Step 3-3: Based on the time step Δt (using 0.01s, Nyquist frequency ≥ 50Hz, taking into account both calculation accuracy and real-time performance), the forward Euler method is used for discretization to obtain the discretized state space model, including:

[0062] Define the state variables as follows:

[0063]

[0064] Obtain the discrete state equation:

[0065] The speed is updated as:

[0066] The pitch angle is updated as:

[0067] in,

[0068] Therefore, the calculation is simplified by explicit discretization, avoiding the time-consuming iteration of implicit methods.

[0069] As an optional implementation, in step 4, the adaptive sliding surface with an integral term introduced based on the power tracking error design eliminates the steady-state error through the integral term, and implements fuzzy logic dynamic adjustment through a time-varying gain, including:

[0070] Step 4-1. Define the power tracking error e(k):

[0071] e(k)=Pref(k)-Pmech(k)

[0072] Where Pref(k) represents the reference power, which is determined according to the preset maximum power tracking curve of wind speed or grid instruction;

[0073] It should be understood that in the embodiment of the present invention, the power generation control goal is to make the actual power generation close to the ideal value. If there is an error, it is controlled and adjusted through the sliding surface, which is the core constraint;

[0074] Step 4-2: Design the adaptive sliding surface σ(k) with integral term:

[0075]

[0076] In the formula, the integral term ∑e(i)Δt is used to eliminate the steady-state error, represents the error change rate;

[0077] Wherein, k(t) represents the time-varying gain: k(t)=k0+Δk(t), k0 represents the initial value of the time-varying gain, and Δk(t) represents the gain adjustment amount;

[0078] According to the power tracking error e(k) and the error change rate Dynamically adjust Δk(t) and further dynamically update the time-varying gain k(t) to realize the dynamically adjusted sliding surface σ(k) and enhance the adaptability to different working conditions.

[0079] Therefore, by designing a time-varying gain, the dynamically updated justice adjustment amount is directly superimposed on the initial gain, and dynamically adjusted through fuzzy logic to adapt to different wind speed conditions (for example, increasing the gain in strong gusts to speed up the response);

[0080] In step 4-2, the process of dynamically updating the time-varying gain k(t) includes:

[0081] Input power tracking error e(k) and error change rate Normalized to [-1,1];

[0082] According to the fuzzy rule base design, the output gain adjustment value Δk(t) is in the domain [-0.5, 0.5];

[0083] Among them, the triangular function is divided into {negative large, negative small, zero, positive small, positive large}, and the fuzzy rule base is designed as follows: if e(k) is positive and If the positive value is large, the gain adjustment Δk(t) is large, which enhances the integral effect; if the negative value of e(k) is small and If Δk(t) is zero, the gain adjustment amount Δk(t) is small, suppressing overshoot; and

[0084] The time-varying gain k(t) is dynamically updated according to k(t)=k0+Δk(t), where the initial value k0 of the time-varying gain is set to 0.1, and the sliding surface σ(k) is dynamically adjusted.

[0085] Therefore, the adaptive dynamic update logic of "strong integration for large errors and weak integration for small errors" is realized through the rule base, and the response speed and overshoot are balanced through dynamic adaptive changes of time-varying gain.

[0086] As an optional implementation, in step 5, the dynamically adjusted sliding surface is used as the core constraint to optimize the objective function of the discretized state space model and convert it into a convex optimization solution to predict the control input sequence {u T (k),u β (k)}, and based on the continuous reaching law design, the hyperbolic tangent function is used to approximate the sign function to achieve continuous chattering suppression and output the optimal control sequence for the next N steps, including:

[0087] Step 5-1: Using the dynamically adjusted sliding surface as the core constraint, determine the optimization objective function as follows:

[0088]

[0089] Where Q represents the power tracking error weight matrix, which takes the value of diag(1,…,1); P represents the control input smoothness weight matrix, which takes the value of diag(r T ,…,r β ); Torque control input weight r T =10 -6 , to avoid drastic changes in current; pitch rate weight r β =10 -3 , designed to protect the servo motor;

[0090] Indicates the torque limit constraint, which is determined by the generator capacity (rated torque), such as [-3000 N·m, 3000 N·m];

[0091] |uβ(k+i)|≤15° / s, which represents the pitch rate limit constraint and determines the mechanical safety constraint (usually the maximum rate is constrained to 15° / s to prevent the blades from rotating too fast);

[0092] Therefore, the power tracking term forces Pmech(t) to be close to Pref, the integral characteristic of the sliding mode surface is used to eliminate the steady-state deviation, and the control smoothing term is used to penalize frequent torque adjustment (reduce gearbox shock) and rapid pitch change (reduce mechanical wear);

[0093] Step 5-2: The optimization objective function is quadratic and the constraints are linear. Convert it to a quadratic programming (QP) problem and solve it using the interior point method. In this example, IPOPT is used. The open source library qpoases is called. The input matrix dimension is 2N*2N. When the step size N=10, the input matrix dimension is 20×20. The single solution time is less than 3ms (satisfying a 100Hz control period).

[0094] Furthermore, based on the continuous reaching law, the hyperbolic tangent function is used to approximate the sign function to suppress the sliding mode control chattering (i.e., mechanical chattering caused by high-frequency switching):

[0095] u(k)=-κtanh(σ(k) / F)

[0096] Here, κ represents the control strength, which is set to 500 in this example and is used to control the response strength to the sliding surface error. F represents the boundary layer thickness, which is set to 0.1 and is used to control the reduction of high-frequency switching, that is, to reduce high-frequency oscillations through smooth switching.

[0097] Therefore, by solving, the optimal control input sequence {u T (k),u β (k)}, for example, N = 10, which means predicting the optimal control input sequence in the 100ms time domain.

[0098] It should be understood that in other embodiments, iteration may be performed using other convex optimization solution methods, such as gradient descent solution, which will not be described in detail here.

[0099] In an optional embodiment, implicit constraints can be further processed by limiting the pitch angle range and the speed safety interval in the aerodynamic model, such as the pitch angle range [0°, 90°] and the speed safety interval [0, ωrated], and adding state boundary constraints (saturation constraints) to the prediction model to prevent state out-of-bounds.

[0100] Therefore, the adaptive sliding surface design forces the system state to converge along the preset sliding surface through integral terms and fuzzy logic. Even when there are large perturbations in the blade aerodynamic parameters, the power tracking error can still be guaranteed to operate within ±5% of the rated power (the traditional PID control error is expanded to ±10% to ±15%).

[0101] For external interference to sudden gusts of wind (wind speed mutation rate > 5m / s), the system response delay is less than 0.1 second. The hyperbolic tangent function is used to suppress vibration and control the torque fluctuation amplitude to ±10% of the rated torque, effectively protecting the gearbox and generator.

[0102] As an optional implementation, in step 6, according to the optimal control sequence, the pitch moment and torque are coordinated and controlled, including the coordinated control of the generator converter and the pitch servo motor, as follows:

[0103] Step 6-1: Torque command conversion, tracking T through the current loop of the generator converter cmd :

[0104] T cmd =K τ u T (k)

[0105] Step 6-2: Based on the wind speed prediction value v pred (k+1) drives feedforward compensation to obtain feedforward torque T ff :

[0106] Feedforward torque T ff =1 / 2*ρπR 2 v pred (k+1) 3 Cp(λpred,β(k)) / λpred;

[0107] Where λpred=ω(k)R / v pred (k+1), used to compensate for the change in aerodynamic torque to reduce the impact of feedback delay (about 50ms);

[0108] Step 6-3, pitch angle control command β cmd Conversion:

[0109] β cmd =β trim +K β u β (k)

[0110] β trim Indicates the pitch angle reference angle, which is preset according to the average wind speed (for example, β trim =0°, increases at high wind speeds to unload power); K β u β (k) represents the real-time adjustment of the pitch angle, which is calculated from the optimization results; K β Indicates the gain of the pitch mechanism, which can be calibrated through actual measurement;

[0111] Step 6-4: Send torque control command T cmd +T ff To the converter for torque control and send pitch angle control command β cmd The pitch angle is controlled by the pitch angle servo motor, for example, it is sent to the actuator (converter, pitch angle servo motor) via the CAN bus to achieve the coordinated action of the actual torque and the pitch angle.

[0112] In the example of the present invention, ARIMA or LSTM can be used to predict the next 1 step (0.01s). Taking ARIMA as an example, the wind speed of the previous 10 seconds is input and the next 1 step is predicted with an accuracy of ±0.3m / s.

[0113] In the embodiment of the present invention, only the optimized first step control input {u T (k),u β (k)}, discard the subsequent sequences, that is, only the first item is applied to the actual control system; at the next sampling time k+1, the optimization problem is re-solved based on the new measured state (x(k+1)) (rolling update).

[0114] Therefore, the torque control strategy for a variable-speed, variable-pitch wind turbine generator system of the present invention utilizes an aerodynamic model (calculating the power generated by wind-driven blades), a drive train model (simulating the mechanical transmission within the generator, including speed and torque transmission), and a pitch model (simulating the actuator for blade angle adjustment, focusing on blade rotation speed and response time) to model the operation of the wind turbine. The generated power is stabilized by designing an error regulator, or sliding surface. Integral control is creatively introduced into the sliding surface to rapidly respond to errors and eliminate long-term stability errors. Adaptive adjustment is achieved by dynamically adjusting the sliding surface parameters using fuzzy logic, achieving dynamic and adaptive rapid response and suppressing the effects of random wind speed fluctuations, the time-varying characteristics of blade aerodynamic parameters, and the uncertainty of drive train damping on control jitter. Finally, model predictive control (MPC) is used to continuously optimize the next control command (torque and blade angle) to achieve both accurate power tracking (minimizing errors) and reduced mechanical losses (for example, avoiding frequent blade angle changes and sudden torque changes that can damage gears). The optimal solution is calculated using a "convex optimization" algorithm to ensure stable system convergence.

[0115] Through the coordinated control of pitch moment and torque of the present invention: for torque control, the calculated optimal torque instruction is sent to the converter to adjust the current of the generator so that the torque keeps up with the target; for pitch control, the blade angle is adjusted in two parts, "reference angle" (preset in advance according to the average wind speed) + "real-time adjustment amount" (according to the current error), and the torque and blade angle are adjusted in advance according to the predicted wind speed, and feedforward compensation is performed to reduce fluctuations caused by delays.

[0116] {Example 2}

[0117] In this embodiment, in combination with the torque control method of the variable speed and variable pitch wind turbine generator set of the above embodiment, real-time performance data including power error e(t), torque fluctuation Δτ(t), and number of pitch action Npitch are input, and performance evaluation is performed based on the root mean square error (RMSE) and mean absolute error (MAE):

[0118]

[0119] M represents the data points in the last hour (36,000).

[0120] Then, the fuzzy rules were adjusted by particle swarm optimization (PSO) to optimize the center value of the fuzzy logic membership function (a total of 10 parameters, 5 input membership centers + 5 output membership centers). The membership function used was: F = 0.7·RMSE + 0.3·MAE;

[0121] The PSO parameters are set as follows:

[0122] Population size = 50, iterations = 100;

[0123] The inertia weight w decreases linearly from 0.9 to 0.4, with a learning factor of \(c1=c2=2\).

[0124] Every day at 2:00 AM (a period of low wind speed and light system load), PSO optimization is performed to verify the new parameters (e.g., after 10 minutes of operation, if the RMSE decreases by >5%, the parameters are updated; otherwise, the original parameters are retained). The optimal parameters are written into the fuzzy rule base, and the controller is restarted. Thus, through PSO tuning, the system adapts to the wind speed distribution characteristics of different seasons (e.g., when turbulence intensity is high in winter, the weight of the error change rate is automatically increased), improving power tracking accuracy during long-term operation.

[0125] While the present invention has been disclosed above with reference to preferred embodiments, this is not intended to limit the present invention. Persons skilled in the art will readily appreciate that various modifications and variations can be made without departing from the spirit and scope of the present invention. Therefore, the scope of protection of the present invention shall be determined by the claims.

Claims

1. A method for controlling torque of a variable speed and variable pitch wind turbine generator set, characterized in that: The following steps are involved: Step 1: Obtain state sampling signals of the wind turbine generator set, including wind speed signal, unit speed, torque and pitch angle, align the unit speed, torque and pitch angle with the wind speed signal, and calculate the tip speed ratio λ; Step 2: Construct an improved blade element momentum model Pmech = f(C p ,β,λ), used to characterize the wind energy capture efficiency C p The dynamic relationship between the tip speed ratio λ and the pitch angle β is calculated, and the parameter estimation value is updated in real time based on the recursive least squares method to achieve online identification and update C p ; Step 3: constructing a multi-objective prediction model based on the improved blade element momentum model, the generator set drive chain dynamic model, and the pitch actuator model, and using the forward Euler method for discretization to obtain a discretized state space model; Step 4: Based on the power tracking error, an adaptive sliding surface with an integral term is designed to eliminate the steady-state error through the integral term, and fuzzy logic dynamic adjustment is achieved through time-varying gain; Step 5: Using the dynamically adjusted sliding surface as the core constraint, optimize the objective function of the discretized state-space model and convert it into a convex optimization method for solution. Based on the continuous reaching law design, use the hyperbolic tangent function to approximate the sign function to achieve continuous chattering suppression, and output the optimal control sequence for the next N steps; and Step 6: Perform coordinated control of pitch moment and torque according to the optimal control sequence; Wherein, in said step 2, an improved blade element momentum model Pmech=f(C p ,β,λ), used to characterize the wind energy capture efficiency C p The dynamic relationship between the tip speed ratio λ and the pitch angle β is calculated, and the parameter estimation value is updated in real time based on the recursive least squares method to achieve online identification and update C p ,include: Step 2-1: Construct the improved blade element momentum model P mech =f(Cp,β,λ), a direct mapping between the wind energy capture efficiency Cp and the input variables λ and β is established, which is specifically expressed as follows: P mech (t)=ρπR 2 v(t) 3 C p Where ρ represents the air density; R represents the radius of the fan blade, in meters; v(t) represents the wind speed at time i, in meters per second. Step 2-2: Set the wind energy capture efficiency C p Approximately in polynomial form: Cp=k1λ+k2β+k3λ 2 +k4β 2 +k5λβ Where k1, k2, k3, k4, k5 are the coefficients of the polynomial respectively; Step 2-3, according to C p The polynomial expression and the measured power P mech (t)=ρπR 2 v(t) 3 C p , construct a linear regression model: Y = Φ(t)θ+∈(t); Output Y(t) = P mech (t), represents the measured mechanical power, which is calculated based on the measured τ(t)*ω(t), where τ(t) and ω(t) represent the sampling values ​​of the unit speed and torque at time t, respectively; Special vector Φ(t) = [λ(t), β(t), λ(t) 2 , β(t), λ(t)β(t)]; Parameter vector θ = [k1, k2, k3, k4, k5] T ; Where, ∈(t) represents the modeling error, which obeys the normal distribution; β(t) represents the sampling value of the pitch angle at time t; λ(t) represents the tip speed ratio at time t; Step 2-4: Use the recursive least squares method to perform real-time update calculations at an update frequency of 10 Hz to obtain a real-time updated parameter vector θ.

2. The torque control method of a variable speed and variable pitch wind turbine generator set according to claim 1, characterized in that: The step of aligning the turbine speed, torque, and pitch angle with the wind speed signal and calculating the tip speed ratio λ includes: Based on the wind speed signal timestamp, the sampling frequency is unified to 100 Hz, that is, the time step Δt = 0.01s, and the unit speed ω(t), torque τ(t) and pitch angle β(t) are linearly interpolated so that the collected signals are at the same time point t i =i·Δt alignment; ω(t), τ(t), β(t) represent the sampling values ​​at the corresponding time t respectively; Calculate the tip speed ratio λ, λ = ω(t)*R / v(t), where R is the radius of the wind turbine blade in meters; v(t) is the wind speed at time i in meters per second.

3. The torque control method of a variable speed and variable pitch wind turbine generator set according to claim 1, characterized in that: In step 3, a multi-objective prediction model is constructed based on the improved blade element momentum model, the generator set drive chain dynamic model, and the pitch actuator model, and a forward Euler method is used for discretization processing to obtain a discretized state space model, including: Step 3-1: Construct the dynamic model of the generator set transmission chain, which is expressed as follows: Among them, T aero =P mech / ω, represents the aerodynamic torque, the unit is N·m; T gen =K τ u T , represents the electromagnetic torque, K τ is the generator torque coefficient, u T is the torque control input; J is the moment of inertia, unit is kg·m 2 ; B is the viscous damping coefficient, unit is N·m·s / rad; Step 3-2: Establish a pitch actuator model based on the first-order inertia link, which is expressed as follows: Among them, T β Represents the pitch time constant, which is used to characterize the mechanical response speed; K β Indicates gain, which is used to characterize the input-output ratio; u β It is the pitch control input; Step 3-3: According to the time step Δt, the forward Euler method is used to perform discretization processing to obtain the discretized state space model, including: Define the state variables as follows: Obtain the discrete state equation: The speed is updated as: The pitch angle is updated as: Among them,T gen (k)=K τ in T (k) 4. The torque control method of a variable speed and variable pitch wind turbine generator set according to claim 3, characterized in that: In step 4, the adaptive sliding surface with an integral term introduced based on the power tracking error design, the steady-state error is eliminated by the integral term, and the fuzzy logic dynamic adjustment is achieved by the time-varying gain, including: Step 4-1. Define the power tracking error e(k): e(k)=Pref(k)-Pmech(k) Where Pref(k) represents the reference power, which is determined according to the preset maximum power tracking curve of wind speed or grid instruction; Step 4-2: Design the adaptive sliding surface σ(k) with integral term: In the formula, the integral term ∑e(i)Δt is used to eliminate the steady-state error, represents the error change rate; Wherein, k(t) represents the time-varying gain: k(t)=k0+Δk(t), k0 represents the initial value of the time-varying gain, and Δk(t) represents the gain adjustment amount; According to the power tracking error e(k) and the error change rate Dynamically adjust Δk(t) and further dynamically update the time-varying gain k(t) to realize the dynamically adjusted sliding surface σ(k) and enhance the adaptability to different working conditions.

5. The torque control method for a variable speed and variable pitch wind turbine generator set according to claim 4, characterized in that: In step 4-2, the process of dynamically updating the time-varying gain k(t) includes: Input power tracking error e(k) and error change rate Normalized to [-1,1]; According to the fuzzy rule base design, the output gain adjustment value Δk(t) is in the domain [-0.5, 0.5]; Among them, the triangular function is divided into {negative large, negative small, zero, positive small, positive large}, and the fuzzy rule base is designed as follows: if e(k) is positive and If the positive value is large, the gain adjustment Δk(t) is large, which enhances the integral effect; if the negative value of e(k) is small and If Δk(t) is zero, the gain adjustment amount Δk(t) is small, suppressing overshoot; and The time-varying gain k(t) is dynamically updated according to k(t)=k0+Δk(t), where the initial value k0 of the time-varying gain is set to 0.1, and the sliding surface σ(k) is dynamically adjusted.

6. The torque control method for a variable speed and variable pitch wind turbine generator set according to claim 1, characterized in that: In step 5, the objective function of the discretized state-space model is optimized using the dynamically adjusted sliding surface as the core constraint and converted into a convex optimization method for solution. Based on the continuous reaching law design, the hyperbolic tangent function is used to approximate the sign function to achieve continuous chattering suppression, and the optimal control sequence for the next N steps is output, including: Step 5-1: Using the dynamically adjusted sliding surface as the core constraint, determine the optimization objective function as follows: Where Q represents the power tracking error weight matrix, which takes the value of diag(1,…,1); P represents the control input smoothness weight matrix, which takes the value of diag(r T ,…,r β ), r T =10 -6 , r β =10 -3 ; represents the torque limit constraint, which is determined by the generator capacity; |u β (k+i)|≤15° / s, represents the pitch rate limit constraint and determines the mechanical safety constraint; Step 5-2: The optimization objective function is quadratic and the constraints are linear. Convert it into a quadratic programming QP problem and solve it using the interior point method or gradient descent method. Furthermore, based on the continuous reaching law, the hyperbolic tangent function is used to approximate the sign function to suppress the chattering of the sliding mode control: u(k)=-κtanh(σ(k) / f) Where κ represents the control strength and F represents the boundary layer thickness, which is used to control and reduce high-frequency switching; By solving, the optimal control sequence {u T (k),u β (k)}.

7. The torque control method for a variable speed and variable pitch wind turbine generator set according to claim 1, characterized in that: In step 6, according to the optimal control sequence, the pitch moment and torque are coordinated and controlled, including the coordinated control of the generator converter and the pitch servo motor, as follows: Step 6-1: Torque command conversion, tracking T through the current loop of the generator converter cmd : T cmd =K τ u T (k) Step 6-2: Based on the wind speed prediction value v pred (k+1) drives feedforward compensation to obtain feedforward torque T ff : Feedforward torque T ff =1 / 2*ρπR 2 v pred (k+1) 3 Cp(λpred,β(k)) / λpred; Where λpred=ω(k)R / v pred (k+1), used to compensate for aerodynamic torque changes; Step 6-3, pitch angle control command β cmd Conversion: b cmd =b trim +K β you β (k) β trim Indicates the pitch angle reference angle, which is preset according to the average wind speed; K β u β (k) represents the real-time adjustment of the pitch angle; Step 6-4: Send torque control command T cmd +T ff To the converter for torque control and send pitch angle control command β cmd The pitch angle servo motor is used to control the pitch angle, realizing the coordinated action of actual torque and pitch angle.

8. A computer system, characterized in that: include: one or more processors; A memory storing operable instructions, wherein when the instructions are executed by the one or more processors, the one or more processors are caused to perform operations, wherein the operations include executing the process of the method according to any one of claims 1 to 7.

9. A computer-readable medium storing software, characterized in that: The software includes instructions that can be executed by one or more computers, and when the instructions are executed by the one or more computers, the process of the method according to any one of claims 1 to 7 is performed.

Images