风力发电机转速控制系统的建模与仿真

Modeling and simulation of wind turbine speed control system

针对风力发电机非线性、随机性、扰动大等特点,设计基于带动量项的粒子群优化的支持向量机的风力发电机转速控制建模的新方法。利用支持向量机对小样本、高维度、非线性特性的映射能力,将风电系统的采样数据映射到高维的特征空间进行建模。支持向量机惩罚因子C和核参数σ的选择对建模效果影响较大,经验试凑的方法难以获得较好的参数,引入粒子群算法进行参数寻优。为了克服传统粒子群算法易陷入局部最优且收敛速度慢的缺陷,提出带动量项的改进粒子群算法寻优。以采集的风速、风力发电机转矩、桨距角作为输入信号,发电机转速数据作为输出信号,在Matlab环境中进行建模。实验结果表明,与传统算法相比,采用该方法的模型在准确性和收敛速度方面得到较大改善。

A new wind turbine speed control modeling method based on support vector machine optimized by particle swarm algorithm with momentum item was designed for the characteristics of nonlinearity,randomness and large disturbance of wind turbine.Since the support vector machine has the mapping ability of small-sample,high-dimensional and nonlinear characteristics,the sampling data of the wind power system is mapped to the high.dimensional feature space for modeling.The selection of penalty factor C and kernel parameterσof support vector machine has a great influence on the modeling effect,and the optimal parameter is difficult to be obtained by the trial and error method,so the particle swarm optimization algorithm is introduced for parameter optimization.In order to overcome that the traditional particle swarm optimization algorithm is easy to fall into local optimum and has slow convergence speed,an improved particle swarm optimization algorithm with momentum term is proposed.The collected wind speed,wind turbine torque and pitch angle of wind turbine are taken as input signals,and the generator speed data is taken as output signal.The system is modeled in Matlab.The experimental results show that the model adopting the proposed method has a great improvement in accuracy and convergence speed than the traditional algorithm.