CN115434852A - Maximum wind energy capture control method and system for wind turbine generator - Google Patents
Maximum wind energy capture control method and system for wind turbine generator Download PDFInfo
- Publication number
- CN115434852A CN115434852A CN202211064491.7A CN202211064491A CN115434852A CN 115434852 A CN115434852 A CN 115434852A CN 202211064491 A CN202211064491 A CN 202211064491A CN 115434852 A CN115434852 A CN 115434852A
- Authority
- CN
- China
- Prior art keywords
- wind
- wind turbine
- torque
- rotating speed
- turbine generator
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 54
- 238000013528 artificial neural network Methods 0.000 claims abstract description 61
- 238000002940 Newton-Raphson method Methods 0.000 claims abstract description 8
- 230000005540 biological transmission Effects 0.000 claims description 9
- 238000004364 calculation method Methods 0.000 claims description 7
- 238000012549 training Methods 0.000 claims description 5
- 238000011217 control strategy Methods 0.000 claims description 3
- 230000004044 response Effects 0.000 abstract description 20
- 238000010586 diagram Methods 0.000 description 9
- 230000006870 function Effects 0.000 description 8
- 238000004590 computer program Methods 0.000 description 7
- 230000008901 benefit Effects 0.000 description 5
- 230000008569 process Effects 0.000 description 4
- 238000012545 processing Methods 0.000 description 4
- 230000009194 climbing Effects 0.000 description 3
- 238000013461 design Methods 0.000 description 3
- 230000007613 environmental effect Effects 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 2
- 230000007547 defect Effects 0.000 description 2
- 238000001514 detection method Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000001914 filtration Methods 0.000 description 2
- 238000010030 laminating Methods 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 230000003044 adaptive effect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000010248 power generation Methods 0.000 description 1
Images
Classifications
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F03—MACHINES OR ENGINES FOR LIQUIDS; WIND, SPRING, OR WEIGHT MOTORS; PRODUCING MECHANICAL POWER OR A REACTIVE PROPULSIVE THRUST, NOT OTHERWISE PROVIDED FOR
- F03D—WIND MOTORS
- F03D7/00—Controlling wind motors
- F03D7/02—Controlling wind motors the wind motors having rotation axis substantially parallel to the air flow entering the rotor
- F03D7/022—Adjusting aerodynamic properties of the blades
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F03—MACHINES OR ENGINES FOR LIQUIDS; WIND, SPRING, OR WEIGHT MOTORS; PRODUCING MECHANICAL POWER OR A REACTIVE PROPULSIVE THRUST, NOT OTHERWISE PROVIDED FOR
- F03D—WIND MOTORS
- F03D17/00—Monitoring or testing of wind motors, e.g. diagnostics
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F03—MACHINES OR ENGINES FOR LIQUIDS; WIND, SPRING, OR WEIGHT MOTORS; PRODUCING MECHANICAL POWER OR A REACTIVE PROPULSIVE THRUST, NOT OTHERWISE PROVIDED FOR
- F03D—WIND MOTORS
- F03D7/00—Controlling wind motors
- F03D7/02—Controlling wind motors the wind motors having rotation axis substantially parallel to the air flow entering the rotor
- F03D7/04—Automatic control; Regulation
- F03D7/042—Automatic control; Regulation by means of an electrical or electronic controller
- F03D7/043—Automatic control; Regulation by means of an electrical or electronic controller characterised by the type of control logic
- F03D7/045—Automatic control; Regulation by means of an electrical or electronic controller characterised by the type of control logic with model-based controls
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F03—MACHINES OR ENGINES FOR LIQUIDS; WIND, SPRING, OR WEIGHT MOTORS; PRODUCING MECHANICAL POWER OR A REACTIVE PROPULSIVE THRUST, NOT OTHERWISE PROVIDED FOR
- F03D—WIND MOTORS
- F03D80/00—Details, components or accessories not provided for in groups F03D1/00 - F03D17/00
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/11—Complex mathematical operations for solving equations, e.g. nonlinear equations, general mathematical optimization problems
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/084—Backpropagation, e.g. using gradient descent
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Sustainable Energy (AREA)
- Combustion & Propulsion (AREA)
- Mechanical Engineering (AREA)
- Chemical & Material Sciences (AREA)
- Sustainable Development (AREA)
- Theoretical Computer Science (AREA)
- Mathematical Physics (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Mathematical Analysis (AREA)
- Software Systems (AREA)
- Pure & Applied Mathematics (AREA)
- Mathematical Optimization (AREA)
- Computational Mathematics (AREA)
- Artificial Intelligence (AREA)
- General Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Computing Systems (AREA)
- Computational Linguistics (AREA)
- Molecular Biology (AREA)
- Health & Medical Sciences (AREA)
- Biophysics (AREA)
- Operations Research (AREA)
- Evolutionary Computation (AREA)
- Algebra (AREA)
- Databases & Information Systems (AREA)
- Fluid Mechanics (AREA)
- Control Of Eletrric Generators (AREA)
- Wind Motors (AREA)
Abstract
The invention discloses a method and a system for controlling maximum wind energy capture of a wind turbine generator, wherein a BP neural network is used for identifying an inverse model of the wind turbine generator on line; the method comprises the steps of controlling a wind turbine generator in real time, estimating aerodynamic torque of a wind wheel on line, carrying out iterative solution on the physical relation between the aerodynamic torque of the wind wheel and wind speed by using a Newton-Raphson method, and obtaining a wind speed estimated value in real time; calculating a reference rotating speed according to the wind speed estimation value; calculating the torque control quantity of the wind turbine inverse model at the current moment by taking the reference rotating speed, the rotating speed of the wind wheel at the previous moment, the electromagnetic torque of the generator at the previous moment and the pneumatic torque estimated value as the input of the wind turbine inverse model; calculating a closed-loop torque control quantity by using a BP neural network controller; the torque control quantity of the wind turbine generator inverse model at the current moment is added with the closed-loop torque control quantity to obtain a combined electromagnetic torque control quantity, a combined torque setting target is achieved through a converter, the maximum wind energy capture control of the wind turbine generator is achieved, the logic is simple, the implementation is easy, the response is fast, and the stability is good.
Description
Technical Field
The invention belongs to the technical field of wind power generation, and particularly relates to a method and a system for controlling maximum wind energy capture of a wind turbine generator.
Background
The topic of constant wind power development is to improve the utilization efficiency of wind energy. The size of energy captured by the wind turbine generator from wind energy mainly depends on the rotating speed, the wind speed and the pitch angle of the wind turbine, and the pitch variation is generally used for limiting the rotating speed of the wind turbine and preventing faults and overlarge aerodynamic noise caused by overspeed. Below rated wind speed, the pitch control is generally not started, at the moment, the power coefficient is a single-value function related to the tip speed ratio, namely, each wind speed below the rated corresponds to an optimal wind wheel rotating speed, so that the wind energy utilization efficiency is highest. The purpose of maximum wind energy capture control of the wind turbine generator is to adjust the electromagnetic torque of the generator, so that the rotating speed of a wind wheel changes to the optimal rotating speed value, and maximum wind energy capture is further realized.
The maximum wind energy capture control of the wind turbine generator mainly comprises an optimal torque method, a blade tip speed ratio method and a hill climbing method. The blade tip speed ratio method calculates a reference rotating speed according to a wind speed measurement value, a common wind speed sensor is installed in an engine room and can only measure a single point, wind shear, a wake effect, wind speed turbulence characteristics and inertia of an anemoscope make the wind speed sensor difficult to measure an accurate wind speed signal, the installation positions are different, the obtained wind speed signals are also different, and the measured signals cannot accurately reflect effective wind speed acting on the whole wind wheel, so that the blade tip speed ratio method is rarely applied to large-scale wind turbine generators. The mountain climbing method is also called a disturbance observation method, does not depend on system parameters, adjusts the operation of the rotating speed of a fan towards the maximum power by comparing the relation between the output powers of the generators, and is slow in tracking speed when the rotational inertia of a wind wheel is large, so that the mountain climbing method is mainly applied to small wind turbine generators. The optimal torque method is a mainstream method for tracking the maximum power point of the large-scale wind turbine generator, and the traditional optimal torque method is based on a steady-state optimal curve and omits the dynamic processes of different steady-state working points. From the control system perspective, the traditional optimal torque method shows remarkable nonlinearity and large inertia characteristics, namely the response delay of the wind wheel is serious at low wind speed, and the response delay degree is lightened along with the increase of the wind speed; on the other hand, the wind turbine has strong randomness, absolute steady state does not exist in the actual working condition, the wind turbine generator is constantly in the dynamic process, and the optimal torque method based on steady state assumption inevitably causes energy loss. Therefore, the nonlinear maximum wind energy capture control method considering the unsteady state of the wind turbine generator is designed, and the method has great significance for improving the dynamic response performance of wind energy capture of the wind turbine generator and the utilization efficiency of the wind energy.
Disclosure of Invention
The invention aims to solve the technical problems that the maximum wind energy capture control method and the maximum wind energy capture control system for the wind turbine generator set aim at overcoming the defects in the prior art, and the technical problems that the dynamic response performance of wind energy capture of the wind turbine generator set and the utilization efficiency of wind energy are low are solved.
The invention adopts the following technical scheme:
a method for controlling maximum wind energy capture of a wind turbine generator comprises the following steps:
s1, identifying an inverse model of a wind turbine generator on line by using a BP neural network;
s2, controlling the wind turbine generator in real time, reading the rotating speed of the wind wheel and an electromagnetic torque signal of the generator, estimating the aerodynamic torque of the wind wheel on line, performing iterative solution on the physical relation between the aerodynamic torque of the wind wheel and the wind speed by using a Newton Raphson method, and acquiring a wind speed estimation value in real time;
s3, designing a reference model, and calculating a reference rotating speed according to the wind speed estimation value obtained in the step S2;
s4, calculating the torque control quantity of the wind turbine generator inverse model at the current moment by taking the aerodynamic torque estimated value of the wind wheel, the reference rotating speed obtained in the step S3, the wind wheel rotating speed at the previous moment obtained in the step S2 and the generator electromagnetic torque signal at the previous moment as the input of the wind turbine generator inverse model obtained in the step S1;
s5, subtracting the reference rotating speed obtained in the step S3 from the rotating speed of the wind wheel obtained in the step S2 to obtain a rotating speed control error;
s6, calculating a closed-loop torque control quantity by using a BP neural network controller based on the rotating speed control error obtained in the step S5;
and S7, adding the torque control quantity of the wind turbine generator inverse model at the current moment obtained in the step S4 and the closed-loop torque control quantity obtained in the step S6 to obtain a combined electromagnetic torque control quantity, and realizing a combined torque setting target through a converter to realize maximum wind energy capture control of the wind turbine generator.
Specifically, in step S1, the online identification of the inverse model of the wind turbine generator by using the BP neural network specifically comprises:
operating the wind turbine generator under a traditional torque control strategy; reading a wind wheel rotating speed signal a and a generator electromagnetic torque signal b in real time; the method comprises the steps that a discrete wind turbine generator set transmission chain state space equation is combined, on the basis of a real-time wind turbine rotating speed signal a and a generator electromagnetic torque signal b, an unscented Kalman filter is used for carrying out online unbiased estimation on wind turbine aerodynamic torque, and a wind turbine aerodynamic torque estimated value c is obtained; and (3) carrying out online identification on the inverse model of the controlled wind turbine generator by using a BP neural network, taking the difference between the electromagnetic torque b (k) at the current moment and the output of the neural network as an error training weight, and taking the trained neural network as the inverse model of the wind turbine generator.
Further, the model structure of the controlled wind turbine generator is as follows:
a(k)＝f[a(k-1),b(k),b(k-1),c(k)]
wherein f represents a function, a (k) is the rotating speed at the current moment, a (k-1) is the rotating speed at the previous moment, b (k) is the electromagnetic torque at the current moment, b (k-1) is the electromagnetic torque at the previous moment, and c (k) is the pneumatic torque at the current moment.
Further, the output of the inverse model of the wind turbine is represented as:
Net[a d (k),a(k-1),b(k-1),c(k)]
wherein a (k) is the rotating speed at the current moment, a (k-1) is the rotating speed at the previous moment, b (k-1) is the electromagnetic torque at the previous moment, and c (k) is the pneumatic torque at the current moment.
Specifically, in step S2, the wind speed estimation value d satisfies the following relationship:
wherein rho is inflow wind density; r is the radius of the wind wheel; c T (lambda) is the wind wheel torque coefficient, lambda is the ratio of the linear speed of the blade tip to the inflow wind speed; and c is the aerodynamic torque of the wind wheel.
Further, the online estimation of the wind wheel aerodynamic torque specifically comprises:
firstly, a wind wheel rotating speed signal a and a generator electromagnetic torque signal b are read, and then a wind wheel aerodynamic torque c is estimated on line by using an unscented Kalman filter.
Specifically, in step S3, the reference model specifically includes:
wherein λ is opt For the best tip speed ratio,
is the reference model gain; e is a time constant, a d (s) is the Laplace transform of the reference rotational speed, d(s) is the Laplace transform of the wind speed estimate, and s is the Laplace operator.
Specifically, in step S4, the torque control amount g (k) of the inverse model of the wind turbine at the current time is:
g(k)＝Net[a d (k),a(k-1),b(k-1),c(k)]
wherein, a d (k) For reference, a (k-1) is the previous timeThe wind wheel rotating speed, b (k-1) is the electromagnetic torque of the generator at the previous moment, and c (k) is the estimated value of the aerodynamic torque.
Specifically, step S6 specifically includes:
the neural network controller obtains the reference rotating speed a in the step S3 d (k) And the wind wheel rotating speed a (k-1) at the previous moment and the closed-loop torque control quantity i (k-1) at the previous moment obtained in the step S2 are used as input, the closed-loop torque control quantity i (k) is used as output, and the rotating speed control error h (k) is used as a target to carry out online training on the weight of the neural network controller.
In a second aspect, an embodiment of the present invention provides a maximum wind energy capture control system for a wind turbine, including:
the identification module is used for identifying the inverse model of the wind turbine generator on line by utilizing a BP neural network;
the estimation module is used for controlling the wind turbine generator in real time, reading the rotating speed of a wind wheel and an electromagnetic torque signal of a generator, estimating the pneumatic torque of the wind wheel on line, performing iterative solution on the physical relation between the pneumatic torque of the wind wheel and the wind speed by using a Newton-Raphson method, and acquiring a wind speed estimation value in real time; designing a reference model, and calculating a reference rotating speed according to the wind speed estimation value;
the calculation module is used for calculating the torque control quantity of the wind turbine inverse model at the current moment by taking the aerodynamic torque estimated value of the wind wheel, the reference rotating speed obtained by the estimation module, the rotating speed of the wind wheel at the previous moment and the electromagnetic torque signal of the generator at the previous moment as the input of the wind turbine inverse model obtained by the identification module;
the network module is used for subtracting the reference rotating speed obtained by the estimation module from the rotating speed of the wind wheel to obtain a rotating speed control error, and calculating a closed-loop torque control quantity by using the BP neural network controller;
and the control module is used for adding the torque control quantity of the wind turbine inverse model at the current moment obtained by the calculation module and the closed-loop torque control quantity obtained by the network module to obtain a combined electromagnetic torque control quantity, realizing a combined torque setting target through the converter and realizing the maximum wind energy capture control of the wind turbine.
Compared with the prior art, the invention has at least the following beneficial effects:
a wind turbine generator set maximum wind energy capture control method comprises two control loops, namely a control loop based on a BP neural network inverse model and a BP neural network control loop based on rotating speed error back transmission; the method utilizes the BP neural network to firstly identify the inverse model, then designs the torque control quantity of the inverse model according to the inverse model, has simple logic and easy realization, directly controls without a lag-based rotating speed error, has quick response and better stability, and has better dynamic response performance of the torque control quantity designed based on the model than the traditional optimal torque control based on steady-state assumption because the inverse model contains the unsteady state characteristic of the wind turbine generator; the method selects a simple and reliable linear reference model and reasonable model gain, so that not only is the steady-state control precision ensured, but also the maximum power point tracking of the wind turbine generator is ensured to have constant tracking bandwidth in a wide wind speed range like a linear system; the BP neural network control loop based on the rotation speed error back transmission transmits the rotation speed error back to the hidden layer laminating input layer to correct the weight, and the weight is high-precision feedback control and high in control precision. The BP neural network based on the inverse model identification is combined with the BP neural network controller based on the minimum error, and meanwhile stability and steady-state accuracy indexes are guaranteed.
Furthermore, the BP neural network is used for identifying the wind turbine inverse model on line, the nonlinear approximation capability of the neural network is very strong, the method is very suitable for a wind turbine maximum power point tracking system with remarkable nonlinear characteristics, and the method is simple in logic, easy to implement and high in identification precision;
furthermore, a model structure of the controlled wind turbine generator is set as a function of the current rotating speed relative to the rotating speed at the previous moment, the pneumatic torque at the current moment, the electromagnetic torque at the current moment and the electromagnetic torque at the previous moment, the model structure has few input and output variables and has the capability of fully reflecting the nonlinear and time-varying characteristics of the dynamic response of the rotating speed of the wind turbine;
furthermore, the rotating speed signal at the current moment and the previous moment, the electromagnetic torque signal at the previous moment and the pneumatic torque estimated value at the current moment are used as the input of an inverse model, the current torque is used as the output of the inverse model, and the model identification is carried out on the relation of the input and the output through BP neural network identification, so that the required inverse model torque control quantity can be easily calculated through the identified inverse model as long as the expected rotating speed is given and the rotating speed at the previous moment, the electromagnetic torque signal at the previous moment and the pneumatic torque estimated value at the current moment are detected;
furthermore, the wind speed estimation is equivalently converted into the solution of a nonlinear equation by utilizing the relation between the wind speed and the aerodynamic torque, the wind speed estimation is realized by directly utilizing the solution method of the nonlinear equation, the estimation cost is low, and a wind speed sensor is not required to be added;
furthermore, the unscented Kalman filter is used for realizing the unbiased estimation of the pneumatic torque, the estimation cost is low, a sensor is not required to be additionally added, and meanwhile, the unscented Kalman filter is more suitable for the state estimation of a nonlinear system than the traditional Kalman filter;
further, gain of reference model
Can ensure the reference rotating speed value a under the steady wind speed d (k) The maximum power point tracking method has the advantages that the maximum power point tracking method meets the optimal tip speed ratio state with the wind speed estimated value d (k), so that the steady-state accuracy of maximum power point tracking control is guaranteed, in addition, a first-order linear inertia reference model is simple, reliable and easy to select, and meanwhile, the maximum power point tracking of the wind turbine generator can be guaranteed to have constant tracking bandwidth in a wide wind speed range like a linear system.
Furthermore, the wind turbine generator inverse model identified by the BP neural network calculates the inverse model torque control quantity, the control quantity is not directly controlled based on the lagging rotating speed error, the response speed is high, and the dynamic response performance of the torque control quantity designed based on the model is obviously superior to the optimal torque control based on the steady-state assumption because the inverse model contains the unsteady-state characteristic of the wind turbine generator;
further, the BP neural network controller based on the minimum rotating speed error transmits the rotating speed error back to the hidden laminating input layer to correct the weight, the essence is high-precision feedback control, the control precision is high, the dependence degree on the model is very low, and the adaptability to environmental factors and unit parameters is strong.
It is understood that the beneficial effects of the second aspect can be referred to the related description of the first aspect, and are not described herein again.
In conclusion, the method fully utilizes the advantages of nonlinear approximation of the neural network, and has high response speed and good stability; the control precision is high, the dependence degree on the model is low, the adaptability to environmental factors and unit parameters is strong, and the stability and the steady-state precision index are ensured.
The technical solution of the present invention is further described in detail by the accompanying drawings and embodiments.
Drawings
FIG. 1 is a flow chart of a method of the present invention;
FIG. 2 is a flow chart of controlled unit inverse model acquisition;
fig. 3 is a block diagram of real-time control of the system.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, not all, embodiments of the present invention. All other embodiments, which can be obtained by a person skilled in the art without making any creative effort based on the embodiments in the present invention, belong to the protection scope of the present invention.
In the description of the present invention, it should be understood that the terms "comprises" and/or "comprising" indicate the presence of the stated features, integers, steps, operations, elements, and/or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and/or groups thereof.
It is also to be understood that the terminology used in the description of the invention herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. As used in the specification of the present invention and the appended claims, the singular forms "a," "an," and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise.
It should be further understood that the term "and/or" as used in this specification and the appended claims refers to any and all possible combinations of one or more of the associated listed items, and including such combinations, e.g., a and/or B, may mean: a exists alone, A and B exist simultaneously, and B exists alone. In addition, the character "/" herein generally indicates that the former and latter related objects are in an "or" relationship.
It should be understood that although the terms first, second, third, etc. may be used to describe preset ranges, etc. in embodiments of the present invention, these preset ranges should not be limited to these terms. These terms are only used to distinguish preset ranges from each other. For example, the first preset range may also be referred to as a second preset range, and similarly, the second preset range may also be referred to as the first preset range, without departing from the scope of the embodiments of the present invention.
The word "if" as used herein may be interpreted as "at 8230; \8230;" or "when 8230; \8230;" or "in response to a determination" or "in response to a detection", depending on the context. Similarly, the phrases "if determined" or "if detected (a stated condition or event)" may be interpreted as "when determined" or "in response to a determination" or "when detected (a stated condition or event)" or "in response to a detection (a stated condition or event)", depending on the context.
Various structural schematics according to the disclosed embodiments of the invention are shown in the drawings. The figures are not drawn to scale, wherein certain details are exaggerated and possibly omitted for clarity of presentation. The shapes of various regions, layers and their relative sizes and positional relationships shown in the drawings are merely exemplary, and deviations may occur in practice due to manufacturing tolerances or technical limitations, and a person skilled in the art may additionally design regions/layers having different shapes, sizes, relative positions, according to actual needs.
The invention provides a wind turbine generator maximum wind energy capture control method, which utilizes a BP neural network to identify a wind turbine generator inverse model on line; the method comprises the steps of controlling a wind turbine generator in real time, estimating pneumatic torque of a wind wheel on line, performing iterative solution on the physical relation between the pneumatic torque of the wind wheel and wind speed by using a Newton-Raphson method, and obtaining a wind speed estimated value in real time; designing a reference model, and calculating a reference rotating speed according to the wind speed estimation value; calculating the torque control quantity of the wind turbine inverse model at the current moment by taking the reference rotating speed, the rotating speed of the wind wheel at the previous moment, the electromagnetic torque of the generator at the previous moment and the pneumatic torque estimated value as the input of the wind turbine inverse model; subtracting the reference rotating speed from the rotating speed of the wind wheel to obtain a rotating speed control error, and calculating a closed-loop torque control quantity by using a BP neural network controller; adding the torque control quantity of the inverse model of the wind turbine generator at the current moment with the closed-loop torque control quantity to obtain a combined electromagnetic torque control quantity, and realizing a combined torque setting target through a converter to realize maximum wind energy capture control of the wind turbine generator; the BP neural network based on the inverse model identification is combined with the BP neural network controller based on the minimum error, so that the stability and the steady-state precision index are ensured.
Referring to fig. 1, the method for controlling maximum wind energy capture of a wind turbine generator according to the present invention includes the following steps:
s1, identifying an inverse model of the wind turbine generator on line by using a BP neural network;
referring to fig. 2, the identification process is as follows:
s101, operating the wind turbine generator under a traditional torque control strategy;
s102, reading a wind wheel rotating speed signal a and a generator electromagnetic torque signal b in real time;
s103, combining a discrete wind turbine generator set transmission chain state space equation, carrying out online unbiased estimation on the wind turbine aerodynamic torque by using an unscented Kalman filter based on a real-time wind turbine rotating speed signal a and a generator electromagnetic torque signal b, and recording the wind turbine aerodynamic torque estimated value as c;
generally, a continuous transmission chain state space equation can be obtained first, and then the continuous transmission chain state space equation is converted into a discrete model by utilizing a linear system theory.
The unscented kalman filter realizes the advantages of the unbiased estimation of the pneumatic torque: the cost is low, and no additional sensor is needed; unscented kalman filtering is more suitable for state estimation of nonlinear systems than traditional kalman filtering.
S104, carrying out online identification on the inverse model of the controlled unit by using a BP neural network;
the model structure of the controlled unit is considered as follows by the basic pneumatic and structural theory of the wind turbine unit:
a(k)＝f[a(k-1),b(k),b(k-1),c(k)]
where f represents a function.
The current-time rotating speed a (k) is related to the previous-time rotating speed a (k-1), the current-time electromagnetic torque b (k), the previous-time electromagnetic torque b (k-1) and the current-time pneumatic torque c (k), and the adjustment of a (k) is generally realized by changing b (k);
in turn, the desired rotor speed is known a d (k) and the current state information a (k-1), b (k-1) and c (k), corresponding current-time electromagnetic torque control quantity can be obtained, the mapping relation is identified by using a BP neural network, the difference between the current-time electromagnetic torque b (k) and the output of the neural network is used as an error to train a weight, the trained neural network is an inverse model of the wind turbine generator, the inverse model is marked as Net, and the output of the Net is expressed as: net [ a ] d (k),a(k-1),b(k-1),c(k)]。
S2, controlling the wind turbine generator in real time, firstly reading a wind wheel rotating speed signal a and a generator electromagnetic torque signal b, estimating a wind wheel pneumatic torque c on line by using an unscented Kalman filter, iteratively solving a physical relation based on the physical relation between the wind wheel pneumatic torque c and wind speed by using a Newton-Raphson method, and acquiring a wind speed estimation value d in real time;
referring to fig. 3, the real-time wind speed estimation value is processed by the linear reference model to calculate the reference rotation speed, and the control target of the entire control system is that the rotation speed of the desired wind wheel calculated by the linear reference model is consistent. And (2) detecting a wind wheel rotating speed signal at the last moment, a wind wheel aerodynamic torque estimation signal at the current moment, an electromagnetic torque signal at the last moment and a reference rotating speed signal at the current moment, which are estimated on line by an unscented Kalman filter, by using the trained BP neural network inverse model S1 to calculate an inverse model torque control quantity, wherein the control quantity is essentially open-loop control, and has good stability but insufficient anti-interference capability. The BP neural network controller makes up the defect, the wind wheel rotating speed signal at the previous moment, the reference rotating speed signal at the current moment and the closed-loop torque control quantity at the previous moment are used as input, the rotating speed error is used as a target to correct the neural network weight, the closed-loop torque control quantity is calculated, the BP neural network controller is essentially rotating speed closed-loop control, and the anti-interference capability is strong. And adding the inverse model torque control quantity and the closed-loop torque control quantity to obtain a total torque control quantity, and realizing the torque setting requirement by the converter.
The estimation of the real-time wind speed is essentially a non-linear equation solving for the aerodynamic torque c of the wind rotor and the wind speed estimate d:
wherein rho is inflow wind density; r is the radius of the wind wheel; c T (lambda) is the wind wheel torque coefficient,
the ratio of the linear speed of the blade tip to the inflow wind speed; wind wheel torque coefficient characteristic C T (λ) may be calculated from the rotor steady state aerodynamics.
S3, designing a reference model, and calculating a reference rotating speed a according to the wind speed estimation value d (k) obtained in the step S2 d (k)；
The reference model is a typical first-order inertial model:
wherein λ is opt For optimum tip speed ratio, it is determined by the wind wheel structure and aerodynamic characteristics, generally provided by the complete machine manufacturer, with reference to model gains
Can ensure the reference rotating speed value a under the steady wind speed d (k) Meets the optimal tip speed ratio state with the wind speed estimated value d (k), thereby ensuring the steady-state precision of the maximum wind energy capture control(ii) a And e is a time constant, the dynamic response speed of maximum power point tracking is determined, and the value is reasonably selected according to the size of the wind turbine generator.
Selecting the first order inertial model advantage:
(1) the reference model is simple and reliable;
(2) ensuring the steady-state control precision;
(3) the traditional maximum power point tracking of the wind turbine generator is nonlinear, the dynamic tracking effect is poor under low wind speed, and a linear reference model is selected in model reference adaptive control, so that the maximum power point tracking of the wind turbine generator can be ensured to have constant tracking bandwidth in a wide wind speed range like a linear system.
S4, calling the Net model identified in the step S1, and using the reference rotating speed a obtained in the step S3 d (k) The wind wheel rotating speed a (k-1) at the previous moment, the generator electromagnetic torque b (k-1) at the previous moment and the pneumatic torque estimated value c (k) obtained in the step S2 are input into a Net model, and the inverse model torque control quantity at the current moment is calculated;
the control quantities are recorded as:
g(k)＝Net[a d (k),a(k-1),b(k-1),c(k)]。
s5, converting the reference rotating speed a obtained in the step S3 d (k) Subtracting the wind wheel rotating speed a (k) obtained in the step S2 to obtain a rotating speed control error h (k);
s6, calculating a closed-loop torque control quantity i (k) by using a BP neural network controller;
the neural network controller obtains the reference rotating speed a in the step S3 d (k) And step S2, the wind wheel rotating speed a (k-1) at the previous moment and the closed-loop torque control quantity i (k-1) at the previous moment are used as input, the closed-loop torque control quantity i (k) is used as output, and the rotating speed control error h (k) is used as a target to carry out online training on the weight.
And S7, adding the inverse model torque control quantity g (k) obtained in the step S4 and the closed-loop torque control quantity h (k) calculated by the BP neural network controller in the step S6 to obtain a combined electromagnetic torque control quantity, and realizing a combined torque setting target through a converter.
In another embodiment of the present invention, a wind turbine maximum wind energy capture control system is provided, which can be used to implement the wind turbine maximum wind energy capture control method described above, and specifically, the wind turbine maximum wind energy capture control system includes an identification module, an estimation module, a calculation module, a network module, and a control module.
The identification module is used for identifying the inverse model of the wind turbine generator on line by using a BP neural network;
the estimation module is used for controlling the wind turbine generator in real time, reading the rotating speed of the wind wheel and an electromagnetic torque signal of the generator, estimating the aerodynamic torque of the wind wheel on line, performing iterative solution on the physical relation between the aerodynamic torque of the wind wheel and the wind speed by using a Newton Raphson method, and acquiring a wind speed estimation value in real time; designing a reference model, and calculating a reference rotating speed according to the wind speed estimation value;
the calculation module is used for calculating the torque control quantity of the wind turbine inverse model at the current moment by taking the aerodynamic torque estimated value of the wind wheel, the reference rotating speed obtained by the estimation module, the rotating speed of the wind wheel at the previous moment and the electromagnetic torque signal of the generator at the previous moment as the input of the wind turbine inverse model obtained by the identification module;
the network module is used for subtracting the reference rotating speed obtained by the estimation module from the rotating speed of the wind wheel to obtain a rotating speed control error, and calculating a closed-loop torque control quantity by using the BP neural network controller;
and the control module is used for adding the torque control quantity of the wind turbine inverse model at the current moment obtained by the calculation module and the closed-loop torque control quantity obtained by the network module to obtain a combined electromagnetic torque control quantity, realizing a combined torque setting target through the converter and realizing the maximum wind energy capture control of the wind turbine.
The neural network is strong in nonlinear approximation capability and suitable for a nonlinear strong wind turbine generator set maximum power point tracking system, the BP neural network is used for identifying an inverse model firstly, then an inverse model torque control quantity is designed according to the inverse model, the logic is simple and easy to realize, direct control is not performed based on a lagging rotation speed error, response is fast, stability is good, the inverse model contains the unsteady state characteristic of the wind turbine generator set, the dynamic response performance of the torque control quantity designed based on the model is better than that of the traditional optimal torque control based on steady state assumption, but the identified inverse model is limited in accuracy due to the fact that the number of samples is limited, control accuracy is limited, and anti-interference capability is insufficient. The BP neural network controller based on the minimum rotating speed error transmits the rotating speed error back to the hidden laminated input layer to correct the weight, and the weight is actually high-precision feedback control, although the response is slow, the control precision is high. The BP neural network based on the inverse model identification is combined with the BP neural network controller based on the minimum error, and meanwhile stability and steady-state accuracy indexes are guaranteed.
In summary, the maximum wind energy capture control method and system for the wind turbine generator fully utilize the nonlinear approximation advantage of the neural network, and a BP design network inverse model controller and a BP neural network controller based on rotating speed error back transmission are introduced into a maximum power point tracking system of the wind turbine generator with remarkable nonlinear characteristics. The wind turbine generator set inverse model identified by the BP neural network calculates an inverse model torque control quantity, the control quantity is not directly controlled based on a lagging rotating speed error, and the wind turbine generator set inverse model control quantity is high in response speed and good in stability; the BP neural network controller based on the rotation speed error back transmission has high control precision, very low dependence degree on a model, strong adaptability to environmental factors and unit parameters, combines two phases, and simultaneously ensures stability and steady-state precision indexes.
As will be appreciated by one skilled in the art, embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
The above-mentioned contents are only for illustrating the technical idea of the present invention, and the protection scope of the present invention is not limited thereby, and any modification made on the basis of the technical idea of the present invention falls within the protection scope of the claims of the present invention.
Claims (10)
1. The method for controlling the maximum wind energy capture of the wind turbine generator is characterized by comprising the following steps of:
s1, identifying an inverse model of the wind turbine generator on line by using a BP neural network;
s2, controlling the wind turbine generator in real time, reading the rotating speed of a wind wheel and an electromagnetic torque signal of a generator, estimating the pneumatic torque of the wind wheel on line, performing iterative solution on the physical relation between the pneumatic torque of the wind wheel and the wind speed by using a Newton-Raphson method, and acquiring a wind speed estimated value in real time;
s3, designing a reference model, and calculating a reference rotating speed according to the wind speed estimation value obtained in the step S2;
s4, calculating the torque control quantity of the wind turbine generator inverse model at the current moment by taking the aerodynamic torque estimated value of the wind wheel, the reference rotating speed obtained in the step S3, the wind wheel rotating speed at the previous moment obtained in the step S2 and the generator electromagnetic torque signal at the previous moment as the input of the wind turbine generator inverse model obtained in the step S1;
s5, subtracting the reference rotating speed obtained in the step S3 from the rotating speed of the wind wheel obtained in the step S2 to obtain a rotating speed control error;
s6, calculating a closed-loop torque control quantity by using a BP neural network controller based on the rotating speed control error obtained in the step S5;
and S7, adding the torque control quantity of the wind turbine generator inverse model at the current moment obtained in the step S4 and the closed-loop torque control quantity obtained in the step S6 to obtain a combined electromagnetic torque control quantity, and realizing a combined torque setting target through a converter to realize maximum wind energy capture control of the wind turbine generator.
2. The method for controlling maximum wind energy capture of a wind turbine generator according to claim 1, wherein in step S1, the online identification of the inverse model of the wind turbine generator by using the BP neural network specifically comprises:
operating the wind turbine generator under a traditional torque control strategy; reading a wind wheel rotating speed signal a and a generator electromagnetic torque signal b in real time; the method comprises the steps that a discrete wind turbine generator set transmission chain state space equation is combined, on the basis of a real-time wind turbine rotating speed signal a and a generator electromagnetic torque signal b, an unscented Kalman filter is used for carrying out online unbiased estimation on wind turbine aerodynamic torque, and a wind turbine aerodynamic torque estimated value c is obtained; and (3) carrying out online identification on the inverse model of the controlled wind turbine generator by using a BP neural network, taking the difference between the electromagnetic torque b (k) at the current moment and the output of the neural network as an error training weight, and taking the trained neural network as the inverse model of the wind turbine generator.
3. The method for controlling maximum wind energy capture of a wind turbine generator as claimed in claim 2, wherein the model structure of the controlled wind turbine generator is:
a(k)＝f[a(k-1),b(k),b(k-1),c(k)]
wherein f represents a function, a (k) is the rotating speed at the current moment, a (k-1) is the rotating speed at the previous moment, b (k) is the electromagnetic torque at the current moment, b (k-1) is the electromagnetic torque at the previous moment, and c (k) is the pneumatic torque at the current moment.
4. The wind turbine generator maximum wind energy capture control method according to claim 2, wherein the output of the wind turbine generator inverse model is represented as:
Net[a d (k),a(k-1),b(k-1),c(k)]
wherein a (k) is the rotating speed at the current moment, a (k-1) is the rotating speed at the previous moment, b (k-1) is the electromagnetic torque at the previous moment, and c (k) is the pneumatic torque at the current moment.
5. The method for controlling maximum wind energy capture of a wind turbine generator as claimed in claim 1, wherein in step S2, the wind speed estimated value d satisfies the following relationship:
wherein rho is inflow wind density; r is the radius of the wind wheel; c T (lambda) is a wind wheel torque coefficient, and lambda is the ratio of the linear speed of the blade tip to the inflow wind speed; and c is the aerodynamic torque of the wind wheel.
6. The method for controlling maximum wind energy capture of a wind turbine generator according to claim 5, wherein the online estimation of the aerodynamic torque of the wind turbine is specifically:
firstly, a wind wheel rotating speed signal a and a generator electromagnetic torque signal b are read, and then a wind wheel aerodynamic torque c is estimated on line by using an unscented Kalman filter.
7. The method for controlling maximum wind energy capture of a wind turbine generator set according to claim 1, wherein in step S3, the reference model is specifically:
wherein λ is opt For the best tip speed ratio,
is the reference model gain; e is a time constant, a d (s) is the Laplace transform of the reference rotational speed, d(s) is the Laplace transform of the wind speed estimate, and s is the Laplace operator.
8. The method for controlling maximum wind energy capture of a wind turbine generator according to claim 1, wherein in step S4, the torque control amount g (k) of the inverse model of the wind turbine generator at the current moment is:
g(k)＝Net[a d (k),a(k-1),b(k-1),c(k)]
wherein, a d (k) For reference speed, a (k-1) is the wind wheel speed at the previous moment, b (k-1) is the generator electromagnetic torque at the previous moment, and c (k) is the aerodynamic torque estimation value.
9. The method for controlling maximum wind energy capture of a wind turbine generator according to claim 1, wherein step S6 specifically comprises:
the neural network controller obtains the reference rotating speed a in step S3 d (k) And the wind wheel rotating speed a (k-1) at the previous moment and the closed-loop torque control quantity i (k-1) at the previous moment obtained in the step S2 are used as input, the closed-loop torque control quantity i (k) is used as output, and the rotating speed control error h (k) is used as a target to carry out online training on the weight of the neural network controller.
10. The maximum wind energy capture control system for the wind turbine generator is characterized by comprising the following components:
the identification module is used for identifying the inverse model of the wind turbine generator on line by utilizing a BP neural network;
the estimation module is used for controlling the wind turbine generator in real time, reading the rotating speed of a wind wheel and an electromagnetic torque signal of a generator, estimating the pneumatic torque of the wind wheel on line, performing iterative solution on the physical relation between the pneumatic torque of the wind wheel and the wind speed by using a Newton-Raphson method, and acquiring a wind speed estimation value in real time; designing a reference model, and calculating a reference rotating speed according to the wind speed estimation value;
the calculation module is used for calculating the torque control quantity of the wind turbine inverse model at the current moment by taking the aerodynamic torque estimated value of the wind wheel, the reference rotating speed obtained by the estimation module, the rotating speed of the wind wheel at the previous moment and the electromagnetic torque signal of the generator at the previous moment as the input of the wind turbine inverse model obtained by the identification module;
the network module subtracts the reference rotating speed obtained by the estimation module from the rotating speed of the wind wheel to obtain a rotating speed control error, and calculates a closed-loop torque control quantity by using a BP neural network controller;
and the control module is used for adding the torque control quantity of the wind turbine inverse model at the current moment obtained by the calculation module and the closed-loop torque control quantity obtained by the network module to obtain a combined electromagnetic torque control quantity, realizing a combined torque setting target through the converter and realizing the maximum wind energy capture control of the wind turbine.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211064491.7A CN115434852A (en) | 2022-08-31 | 2022-08-31 | Maximum wind energy capture control method and system for wind turbine generator |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211064491.7A CN115434852A (en) | 2022-08-31 | 2022-08-31 | Maximum wind energy capture control method and system for wind turbine generator |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115434852A true CN115434852A (en) | 2022-12-06 |
Family
ID=84244218
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211064491.7A Pending CN115434852A (en) | 2022-08-31 | 2022-08-31 | Maximum wind energy capture control method and system for wind turbine generator |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115434852A (en) |
-
2022
- 2022-08-31 CN CN202211064491.7A patent/CN115434852A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109185054B (en) | Method, system and device for controlling pitch angle of wind driven generator and readable storage medium | |
| CN106460793B (en) | In response to wind shear to the control of wind turbine | |
| CN103384764B (en) | The controlling method of wind turbine | |
| CN109659931B (en) | Speed change unit coordination control method based on radial basis function interpolation model | |
| CN105649875B (en) | Variable pitch control method and device of wind generating set | |
| CN110552850B (en) | Wind turbine generator active power adjusting method and device based on wind speed advanced measurement | |
| EP3770423B1 (en) | Wind turbine control method and device, controller, and control system | |
| CN109958576B (en) | Method and device for controlling rotating speed of wind generating set | |
| CN102966488A (en) | Method and system for lowering offshore wind generating set load | |
| CN116316883B (en) | Optimization control method for cooperative operation of wind turbine clusters | |
| CN111756038B (en) | New energy power system equal frequency difference inertia estimation method considering frequency modulation characteristics | |
| CN109960823A (en) | Equivalent wind speed determination method and equipment of wind generating set | |
| CN113048017A (en) | Wind turbine generator active power control optimization method and system based on internal model control | |
| Liu et al. | Blade effective wind speed estimation: A subspace predictive repetitive estimator approach | |
| CN107979112B (en) | Fan control method, system, terminal and readable storage medium | |
| CN111997833B (en) | Wind turbine generator set composite intelligent pitch control method based on laser wind measurement feedforward | |
| CN115434852A (en) | Maximum wind energy capture control method and system for wind turbine generator | |
| US11846270B2 (en) | Control method and device of a wind park | |
| KR101280764B1 (en) | Method and apparatus for controlling wind turbine using wind speed feedforward control | |
| CN112682258B (en) | Backstepping-based large wind turbine maximum power point tracking control method | |
| Kazda et al. | Framework of multi-objective wind farm controller applicable to real wind farms | |
| Xu et al. | Self-tuning method of electronic governor parameters for marine medium-speed diesel engine | |
| CN112884262A (en) | Method and system for determining load adaptability of wind turbine generator | |
| CN114297819A (en) | Control method and device of wind generating set and computer readable storage medium | |
| CN115288928B (en) | Maximum power point tracking control method and system for wind turbine generator |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |