[go: up one dir, main page]

CN116816597B - Control method and system of wind turbine generator, electronic equipment and storage medium - Google Patents

Control method and system of wind turbine generator, electronic equipment and storage medium

Info

Publication number
CN116816597B
CN116816597B CN202310841716.3A CN202310841716A CN116816597B CN 116816597 B CN116816597 B CN 116816597B CN 202310841716 A CN202310841716 A CN 202310841716A CN 116816597 B CN116816597 B CN 116816597B
Authority
CN
China
Prior art keywords
sub
characterize
wind
control cycle
wind turbine
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.)
Active
Application number
CN202310841716.3A
Other languages
Chinese (zh)
Other versions
CN116816597A (en
Inventor
吴立建
郑松岳
许移庆
王立忠
韦国强
王思奇
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Zhejiang University ZJU
Shanghai Electric Wind Power Group Co Ltd
Original Assignee
Zhejiang University ZJU
Shanghai Electric Wind Power Group Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Zhejiang University ZJU, Shanghai Electric Wind Power Group Co Ltd filed Critical Zhejiang University ZJU
Priority to CN202310841716.3A priority Critical patent/CN116816597B/en
Publication of CN116816597A publication Critical patent/CN116816597A/en
Application granted granted Critical
Publication of CN116816597B publication Critical patent/CN116816597B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02E—REDUCTION OF GREENHOUSE GAS [GHG] EMISSIONS, RELATED TO ENERGY GENERATION, TRANSMISSION OR DISTRIBUTION
    • Y02E10/00—Energy generation through renewable energy sources
    • Y02E10/70—Wind energy
    • Y02E10/72—Wind turbines with rotation axis in wind direction

Landscapes

  • Wind Motors (AREA)

Abstract

本公开提供了一种风电机组的控制方法、系统、电子设备及存储介质。该控制方法包括：在当前控制周期内获取风电机组在至少一个预测控制周期内的来流风速；基于来流风速获取风电机组分别在预测控制周期内的运行状态数据；基于运行状态数据和发电机的预设成本函数，生成目标控制序列；响应于进入下一控制周期，根据目标控制序列中的目标转矩值控制发电机转矩。本公开基于帕累托理论，提出了一种预设成本函数，可以协同优化风电机组的塔架载荷和风能捕获功率，能够有效地对降低风电机组的塔架的侧向结构载荷，提升发电机应用在大型风电机组中的功率输出质量，提高风电机组运行的可靠性和高能效具有重要的工程应用价值。

This disclosure provides a control method, system, electronic device, and storage medium for a wind turbine. The control method includes: acquiring the incoming wind speed of the wind turbine in at least one predicted control cycle within the current control cycle; acquiring the operating status data of the wind turbine in each predicted control cycle based on the incoming wind speed; generating a target control sequence based on the operating status data and a preset cost function of the generator; and controlling the generator torque according to the target torque value in the target control sequence in response to entering the next control cycle. Based on Pareto theory, this disclosure proposes a preset cost function that can synergistically optimize the tower load and wind energy capture power of the wind turbine. It effectively reduces the lateral structural load on the wind turbine tower, improves the power output quality of the generator in large wind turbines, and enhances the reliability and energy efficiency of wind turbine operation, which has significant engineering application value.

Description

Control method and system of wind turbine generator, electronic equipment and storage medium
Technical Field
The disclosure relates to the technical field of wind turbine generator control, in particular to a control method, a control system, electronic equipment and a storage medium of a wind turbine generator.
Background
The wind turbine generator is a device for converting wind energy into electric energy, and consists of a plurality of components. The wind turbine mainly comprises a wind wheel (blade), a generator, a converter, a tower, a control system and the like. The wind wheel is driven to rotate by wind, the generator is activated to generate electric energy, and the electric energy is transmitted to a power grid or other electric equipment through the power transmission system.
With the increasing demand for wind energy, the rated power of the wind turbine and the size of the key supporting structure are designed in a large scale, so that the flexible characteristic of the wind turbine structure is obvious.
Moreover, the influence of complex pneumatic load of the large wind turbine is easy to generate elastic deformation, so that the load of the tower is increased, and the running stability and the service life of the wind turbine are further influenced.
At present, the structural damping of the tower can be adjusted by controlling the blade pitch angle and the generator torque, for example, an active damping control loop is added in the process of controlling the blade pitch angle to reduce oscillation, so that the load of the tower is reduced without adding an additional structure. However, the method mainly reduces the load in the front-rear direction of the tower, and the lateral load of the tower cannot be effectively optimized.
It is also possible to reduce the tower load by suppressing the tower lateral deformation acceleration during the control of the generator torque. However, the lateral deformation acceleration of the tower is mainly measured in real time through a sensor, has obvious nonlinear characteristics and is difficult to directly predict.
Or adopting a multivariable control strategy to restrain the power output quality and the lateral oscillation of the tower so as to reduce the lateral load of the tower. But the multi-objective cost function of nonlinear variable composition is difficult to solve, resulting in a multi-variable control strategy that is difficult to implement.
Disclosure of Invention
The disclosure provides a control method, a control system, electronic equipment and a storage medium for a wind turbine generator.
The technical problems are solved by the following technical scheme:
In a first aspect, the present disclosure provides a control method of a wind turbine generator. The wind turbine generator comprises a generator and a tower.
The control method comprises the following steps:
acquiring the incoming wind speed of the wind turbine generator in at least one prediction control period in the current control period;
Acquiring running state data of the wind turbine generator in the prediction control period respectively based on the incoming wind speed, wherein the running state data comprises predicted wind energy capturing power, ideal wind energy capturing power and lateral deformation acceleration of the tower;
Generating a target control sequence based on the running state data and a preset cost function of the generator, wherein the target control sequence comprises target torque values of generator torques respectively corresponding to the predicted control periods;
In response to entering a next control period, the generator torque is controlled in accordance with the target torque value in the target control sequence.
Optionally, the preset cost function is expressed as:
Wherein, the For characterizing the generator torque respectively corresponding from the 1 st to the nth predictive control period, F 1 for characterizing a first weight factor, F 2 for characterizing a second weight factor, n for characterizing the number of predictive control periods, T s for characterizing the duration of the predictive control period,For characterizing said predicted wind energy capture power during an ith said predicted control period,For characterizing said ideal wind energy capture power during an ith said predictive control period,For characterizing said deformation acceleration in an ith said predictive control period,The method is used for representing a preset maximum deformation acceleration record value;
the predicted wind energy capture power, the ideal wind energy capture power, and the deformation acceleration are each represented based on the generator torque.
Optionally, the step of generating a target control sequence based on the operating state data and a preset cost function of the generator comprises:
Performing iterative computation on the torque control sequence and the iteration change rate in a plurality of different solving directions by using a particle swarm algorithm until the number of iterative computation reaches a preset iteration number, and acquiring the target control sequence;
the target control sequence is the torque control sequence corresponding to the preset cost function in all solving directions when the preset cost function takes a global minimum value.
Optionally, the formula of the iterative calculation is:
Wherein, the For characterizing the torque control sequence obtained by the j-th iterative calculation,For characterizing the iteration change rate obtained by the jth iteration calculation,For characterizing the torque control sequence corresponding to the preset cost function taking the minimum value in the previous j iterative computations of the solving direction,For characterizing the torque control sequence corresponding to the preset cost function taking the global minimum in the previous j iterative computations of all the solving directions, c 1 and c 2 are respectively used for characterizing learning factors, r 1 and r 2 are respectively used for characterizing preset parameters,For characterizing inertial weights.
Optionally, the wind turbine generator further comprises a wind wheel;
the step of obtaining the running state data of the wind turbine generator set in the prediction control period based on the incoming wind speed comprises the following steps:
And acquiring the rotor speed of the wind wheel in the prediction control period and the predicted wind energy capturing power and the ideal wind energy capturing power of the wind turbine in the prediction control period by using a wind energy capturing prediction model according to the actual rotor speed, the actual incoming wind speed, the actual energy conversion efficiency and the actual torque value in the control period which is the last control period of the current control period and the incoming wind speed in each prediction control period.
Optionally, the step of acquiring the operation state data of the wind turbine generator in the prediction control period based on the incoming wind speed further includes:
And according to the actual incoming flow wind speed, the actual running state data and the actual target torque value of the current control period and the previous control period, and the incoming flow wind speed and the running state data in each prediction control period, the deformation acceleration in the prediction control period is predicted by using a deformation acceleration prediction model in sequence.
Optionally, the wind energy capture prediction model is expressed as:
Wherein, the For characterizing said predicted wind energy capture power in an ith said predicted control period, ρ a for characterizing air density, pi for characterizing circumferential rate, R for characterizing rotor radius of said wind turbine,For characterizing said ideal wind energy capture power during an ith said predictive control period,For characterizing the energy conversion efficiency in the ith said predictive control period,A preset maximum value for characterizing the energy conversion efficiency,For characterizing said incoming wind speed in an ith said predictive control period,For the theoretical value of the pitch angle corresponding to the incoming wind speed in the ith predictive control period,For characterizing the tip speed ratio in the ith said predictive control period,The method comprises the steps of representing the rotor speed of the wind wheel in an ith predictive control period, representing the gear box transformation ratio of the wind turbine by N gear, representing the moment of inertia of the wind wheel by J rotor, representing the actual rotor speed of the wind wheel in the current control period by omega 0, and representing preset parameters by a 1、a2、a3、a4、a5、a6、b1、b2 respectively.
Optionally, the deformation acceleration prediction model is expressed as:
Wherein F is used for representing a deformation acceleration prediction model, For characterizing said deformation acceleration in an ith said predictive control period,For characterizing said operating state data during an ith said predictive control period, x i for characterizing said actual operating state data during an ith said current control period,For characterizing the generator torque corresponding to the i-th said predicted control period,The method comprises the steps of representing incoming wind speed in an ith predictive control period, representing active power of the wind turbine corresponding to the ith predictive control period by P i, and representing wind wheel rotating speed of the wind turbine corresponding to the ith predictive control period by omega i.
Optionally, the deformation acceleration prediction model is a support vector machine, and a Gaussian kernel function is adopted as a kernel function in the deformation acceleration prediction model, wherein the deformation acceleration prediction model is obtained through training according to historical running state data, historical torque data and historical incoming flow wind speed data of the wind turbine generator.
In a second aspect, the present disclosure provides a control system for a wind turbine. The wind turbine generator comprises a generator and a tower.
The control system includes:
the wind speed acquisition module is used for acquiring the incoming wind speed of the wind turbine generator in at least one prediction control period in the current control period;
the state data prediction module is used for acquiring running state data of the wind turbine generator in the prediction control period respectively based on the incoming wind speed, wherein the running state data comprises predicted wind energy capture power, ideal wind energy capture power and lateral deformation acceleration of the tower;
The calculation module is used for generating a target control sequence based on the running state data and a preset cost function of the generator, wherein the target control sequence comprises target torque values of generator torques corresponding to the prediction control periods respectively;
And the control module is used for controlling the generator torque according to the target torque value in the target control sequence in response to entering the next control period.
Optionally, the preset cost function is expressed as:
Wherein, the For characterizing the generator torque respectively corresponding from the 1 st to the nth predictive control period, F 1 for characterizing a first weight factor, F 2 for characterizing a second weight factor, n for characterizing the number of predictive control periods, T s for characterizing the duration of the predictive control period,For characterizing said predicted wind energy capture power during an ith said predicted control period,For characterizing said ideal wind energy capture power during an ith said predictive control period,For characterizing said deformation acceleration in an ith said predictive control period,The method is used for representing a preset maximum deformation acceleration record value;
the predicted wind energy capture power, the ideal wind energy capture power, and the deformation acceleration are each represented based on the generator torque.
Optionally, the solution module is specifically configured to perform iterative computation on the torque control sequence and the iteration change rate in a plurality of different solution directions by using a particle swarm algorithm, until the number of times of iterative computation reaches a preset iteration number, and obtain the target control sequence;
the target control sequence is the torque control sequence corresponding to the preset cost function in all solving directions when the preset cost function takes a global minimum value.
Optionally, the formula of the iterative calculation is:
Wherein, the For characterizing the torque control sequence obtained by the j-th iterative calculation,For characterizing the iteration change rate obtained by the jth iteration calculation,For characterizing the torque control sequence corresponding to the preset cost function taking the minimum value in the previous j iterative computations of the solving direction,For characterizing the torque control sequence corresponding to the preset cost function taking the global minimum in the previous j iterative computations of all the solving directions, c 1 and c 2 are respectively used for characterizing learning factors, r 1 and r 2 are respectively used for characterizing preset parameters,For characterizing inertial weights.
Optionally, the wind turbine generator further comprises a wind wheel;
The state data prediction module includes:
the wind energy capturing prediction unit is used for obtaining the rotor rotating speed of the wind wheel in the prediction control period by utilizing a wind energy capturing prediction model according to the actual rotor rotating speed, the actual incoming wind speed, the actual energy conversion efficiency and the actual torque value in the control period which is the last control period of the current control period and the incoming wind speed in each prediction control period, and obtaining the predicted wind energy capturing power and the ideal wind energy capturing power of the wind turbine generator in the prediction control period.
Optionally, the state data prediction module includes:
And the deformation acceleration prediction unit is used for sequentially predicting and obtaining the deformation acceleration in the prediction control period by using a deformation acceleration prediction model according to the actual incoming flow wind speed, the actual running state data and the actual target torque value of each current control period and the previous control period and the incoming flow wind speed and the running state data in each prediction control period.
Optionally, the wind energy capture prediction model is expressed as:
Wherein, the For characterizing said predicted wind energy capture power in an ith said predicted control period, ρ a for characterizing air density, pi for characterizing circumferential rate, R for characterizing rotor radius of said wind turbine,For characterizing said ideal wind energy capture power during an ith said predictive control period,For characterizing the energy conversion efficiency in the ith said predictive control period,A preset maximum value for characterizing the energy conversion efficiency,For characterizing said incoming wind speed in an ith said predictive control period,For the theoretical value of the pitch angle corresponding to the incoming wind speed in the ith predictive control period,For characterizing the tip speed ratio in the ith said predictive control period,The method comprises the steps of representing the rotor speed of the wind wheel in an ith predictive control period, representing the gear box transformation ratio of the wind turbine by N gear, representing the moment of inertia of the wind wheel by J rotor, representing the actual rotor speed of the wind wheel in the current control period by omega 0, and representing preset parameters by a 1、a2、a3、a4、a5、a6、b1、b2 respectively.
Optionally, the deformation acceleration prediction model is expressed as:
Wherein F is used for representing a deformation acceleration prediction model, For characterizing said deformation acceleration in an ith said predictive control period,For characterizing said operating state data during an ith said predictive control period, x i for characterizing said actual operating state data during an ith said current control period,For characterizing the generator torque corresponding to the i-th said predicted control period,The method comprises the steps of representing incoming wind speed in an ith predictive control period, representing active power of the wind turbine corresponding to the ith predictive control period by P i, and representing wind wheel rotating speed of the wind turbine corresponding to the ith predictive control period by omega i.
Optionally, the deformation acceleration prediction model is a support vector machine, and a Gaussian kernel function is adopted as a kernel function in the deformation acceleration prediction model, wherein the deformation acceleration prediction model is obtained through training according to historical running state data, historical torque data and historical incoming flow wind speed data of the wind turbine generator.
In a third aspect, the present disclosure provides an electronic device comprising a memory, a processor and a computer program stored on the memory for running on the processor, the processor implementing the control method of the first aspect when executing the computer program.
In a fourth aspect, the present disclosure provides a computer-readable storage medium having stored thereon a computer program which, when executed by a processor, implements the control method of the first aspect.
The wind turbine generator system has the positive progress effects that based on the pareto theory, a preset cost function is provided, the tower load and wind energy capturing power of the wind turbine generator system can be cooperatively optimized, the lateral structural load of the tower of the wind turbine generator system can be effectively reduced, the power output quality of the generator applied to a large wind turbine generator system is improved, and the running reliability and high energy efficiency of the wind turbine generator system are improved.
And combining the established wind energy capturing prediction model and the deformation acceleration prediction model for acquiring the lateral deformation acceleration of the tower, adopting a particle swarm algorithm to solve the nonlinear preset cost function in real time so as to obtain a target control sequence comprising a target torque value corresponding to each prediction control period, and further controlling the generator torque in the next control period by using the target torque value in the target control sequence.
Drawings
Fig. 1 is a schematic flow chart of a control method provided in embodiment 1 of the disclosure;
fig. 2 is a schematic flow chart of a particle swarm algorithm according to embodiment 1 of the present disclosure;
fig. 3 is a schematic block diagram of a control system according to embodiment 2 of the present disclosure;
Fig. 4 is a schematic structural diagram of a wind turbine generator provided in embodiment 3 of the present disclosure;
fig. 5 is a schematic block diagram of an electronic device according to embodiment 4 of the present disclosure.
Detailed Description
The present disclosure is further illustrated by way of examples below, but is not thereby limited to the scope of the examples described.
It should be noted that, if there is a description of "first", "second", etc. in the embodiments of the present disclosure, the description of "first", "second", etc. is for descriptive purposes only and is not to be construed as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defining "a first" or "a second" may explicitly or implicitly include at least one such feature.
In addition, the technical solutions of the embodiments may be combined with each other, but it is necessary to be based on the fact that those skilled in the art can realize the technical solutions, and when the technical solutions are contradictory or cannot be realized, the combination of the technical solutions should be considered as not exist, and is not within the protection scope of the present disclosure.
Example 1
The embodiment provides a control method of a wind turbine generator set shown in fig. 1. The wind turbine mainly comprises a wind wheel (blade), a generator, a tower and the like.
The control method comprises the following steps:
s101, acquiring the incoming wind speed of a wind turbine generator in at least one prediction control period in a current control period;
S102, acquiring running state data of the wind turbine generator set in a prediction control period respectively based on the incoming wind speed, wherein the running state data comprise predicted wind energy capturing power, ideal wind energy capturing power and lateral deformation acceleration of a tower;
S103, generating a target control sequence based on the running state data and a preset cost function of the generator, wherein the target control sequence comprises target torque values of generator torque corresponding to the prediction control period respectively, and the number of the target torque values corresponds to the prediction step length;
S104, in response to entering the next control period, controlling the generator torque according to the target torque value in the target control sequence.
According to the embodiment, the running state data of the wind turbine generator in the prediction control period is predicted through the acquired incoming wind speed in the prediction control period. Wherein the operational state data comprises operational state data comprising predicted wind energy capture power, ideal wind energy capture power, and tower lateral deformation acceleration.
And solving a preset cost function based on the running state data to obtain a target control sequence. Wherein the target control sequence includes target torque values each within a predicted control period.
After the next control period, the generator torque is controlled according to the target torque value in the target control sequence. The method can realize the cooperative optimization of the tower load and wind energy capturing power of the wind turbine, effectively reduce the lateral structural load of the tower of the wind turbine, and improve the power output quality of the generator applied to the large wind turbine.
And after entering the next control period, repeating the above-mentioned process with it as the current control period to obtain again the control sequence for the target.
In step S101, there may be one or more prediction control periods, and the number of prediction control periods characterizes the prediction step size. That is, the prediction step length may control the length of the target control sequence, the number of target torque values contained in the target control sequence is the same as the number of prediction control periods, and the target torque values correspond to the prediction control periods one by one.
Illustratively, the prediction step size is first determined as n, i.e., the number of prediction control periods is determined as n. The duration of each predictive control period is T s. In consideration of the wind speed variation and the accuracy of the wind measuring device, the prediction step length n and the duration T s of the prediction control period are not required to be too large.
Therefore, the wind speed of the incoming flow of the wind turbine generator from the 1 st predictive control period to the nth predictive control period is measured by the wind measuring device and is sequentially as follows
The wind measuring device can be a laser radar detection device. The lidar detection device may calculate the distance of the object by sending a laser pulse and measuring its return time. In wind speed detection, the laser radar detection device can measure the distance from the position of the wind turbine generator to particulate matters (such as dust, aerosol and the like) in the air, and then judge the incoming wind speed which is about to reach the wind turbine generator.
The lidar detection device may obtain time-series data of the incoming wind speed by continuously measuring to represent the incoming wind speed measured continuously over a period of time. And determining a plurality of discrete predictive control periods from the time, and respectively obtaining the incoming wind speed in each predictive control period.
Obtaining the incoming wind speed from the 1 st predictive control period to the nth predictive control period based on step S101Step S102 may respectively obtain operation state data of the wind turbine generator in each prediction control period.
Step S102 comprises the steps of obtaining the rotor rotating speed of a wind wheel in a predicted control period by utilizing a wind energy capturing prediction model according to the actual rotor rotating speed, the actual incoming wind speed, the actual energy conversion efficiency and the actual torque value in the previous control period of the current control period and the incoming wind speed in each predicted control period, and obtaining the predicted wind energy capturing power and the ideal wind energy capturing power of the wind turbine in the predicted control period by utilizing the wind energy capturing prediction model.
For example, the wind energy capture prediction model may be expressed as:
Wherein, the For characterizing the wind energy capture power predicted in the ith predictive control period, ρ a for characterizing the air density, pi for characterizing the circumferential rate, R for characterizing the rotor radius of the wind turbine,For characterizing the ideal wind energy capture power during the ith predictive control period,For characterizing the energy conversion efficiency in the ith predictive control period,A preset maximum value for characterizing the energy conversion efficiency,For characterizing the incoming wind speed in the ith predictive control period,For the theoretical value of the pitch angle corresponding to the incoming wind speed in the ith predictive control period,For characterizing the tip speed ratio in the ith predictive control period,The method comprises the steps of representing the rotor rotating speed of the wind wheel in an ith prediction control period, representing the gear box transformation ratio of the wind turbine by N gear, representing the moment of inertia of the wind wheel by J rotor, representing the actual rotor rotating speed of the wind wheel in a current control period by omega 0, and representing preset parameters by a 1、a2、a3、a4、a5、a6、b1、b2 respectively.
The pitch angle theoretical value beta i can be determined by an optimal wind-power curve, wherein the optimal wind refers to the maximum wind energy capturing power which can be achieved in a low wind speed area, and the curve is determined in the design stage of the wind turbine generator.
The rotor speed of the wind wheel in the 1 st predictive control period and the wind energy conversion efficiency of the wind turbine in the 1 st predictive control period are calculated according to the actual rotor speed, the actual incoming wind speed, the actual energy conversion efficiency and the actual torque value of the wind wheel in the previous control period of the current control period;
by using the wind energy capturing prediction model, the rotor speed of the wind wheel in each prediction control period and the predicted wind energy capturing power of the wind turbine in each prediction control period and the ideal wind energy capturing power of the wind turbine in each prediction control period are sequentially calculated based on the incoming wind speed, the rotor speed in the 1 st prediction control period and the wind energy conversion efficiency in the 1 st prediction control period.
That is, the incoming wind speed based on the 1 st predictive control period to the n-th predictive control periodAnd the wind energy capturing prediction model can respectively represent the predicted wind energy capturing power asExpressed as ideal wind energy capture power
Step S102 further includes:
and according to the actual incoming flow wind speed, the actual running state data and the actual target torque value of the current control period and the previous control period, and the incoming flow wind speed and the running state data in each prediction control period, the deformation acceleration in the prediction control period is obtained by utilizing the deformation acceleration prediction model in sequence.
Since the dynamic behavior of the wind turbine may be represented as a second order model, the second incoming wind speed of the predictive control period to be predicted may be obtained by at least two predicted predictive control periods.
Illustratively, the deformation acceleration prediction model is expressed as:
Wherein F is used for representing a deformation acceleration prediction model, For characterizing the deformation acceleration in the ith predictive control period,For characterizing the operating state data during the ith predictive control period, x i for characterizing the actual operating state data during the ith current control period,For characterizing the generator torque corresponding to the ith predictive control period,The method is used for representing incoming wind speed in the ith predictive control period, P i is used for representing active power of the wind turbine corresponding to the ith predictive control period, and omega i is used for representing wind wheel rotating speed of the wind turbine corresponding to the ith predictive control period.
Specifically, when predicting the deformation acceleration in the 1 st prediction control period, the actual incoming flow wind speed, the actual running state data, the actual target torque value and the first incoming flow wind speed in the 1 st prediction control period of the current control period and the previous control period can be substituted into the deformation acceleration prediction model to predict and obtain the first deformation acceleration in the 1 st prediction control period.
Similarly, when the deformation acceleration of the 2 nd prediction control period is predicted, the first incoming wind speed, the first running state data, the first target torque value, the actual incoming wind speed, the actual running state data and the actual target torque value of the current control period in the 1 st prediction control period can be substituted into the deformation acceleration prediction model to predict and obtain the second deformation acceleration of the 2 nd prediction control period.
When the deformation acceleration of the 3 rd and subsequent prediction control periods is predicted, substituting the second incoming wind speed, the second running state data, the second target torque value and the third incoming wind speed of the second prediction control period into the deformation acceleration prediction model to predict and obtain the third deformation acceleration of the second prediction control period.
The two first prediction control periods are two predicted adjacent pre-stored control periods, and the second prediction control period is adjacent to the latter one of the two first prediction control periods.
Illustratively, when predicting the deformation acceleration of the 1 st predictive control period:
for example, when predicting the deformation acceleration in the 1 st predictive control cycle:
Wherein x k0、xk-1 is used to characterize the actual operating state data in the current control period and the last control period, respectively, For characterizing the actual torque value in the current control period and in the last control period respectively,Respectively for characterizing the actual incoming wind speed in the current control period and in the last control period.
When deformation acceleration of the 2 nd prediction control period is predicted:
In addition, the deformation acceleration prediction model can be a support vector machine, and a Gaussian kernel function is adopted as a kernel function in the deformation acceleration prediction model.
Support vector regression is a machine learning algorithm used for pattern classification and regression analysis. It can effectively deal with both linear and nonlinear data classification problems.
The basic idea of SVR is to find an optimal hyperplane that separates the different classes of data samples and to find a set of support vectors (support samples) on the boundaries on both sides of the hyperplane for defining decision boundaries. This optimal hyperplane is called the maximum-spaced hyperplane, whose goal is to maximize the distance of the support vector on the boundary from the decision boundary.
The deformation acceleration prediction model is obtained through training according to historical running state data, historical torque data and historical incoming flow wind speed data of the wind turbine generator.
For example, the deformation acceleration prediction model may be specifically expressed as:
Wherein F (y) is used for representing the lateral deformation acceleration of the tower, W is used for representing the multidimensional weight factor, b is used for representing the adjustable factor, Used for representing a regression equation to express the mapping relation of the input y and the output F (y).
Substituting Lagrangian multiplier xi i,ξi *, solving by adopting a quadratic programming method, and finally, expressing a lateral deformation acceleration prediction model of the tower as follows:
Wherein K (y i -y) is a Gaussian kernel function.
In step S103, the preset cost function may be expressed as:
the preset cost function is expressed as:
Wherein, the For characterizing the generator torque respectively corresponding from the 1 st to the n th predictive control period, F 1 for characterizing the first weight factor, F 2 for characterizing the second weight factor, n for characterizing the number of predictive control periods, T s for characterizing the duration of the predictive control period,For characterizing the predicted wind energy capture power in the ith predicted control period,For characterizing the ideal wind energy capture power during the ith predictive control period,For characterizing the deformation acceleration in the ith predictive control period,The method is used for representing a preset maximum deformation acceleration record value.
The predicted wind energy capture power, the ideal wind energy capture power, and the deformation acceleration are all represented based on the generator torque.
In order to generate the target control sequence, the nonlinear preset cost function needs to be solved. The step S103 specifically includes:
according to the running state data, performing iterative computation on the torque control sequence and the iteration change rate in a plurality of different solving directions by using a particle swarm algorithm respectively until the number of iterative computation reaches the preset iteration number to obtain a target control sequence;
the target control sequence is a torque control sequence corresponding to a preset cost function in all solving directions when the preset cost function takes a global minimum value.
Illustratively, referring to fig. 2, the torque control sequence and the iterative rate of change are iteratively calculated from m different solving directions based on a particle swarm algorithm, which is equivalent to searching in space for a population of m particles.
For any particle, various parameters used in the algorithm are required to be initialized, such as learning factors and preset parameters. I.e. for different solving directions, the values of the learning factors and the preset parameters obtained by initialization are different. Based on the initialized algorithm parameters, calculating the value of a preset cost function of each particle, updating the iteration change rate and the torque control sequence of each particle, and based on the torque control sequence corresponding to the minimum residence time of the preset cost function obtained by current calculation, updating the local optimal torque control sequence and the global optimal torque control sequence. And judging whether the number of iterative computation is smaller than the preset number of iterative computation, if so, continuing the iterative computation to update the local optimal torque control sequence and the global optimal torque control sequence, and if not, outputting the global optimal torque control sequence as a target control sequence.
And then carrying out iterative computation on the preset cost function in different solving directions to obtain the value of the preset cost function.
The formula of iterative calculation is:
Wherein, the For characterizing the torque control sequence obtained by the j-th iterative calculation,For characterizing the iteration change rate obtained by the jth iteration calculation,Used for representing a torque control sequence corresponding to the preset cost function taking the minimum value in the previous j iterative calculations of the solving direction,For characterizing the corresponding torque control sequence when the preset cost function takes the global minimum in the previous j iterative computations of all solving directions, c 1 and c 2 are respectively used for characterizing the learning factors, r 1 and r 2 are respectively used for characterizing the preset parameters,For characterizing inertial weights.
Finally, the target control sequence is obtained
The iterative change rate includes a change value corresponding to each n torque values in the corresponding torque control sequence. Namely, n torque values contained in the torque control sequence are obtained through the jth iterative computation, the iteration change rate obtained through the j+1th iterative computation is firstly obtained, each change value in the iteration change rate is added with the torque value in a one-to-one correspondence mode, and the j+1th iterative computation on the torque control sequence can be achieved.
In step S104, in response to entering the next control period, the first target torque value in the target control sequence is determinedAs an output of a controller of the generator to effect control of the generator torque.
In addition, before solving the preset cost function, the target torque value of the generator torque of the wind turbine and the rotor rotating speed of the wind wheel can be constrained:
|ωref-ωi|≤σωωref,
Wherein, the For characterizing the torque reference, ω ref for characterizing the rotor speed reference, σ T for characterizing the torque allowable deviation range, and σ ω for characterizing the speed allowable deviation range.
Example 2
The embodiment provides a control system of a wind turbine generator shown in fig. 3. The wind turbine mainly comprises a wind wheel (blade), a generator, a tower and the like.
The control system includes:
the wind speed acquisition module 301 is configured to acquire an incoming wind speed of the wind turbine generator in at least one prediction control period in a current control period;
the state data prediction module 302 is configured to obtain, based on the incoming wind speed, operation state data of the wind turbine generator in the prediction control period, where the operation state data includes predicted wind energy capture power, ideal wind energy capture power, and deformation acceleration of the tower in a lateral direction;
A resolving module 303, configured to generate a target control sequence based on the running state data and a preset cost function of the generator, where the target control sequence includes target torque values of generator torques corresponding to the predicted control periods respectively;
a control module 304 for controlling the generator torque according to the torque value in the target control sequence in response to entering the next control period.
According to the embodiment, the running state data of the wind turbine generator in the prediction control period is predicted through the acquired incoming wind speed in the prediction control period. Wherein the operational state data comprises operational state data comprising predicted wind energy capture power, ideal wind energy capture power, and tower lateral deformation acceleration.
And solving a preset cost function based on the running state data to obtain a target control sequence. Wherein the target control sequence includes target torque values each within a predicted control period.
After the next control period, the generator torque is controlled according to the target torque value in the target control sequence. The method can realize the cooperative optimization of the tower load and wind energy capturing power of the wind turbine, effectively reduce the lateral structural load of the tower of the wind turbine, and improve the power output quality of the generator applied to the large wind turbine.
And after entering the next control period, repeating the above-mentioned process with it as the current control period to obtain again the control sequence for the target.
For the wind speed acquisition module 301, there may be one or more prediction control periods, the number of which characterizes the prediction step size. That is, the prediction step length may control the length of the target control sequence, the number of target torque values contained in the target control sequence is the same as the number of prediction control periods, and the target torque values correspond to the prediction control periods one by one.
Illustratively, the prediction step size is first determined as n, i.e., the number of prediction control periods is determined as n. The duration of each predictive control period is T s. In consideration of the wind speed variation and the accuracy of the wind measuring device, the prediction step length n and the duration T s of the prediction control period are not required to be too large.
Therefore, the wind speed of the incoming flow of the wind turbine generator from the 1 st predictive control period to the nth predictive control period is measured by the wind measuring device and is sequentially as follows
The wind measuring device can be a laser radar detection device. The lidar detection device may calculate the distance of the object by sending a laser pulse and measuring its return time. In wind speed detection, the laser radar detection device can measure the distance from the position of the wind turbine generator to particulate matters (such as dust, aerosol and the like) in the air, and then judge the incoming wind speed which is about to reach the wind turbine generator.
The lidar detection device may obtain time-series data of the incoming wind speed by continuously measuring to represent the incoming wind speed measured continuously over a period of time. And determining a plurality of discrete predictive control periods from the time, and respectively obtaining the incoming wind speed in each predictive control period.
Obtaining the incoming wind speed from the 1 st predictive control period to the nth predictive control period based on the wind speed obtaining module 301The state data prediction module 302 may respectively obtain operation state data of the wind turbine generator in each prediction control period.
The state data prediction module 302 includes:
The wind energy capturing and predicting unit is used for obtaining the rotor rotating speed of the wind wheel in the predicted control period by utilizing the wind energy capturing and predicting model according to the actual rotor rotating speed, the actual incoming wind speed, the actual energy conversion efficiency and the actual torque value in the previous control period of the current control period and the incoming wind speed in each predicted control period, and the predicted wind energy capturing power and the ideal wind energy capturing power of the wind turbine in the predicted control period.
For example, the wind energy capture prediction model may be expressed as:
Wherein, the For characterizing the wind energy capture power predicted in the ith predictive control period, ρ a for characterizing the air density, pi for characterizing the circumferential rate, R for characterizing the rotor radius of the wind turbine,For characterizing the ideal wind energy capture power during the ith predictive control period,For characterizing the energy conversion efficiency in the ith predictive control period,A preset maximum value for characterizing the energy conversion efficiency,For characterizing the incoming wind speed in the ith predictive control period,For the theoretical value of the pitch angle corresponding to the incoming wind speed in the ith predictive control period,For characterizing the tip speed ratio in the ith predictive control period,The method comprises the steps of representing the rotor rotating speed of the wind wheel in an ith prediction control period, representing the gear box transformation ratio of the wind turbine by N gear, representing the moment of inertia of the wind wheel by J rotor, representing the actual rotor rotating speed of the wind wheel in a current control period by omega 0, and representing preset parameters by a 1、a2、a3、a4、a5、a6、b1、b2 respectively.
The pitch angle theoretical value beta i can be determined by an optimal wind-power curve, wherein the optimal wind refers to the maximum wind energy capturing power which can be achieved in a low wind speed area, and the curve is determined in the design stage of the wind turbine generator.
The rotor speed of the wind wheel in the 1 st predictive control period and the wind energy conversion efficiency of the wind turbine in the 1 st predictive control period are calculated according to the actual rotor speed, the actual incoming wind speed, the actual energy conversion efficiency and the actual torque value of the wind wheel in the previous control period of the current control period;
by using the wind energy capturing prediction model, the rotor speed of the wind wheel in each prediction control period and the predicted wind energy capturing power of the wind turbine in each prediction control period and the ideal wind energy capturing power of the wind turbine in each prediction control period are sequentially calculated based on the incoming wind speed, the rotor speed in the 1 st prediction control period and the wind energy conversion efficiency in the 1 st prediction control period.
That is, the incoming wind speed based on the 1 st predictive control period to the n-th predictive control periodAnd the wind energy capturing prediction model can respectively represent the predicted wind energy capturing power asExpressed as ideal wind energy capture power
The state data prediction module 302 further includes:
The deformation acceleration prediction unit is used for sequentially predicting the deformation acceleration in the prediction control period by using the deformation acceleration prediction model according to the actual incoming flow wind speed, the actual running state data and the actual target torque value of the current control period and the previous control period and the incoming flow wind speed and the running state data in each prediction control period.
Since the dynamic behavior of the wind turbine may be represented as a second order model, the second incoming wind speed of the predictive control period to be predicted may be obtained by at least two predicted predictive control periods.
Illustratively, the deformation acceleration prediction model is expressed as:
Wherein F is used for representing a deformation acceleration prediction model, For characterizing the deformation acceleration in the ith predictive control period,For characterizing the operating state data during the ith predictive control period, x i for characterizing the actual operating state data during the ith current control period,For characterizing the generator torque corresponding to the ith predictive control period,The method is used for representing incoming wind speed in the ith predictive control period, P i is used for representing active power of the wind turbine corresponding to the ith predictive control period, and omega i is used for representing wind wheel rotating speed of the wind turbine corresponding to the ith predictive control period.
Specifically, when predicting the deformation acceleration in the 1 st prediction control period, the actual incoming flow wind speed, the actual running state data, the actual target torque value and the first incoming flow wind speed in the 1 st prediction control period of the current control period and the previous control period can be substituted into the deformation acceleration prediction model to predict and obtain the first deformation acceleration in the 1 st prediction control period.
Similarly, when the deformation acceleration of the 2 nd prediction control period is predicted, the first incoming wind speed, the first running state data, the first target torque value, the actual incoming wind speed, the actual running state data and the actual target torque value of the current control period in the 1 st prediction control period can be substituted into the deformation acceleration prediction model to predict and obtain the second deformation acceleration of the 2 nd prediction control period.
When the deformation acceleration of the 3 rd and subsequent prediction control periods is predicted, substituting the second incoming wind speed, the second running state data, the second target torque value and the third incoming wind speed of the second prediction control period into the deformation acceleration prediction model to predict and obtain the third deformation acceleration of the second prediction control period.
The two first prediction control periods are two predicted adjacent pre-stored control periods, and the second prediction control period is adjacent to the latter one of the two first prediction control periods.
Illustratively, when predicting the deformation acceleration of the 1 st predictive control period:
Wherein x k0、xk-1 is used to characterize the actual operating state data in the current control period and the last control period, respectively, For characterizing the actual torque value in the current control period and in the last control period respectively,Respectively for characterizing the actual incoming wind speed in the current control period and in the last control period.
When deformation acceleration of the 2 nd prediction control period is predicted:
In addition, the deformation acceleration prediction model can be a support vector machine, and a Gaussian kernel function is adopted as a kernel function in the deformation acceleration prediction model.
Support vector regression (Support Vector Regression, SVR) is a machine learning algorithm used to perform pattern classification and regression analysis. It can effectively deal with both linear and nonlinear data classification problems.
The basic idea of SVR is to find an optimal hyperplane that separates the different classes of data samples and to find a set of support vectors (support samples) on the boundaries on both sides of the hyperplane for defining decision boundaries. This optimal hyperplane is called the maximum-spaced hyperplane, whose goal is to maximize the distance of the support vector on the boundary from the decision boundary.
The deformation acceleration prediction model is obtained through training according to historical running state data, historical torque data and historical incoming flow wind speed data of the wind turbine generator.
For example, the deformation acceleration prediction model may be specifically expressed as:
Wherein F (y) is used for representing the lateral deformation acceleration of the tower, W is used for representing the multidimensional weight factor, b is used for representing the adjustable factor, Used for representing a regression equation to express the mapping relation of the input y and the output F (y).
Substituting Lagrangian multiplier xi i,ξi *, solving by adopting a quadratic programming method, and finally, expressing a lateral deformation acceleration prediction model of the tower as follows:
Wherein K (y i -y) is a Gaussian kernel function.
The preset cost function is expressed as:
Wherein, the For characterizing the generator torque respectively corresponding from the 1 st to the n th predictive control period, F 1 for characterizing the first weight factor, F 2 for characterizing the second weight factor, n for characterizing the number of predictive control periods, T s for characterizing the duration of the predictive control period, P i for characterizing the predicted wind energy capture power in the i th predictive control period,For characterizing the ideal wind energy capture power during the ith predictive control period,For characterizing the deformation acceleration in the ith predictive control period,The method is used for representing a preset maximum deformation acceleration record value.
The measured wind energy capture power, the ideal wind energy capture power and the deformation acceleration are all expressed based on the torque of the generator.
In order to generate the target control sequence, the nonlinear preset cost function needs to be solved. The calculation module 303 is specifically configured to perform iterative calculation on the torque control sequence and the iteration change rate in a plurality of different solving directions by using a particle swarm algorithm according to the running state data, until the number of iterative calculation reaches a preset number of iterations, and obtain a target control sequence.
The target control sequence is a torque control sequence corresponding to a preset cost function in all solving directions when the preset cost function takes a global minimum value.
Illustratively, referring to fig. 2, the torque control sequence and the iterative rate of change are iteratively calculated from m different solving directions based on a particle swarm algorithm, which is equivalent to searching in space for a population of m particles.
For any particle, various parameters used in the algorithm are required to be initialized, such as learning factors and preset parameters. I.e. for different solving directions, the values of the learning factors and the preset parameters obtained by initialization are different. Based on the initialized algorithm parameters, calculating the value of a preset cost function of each particle, updating the iteration change rate and the torque control sequence of each particle, and based on the torque control sequence corresponding to the minimum residence time of the preset cost function obtained by current calculation, updating the local optimal torque control sequence and the global optimal torque control sequence. And judging whether the number of iterative computation is smaller than the preset number of iterative computation, if so, continuing the iterative computation to update the local optimal torque control sequence and the global optimal torque control sequence, and if not, outputting the global optimal torque control sequence as a target control sequence.
And then carrying out iterative computation on the preset cost function in different solving directions to obtain the value of the preset cost function.
The formula of iterative calculation is:
Wherein, the For characterizing the torque control sequence obtained by the j-th iterative calculation,For characterizing the iteration change rate obtained by the jth iteration calculation,Used for representing a torque control sequence corresponding to the preset cost function taking the minimum value in the previous j iterative calculations of the solving direction,For characterizing the corresponding torque control sequence when the preset cost function takes the global minimum in the previous j iterative computations of all solving directions, c 1 and c 2 are respectively used for characterizing the learning factors, r 1 and r 2 are respectively used for characterizing the preset parameters,For characterizing inertial weights.
Finally, the target control sequence is obtained
The iterative change rate includes a change value corresponding to each n torque values in the corresponding torque control sequence. Namely, n torque values contained in the torque control sequence are obtained through the jth iterative computation, the iteration change rate obtained through the j+1th iterative computation is firstly obtained, each change value in the iteration change rate is added with the torque value in a one-to-one correspondence mode, and the j+1th iterative computation on the torque control sequence can be achieved.
In step S104, in response to entering the next control period, the first target torque value in the target control sequence is determinedAs an output of a controller of the generator to effect control of the generator torque.
In addition, before solving the preset cost function, the target torque value of the generator torque of the wind turbine and the rotor rotating speed of the wind wheel can be constrained:
|ωref-ωi|≤σωωref,
Wherein, the For characterizing the torque reference, ω ref for characterizing the rotor speed reference, σ T for characterizing the torque allowable deviation range, and σ ω for characterizing the speed allowable deviation range.
Example 3
The embodiment provides a wind turbine generator system, which comprises a control system in embodiment 2.
For example, see fig. 4. The method comprises the steps that the running state data of a wind turbine in a prediction control period are predicted according to the incoming wind speed by using a wind energy capturing prediction model and a deformation acceleration prediction model, wherein the incoming wind speed is acquired by a radar of the ultra-large wind turbine in the prediction control period. Wherein the operational state data comprises operational state data comprising predicted wind energy capture power, ideal wind energy capture power, and tower lateral deformation acceleration. And solving a preset cost function based on the running state data by using a particle swarm algorithm to obtain a target control sequence. Wherein the target control sequence includes target torque values each within a predicted control period.
After the next control period, the generator torque is controlled according to the target torque value in the target control sequence. The method can realize the cooperative optimization of the tower load and wind energy capturing power of the wind turbine, effectively reduce the lateral structural load of the tower of the wind turbine, and improve the power output quality of the generator applied to the large wind turbine. And after entering the next control period, repeating the above-mentioned process with it as the current control period to obtain again the control sequence for the target.
Example 4
Fig. 5 shows a structure of one of the electronic devices of the present disclosure. The electronic device comprises a memory, a processor, and a computer program stored on the memory and executable on the processor, wherein the processor implements the control method when executing the program. The electronic device 50 shown in fig. 5 is merely an example and should not be construed to limit the functionality and scope of use of embodiments of the present disclosure in any way.
As shown in fig. 5, the electronic device 50 may also be in the form of a general purpose computing device, which may be a server device, for example. The components of the electronic device 50 may include, but are not limited to, the at least one processor 51 described above, the at least one memory 52 described above, and a bus 53 that connects the various system components, including the memory 52 and the processor 51.
The bus 53 includes a data bus, an address bus, and a control bus.
Memory 52 may include volatile memory such as Random Access Memory (RAM) 521 and/or cache memory 522, and may further include Read Only Memory (ROM) 523.
Memory 52 may also include a program/utility 525 having a set (at least one) of program modules 524, such program modules 524 including, but not limited to, an operating system, one or more application programs, other program modules, and program data, each or some combination of which may include an implementation of a network environment.
The processor 51 executes various functional applications and data processing, such as the control method described above of the present disclosure, by running a computer program stored in the memory 52.
The electronic device 50 may also communicate with one or more external devices 54 (e.g., keyboard, pointing device, etc.). Such communication may occur through an input/output (I/O) interface 55. Also, model-generating device 50 may also communicate with one or more networks such as a Local Area Network (LAN), a Wide Area Network (WAN), and/or a public network such as the internet via network adapter 56. As shown in fig. 5, the network adapter 56 communicates with other modules of the model-generating device 50 via the bus 53. It should be appreciated that although not shown, other hardware and/or software modules may be used in connection with the model-generating device 50, including, but not limited to, microcode, device drivers, redundant processors, external disk drive arrays, RAID (disk array) systems, tape drives, and data backup storage systems, among others.
It should be noted that although several units/modules or sub-units/modules of an electronic device are mentioned in the above detailed description, such a division is merely exemplary and not mandatory. Indeed, the features and functionality of two or more units/modules described above may be embodied in one unit/module in accordance with embodiments of the present disclosure. Conversely, the features and functions of one unit/module described above may be further divided into ones that are embodied by a plurality of units/modules.
The present disclosure also provides a computer-readable storage medium having stored thereon a computer program which, when executed by a processor, implements the above-described control method.
More specifically, a readable storage medium may include, but is not limited to, a portable disk, hard disk, random access memory, read only memory, erasable programmable read only memory, optical storage device, magnetic storage device, or any suitable combination of the foregoing.
In a possible embodiment, the disclosure may also be implemented in the form of a program product comprising program code for causing a terminal device to carry out the above-mentioned control method when the program product is run on the terminal device.
Wherein the program code for carrying out the present disclosure may be written in any combination of one or more programming languages, and the program code may be executed entirely on the user device, partially on the user device, as a stand-alone software package, partially on the user device, partially on a remote device, or entirely on the remote device.
While specific embodiments of the present disclosure have been described above, it will be appreciated by those skilled in the art that this is by way of example only, and the scope of the disclosure is defined by the appended claims. Various changes and modifications to these embodiments may be made by those skilled in the art without departing from the principles and spirit of the disclosure, but such changes and modifications fall within the scope of the disclosure.

Claims (9)

1.一种风电机组的控制方法，其特征在于，所述风电机组包括发电机和塔架；1. A control method for a wind turbine generator set, characterized in that the wind turbine generator set includes a generator and a tower; 所述控制方法的步骤包括：The control method includes the following steps: 在当前控制周期内获取所述风电机组在至少一个预测控制周期内的来流风速；Within the current control cycle, obtain the incoming wind speed of the wind turbine unit in at least one predicted control cycle; 基于所述来流风速获取所述风电机组分别在所述预测控制周期内的运行状态数据；其中，所述运行状态数据包括预测风能捕获功率、理想风能捕获功率以及所述塔架侧向的形变加速度；Based on the incoming wind speed, the operating status data of the wind turbine generator within the predictive control cycle are obtained; wherein, the operating status data includes the predicted wind energy capture power, the ideal wind energy capture power, and the lateral deformation acceleration of the tower; 基于所述运行状态数据和所述发电机的预设成本函数，生成目标控制序列；其中，所述目标控制序列包括分别与所述预测控制周期对应的发电机转矩的目标转矩值；Based on the operating status data and the preset cost function of the generator, a target control sequence is generated; wherein, the target control sequence includes target torque values of the generator torque corresponding to the predicted control cycle; 响应于进入下一控制周期，根据所述目标控制序列中的所述目标转矩值控制所述发电机转矩；In response to entering the next control cycle, the generator torque is controlled according to the target torque value in the target control sequence; 所述预设成本函数表示为：The preset cost function is expressed as follows: 其中，用于表征从第1个所述预测控制周期至第n个所述预测控制周期分别对应的所述发电机转矩，F1用于表征第一权重因子，F2用于表征第二权重因子，n用于表征所述预测控制周期的数量，Ts用于表征所述预测控制周期的时长，用于表征在第i个所述预测控制周期内所述预测风能捕获功率，用于表征在第i个所述预测控制周期内所述理想风能捕获功率，用于表征在第i个所述预测控制周期内的所述形变加速度，用于表征预设最大形变加速度记录值；in, The parameters are used to characterize the generator torque corresponding to the first to the nth predictive control cycle, respectively. F1 represents the first weighting factor, F2 represents the second weighting factor, n represents the number of predictive control cycles, and Ts represents the duration of each predictive control cycle. Used to characterize the predicted wind energy capture power during the i-th prediction control period. Used to characterize the ideal wind energy capture power during the i-th prediction control cycle. Used to characterize the deformation acceleration during the i-th predictive control cycle. Used to characterize the preset maximum deformation acceleration recorded value; 所述预测风能捕获功率、所述理想风能捕获功率以及所述形变加速度均基于所述发电机转矩进行表示。The predicted wind energy capture power, the ideal wind energy capture power, and the deformation acceleration are all expressed based on the generator torque. 2.根据权利要求1所述的控制方法，其特征在于，所述基于所述运行状态数据和所述发电机的预设成本函数，生成目标控制序列的步骤包括：2. The control method according to claim 1, characterized in that the step of generating the target control sequence based on the operating state data and the preset cost function of the generator includes: 使用粒子群算法分别在多个不同的求解方向对转矩控制序列和迭代变化率进行迭代计算，直到所述迭代计算的次数达到预设迭代次数，获取所述目标控制序列；The particle swarm optimization algorithm is used to iteratively calculate the torque control sequence and the rate of change in multiple different solution directions until the number of iterations reaches a preset number of iterations, thereby obtaining the target control sequence. 其中，所述目标控制序列为在所有所述求解方向中所述预设成本函数取全局最小值时对应的所述转矩控制序列。The target control sequence is the torque control sequence corresponding to the global minimum value of the preset cost function in all the solution directions. 3.根据权利要求2所述的控制方法，其特征在于，所述迭代计算的公式为：3. The control method according to claim 2, wherein the formula for the iterative calculation is: 其中，用于表征第j次进行迭代计算得到的所述转矩控制序列，用于表征第j次进行迭代计算得到的所述迭代变化率，用于表征在所述求解方向的前j次迭代计算中所述预设成本函数取最小值时对应的所述转矩控制序列，用于表征在所有所述求解方向的前j次迭代计算中所述预设成本函数取全局最小值时对应的所述转矩控制序列，c1和c2分别用于表征学习因子，r1和r2分别用于表征预设参数，用于表征惯性权重。in, This is used to characterize the torque control sequence obtained from the j-th iteration calculation. The iterative rate of change is used to characterize the iterative calculation obtained in the j-th iteration. This is used to characterize the torque control sequence corresponding to the minimum value of the preset cost function in the first j iterations of the calculation in the solution direction. The torque control sequence is used to characterize the preset cost function when it reaches its global minimum value in the first j iterations of calculations in all the solution directions. c1 and c2 are used to characterize the learning factors, and r1 and r2 are used to characterize the preset parameters. Used to characterize inertia weights. 4.根据权利要求1-3中任一项所述的控制方法，其特征在于，所述风电机组还包括风轮；4. The control method according to any one of claims 1-3, characterized in that the wind turbine further includes a wind rotor; 所述基于所述来流风速获取所述风电机组在所述预测控制周期内的运行状态数据的步骤包括：The step of obtaining the operating status data of the wind turbine during the predictive control cycle based on the incoming wind speed includes: 根据在所述当前控制周期的上一控制周期内的实际转子转速、实际来流风速、实际能量转化效率和实际转矩值，以及在每个所述预测控制周期内的所述来流风速，利用风能捕获预测模型获取所述风轮在所述预测控制周期内的转子转速，以及所述风电机组在所述预测控制周期内的所述预测风能捕获功率、所述理想风能捕获功率；Based on the actual rotor speed, actual incoming wind speed, actual energy conversion efficiency, and actual torque value in the previous control cycle of the current control cycle, and the incoming wind speed in each of the predicted control cycles, the wind energy capture prediction model is used to obtain the rotor speed of the wind turbine in the predicted control cycle, as well as the predicted wind energy capture power and the ideal wind energy capture power of the wind turbine in the predicted control cycle. 和/或，And/or, 根据所述当前控制周期和上一控制周期各自的实际来流风速、实际运行状态数据、实际目标转矩值，以及在每个所述预测控制周期内的来流风速和运行状态数据，利用形变加速度预测模型依次预测得到在预测控制周期内的形变加速度。Based on the actual incoming wind speed, actual operating status data, and actual target torque value of the current control cycle and the previous control cycle, as well as the incoming wind speed and operating status data in each of the prediction control cycles, the deformation acceleration in the prediction control cycle is predicted sequentially using the deformation acceleration prediction model. 5.根据权利要求4所述的控制方法，其特征在于，所述风能捕获预测模型表示为：5. The control method according to claim 4, wherein the wind energy capture prediction model is expressed as: 其中，用于表征在第i个所述预测控制周期内所述预测风能捕获功率，ρa用于表征空气密度，π用于表征圆周率，R用于表征所述风电机组的风轮半径，用于表征在第i个所述预测控制周期内所述理想风能捕获功率，用于表征在第i个所述预测控制周期内的能量转化效率，用于表征所述能量转化效率的预设最大值，用于表征在第i个所述预测控制周期内的所述来流风速，为在第i个所述预测控制周期内的所述来流风速对应的桨距角理论值，用于表征在第i个所述预测控制周期内的叶尖速比值，用于表征在第i个所述预测控制周期内所述风轮的转子转速，Ngear用于表征所述风电机组的齿轮箱变比，Jrotor用于表征所述风轮的转动惯量，ω0用于表征在所述当前控制周期内所述风轮的实际转子转速，a1、a2、a3、a4、a5、a6、b1、b2分别用于表征预设参数；in, The predicted wind energy capture power is used to characterize the predicted wind energy capture power in the i-th predicted control cycle, ρa is used to characterize air density, π is used to characterize pi, and R is used to characterize the rotor radius of the wind turbine. Used to characterize the ideal wind energy capture power during the i-th prediction control cycle. Used to characterize the energy conversion efficiency during the i-th prediction control cycle. A preset maximum value used to characterize the energy conversion efficiency. Used to characterize the incoming wind speed during the i-th predictive control cycle. The theoretical value of the blade pitch angle corresponding to the incoming wind speed in the i-th predictive control cycle. Used to characterize the tip velocity ratio during the i-th predictive control cycle. The parameters are: N<sub> gear </sub>, J<sub>rotor</sub>, ω<sub>0</sub>, a<sub>1</sub>, a<sub>2</sub>, a<sub>3</sub>, a<sub>4</sub>, a<sub>5</sub>, a<sub>6</sub>, b <sub>1 </sub> , and b <sub> 2 </sub>, which are used to characterize the rotor speed of the wind turbine in the i-th predictive control cycle; N<sub>gear</sub>, which is used to characterize the gearbox ratio of the wind turbine; J<sub>rotor</sub>, which is used to characterize the moment of inertia of the wind turbine; ω<sub> 0 </sub>, which is used to characterize the actual rotor speed of the wind turbine in the current control cycle; and b<sub>1</sub>, a<sub> 2 </sub>, a<sub> 3 </sub>, a <sub>4 </sub>, a<sub> 5 </ 和/或，And/or, 所述形变加速度预测模型表示为：The deformation acceleration prediction model is expressed as follows: 其中，F用于表征形变加速度预测模型，用于表征在第i个所述预测控制周期内的所述形变加速度，用于表征在第i个所述预测控制周期内的所述运行状态数据，xi用于表征在第i个所述当前控制周期内的所述实际运行状态数据，用于表征第i个所述预测控制周期对应的所述发电机转矩，用于表征在第i个所述预测控制周期内的所述来流风速，Pi用于表征在第i个所述预测控制周期对应的所述风电机组的有功功率，ωi用于表征在第i个所述预测控制周期对应的所述风电机组的风轮转速。Where F is used to characterize the deformation acceleration prediction model, Used to characterize the deformation acceleration during the i-th predictive control cycle. The data used to characterize the operating status within the i-th predictive control cycle, and xi used to characterize the actual operating status within the i-th current control cycle. The generator torque is used to characterize the i-th predictive control cycle. The incoming wind speed is used to characterize the wind speed in the i-th predictive control cycle, P <sub>i</sub> is used to characterize the active power of the wind turbine corresponding to the i-th predictive control cycle, and ω<sub>i</sub> is used to characterize the rotor speed of the wind turbine corresponding to the i-th predictive control cycle. 6.根据权利要求5所述的控制方法，其特征在于，所述形变加速度预测模型为支持向量机，所述形变加速度预测模型中的核函数采用高斯核函数；其中，所述形变加速度预测模型根据所述风电机组的历史运行状态数据、历史转矩数据以及历史来流风速数据训练得到。6. The control method according to claim 5, wherein the deformation acceleration prediction model is a support vector machine, and the kernel function in the deformation acceleration prediction model is a Gaussian kernel function; wherein the deformation acceleration prediction model is trained based on the historical operating status data, historical torque data, and historical incoming wind speed data of the wind turbine. 7.一种风电机组的控制系统，其特征在于，所述风电机组包括发电机和塔架；7. A control system for a wind turbine generator set, characterized in that the wind turbine generator set includes a generator and a tower; 所述控制系统包括：The control system includes: 风速获取模块，用于在当前控制周期内获取所述风电机组在至少一个预测控制周期内的来流风速；The wind speed acquisition module is used to acquire the incoming wind speed of the wind turbine in at least one predicted control cycle within the current control cycle. 状态数据预测模块，用于基于所述来流风速获取所述风电机组分别在所述预测控制周期内的运行状态数据；其中，所述运行状态数据包括预测风能捕获功率、理想风能捕获功率以及所述塔架侧向的形变加速度；The status data prediction module is used to obtain the operating status data of the wind turbine in the prediction control cycle based on the incoming wind speed; wherein, the operating status data includes the predicted wind energy capture power, the ideal wind energy capture power, and the lateral deformation acceleration of the tower; 解算模块，用于基于所述运行状态数据和所述发电机的预设成本函数，生成目标控制序列；其中，所述目标控制序列包括分别与所述预测控制周期对应的发电机转矩的目标转矩值；The calculation module is used to generate a target control sequence based on the operating status data and the preset cost function of the generator; wherein, the target control sequence includes target torque values of the generator torque corresponding to the predicted control cycle; 控制模块，用于响应于进入下一控制周期，根据所述目标控制序列中的所述目标转矩值控制所述发电机转矩；The control module is configured to control the generator torque according to the target torque value in the target control sequence in response to entering the next control cycle; 所述预设成本函数表示为：The preset cost function is expressed as follows: 其中，用于表征从第1个所述预测控制周期至第n个所述预测控制周期分别对应的所述发电机转矩，F1用于表征第一权重因子，F2用于表征第二权重因子，n用于表征所述预测控制周期的数量，Ts用于表征所述预测控制周期的时长，用于表征在第i个所述预测控制周期内所述预测风能捕获功率，用于表征在第i个所述预测控制周期内所述理想风能捕获功率，用于表征在第i个所述预测控制周期内的所述形变加速度，用于表征预设最大形变加速度记录值；in, The parameters are used to characterize the generator torque corresponding to the first to the nth predictive control cycle, respectively. F1 represents the first weighting factor, F2 represents the second weighting factor, n represents the number of predictive control cycles, and Ts represents the duration of each predictive control cycle. Used to characterize the predicted wind energy capture power during the i-th prediction control period. Used to characterize the ideal wind energy capture power during the i-th prediction control cycle. Used to characterize the deformation acceleration during the i-th predictive control cycle. Used to characterize the preset maximum deformation acceleration recorded value; 所述预测风能捕获功率、所述理想风能捕获功率以及所述形变加速度均基于所述发电机转矩进行表示。The predicted wind energy capture power, the ideal wind energy capture power, and the deformation acceleration are all expressed based on the generator torque. 8.一种电子设备，包括存储器、处理器及存储在存储器上并用于在处理器上运行的计算机程序，其特征在于，所述处理器执行计算机程序时实现如权利要求1-6中任一项所述的控制方法。8. An electronic device comprising a memory, a processor, and a computer program stored in the memory and for running on the processor, characterized in that the processor, when executing the computer program, implements the control method as described in any one of claims 1-6. 9.一种可读计算机存储介质，其上存储有计算机程序，其特征在于，所述计算机程序被处理器执行时实现如权利要求1-6中任一项所述的控制方法。9. A readable computer storage medium having a computer program stored thereon, characterized in that the computer program, when executed by a processor, implements the control method as described in any one of claims 1-6.
CN202310841716.3A 2023-07-10 2023-07-10 Control method and system of wind turbine generator, electronic equipment and storage medium Active CN116816597B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202310841716.3A CN116816597B (en) 2023-07-10 2023-07-10 Control method and system of wind turbine generator, electronic equipment and storage medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202310841716.3A CN116816597B (en) 2023-07-10 2023-07-10 Control method and system of wind turbine generator, electronic equipment and storage medium

Publications (2)

Publication Number Publication Date
CN116816597A CN116816597A (en) 2023-09-29
CN116816597B true CN116816597B (en) 2025-12-19

Family

ID=88121980

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202310841716.3A Active CN116816597B (en) 2023-07-10 2023-07-10 Control method and system of wind turbine generator, electronic equipment and storage medium

Country Status (1)

Country Link
CN (1) CN116816597B (en)

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN118092147B (en) * 2024-04-28 2024-07-30 浙江大学 Industrial Planning Controller Design Method for Offshore Wind Turbines

Citations (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102434400A (en) * 2011-12-08 2012-05-02 浙江大学 Wind driven generator matching wind speed

Family Cites Families (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US8419362B2 (en) * 2004-08-31 2013-04-16 Hamilton Sundstrand Corporation Foldable blades for wind turbines
US7342323B2 (en) * 2005-09-30 2008-03-11 General Electric Company System and method for upwind speed based control of a wind turbine

Patent Citations (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102434400A (en) * 2011-12-08 2012-05-02 浙江大学 Wind driven generator matching wind speed

Also Published As

Publication number Publication date
CN116816597A (en) 2023-09-29

Similar Documents

Publication Publication Date Title
Barlas et al. Model predictive control for wind turbines with distributed active flaps: incorporating inflow signals and actuator constraints
Baisthakur et al. Physics-Informed Neural Network surrogate model for bypassing Blade Element Momentum theory in wind turbine aerodynamic load estimation
CN115167140B (en) Multi-objective stochastic model predictive control strategy method and system for wind turbines
WO2019184171A1 (en) Yaw control method, device and system for wind turbine
CN113794199B (en) Maximum benefit optimization method of wind power energy storage system considering electric power market fluctuation
Nouriani et al. Variable speed wind turbine power control: A comparison between multiple MPPT based methods
CN107829878A (en) Yaw control device and method of wind generating set
CN116816597B (en) Control method and system of wind turbine generator, electronic equipment and storage medium
CN112131753A (en) Method, system, apparatus and readable medium for assessing fatigue life of wind turbines
CN112052604B (en) Method, system, equipment and readable medium for predicting equivalent fatigue load of fan
Coquelet et al. A reinforcement‐learning approach for individual pitch control
CN118092147B (en) Industrial Planning Controller Design Method for Offshore Wind Turbines
Sun et al. Wind power prediction through acoustic data-driven online modeling and active wake control
Dittmer et al. A velocity quasiLPV-MPC algorithm for wind turbine control
CN118462479A (en) Control method, device, equipment, medium and program for offshore wind turbine generator
CN113864114A (en) Method, device and equipment for coordinating and controlling semi-submersible floating type fan and storage medium
CN118997980A (en) Wind energy capturing method and system with efficiency and load at low wind speed
CN116661301B (en) Nonlinear Model Predictive Control Method Based on GRU Equivalent Wind Speed Prediction
CN113027674A (en) Control method and device of wind generating set
CN117829200A (en) Model generation, wind speed and power generation prediction method, system, device and medium
Baisthakur et al. Predicting Wind Turbine Blade Tip Deformation With Long Short‐Term Memory (LSTM) Models
CN113537595A (en) Model training method, wind power prediction method, system, device and medium
CN111461416B (en) Wind speed prediction method, system, electronic equipment and storage medium
CN113468765B (en) Component life determining method, system and readable storage medium
Mirzaei Wind turbine control: Robust model based approach

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
GR01 Patent grant
GR01 Patent grant