摘要
在风力发电变桨距优化控制问题的研究中,针对具有不确定性的非线性风电机组,设计了基于径向基函数神经网络(RBFNN)的风电机组变桨距反推滑模控制器。首先应用精确反馈线性化理论将原非线性系统模型进行全局线性化处理,再应用RBFNN对不确定项进行逼近,结合滑模控制和反推法,设计反推滑模控制器(BSMC),保证了高风速下风机的稳定性,抑制了不确定项对系统的影响,避免了传统反推法存在的计算复杂问题。通过与传统滑模控制器(SMC)进行仿真对比,结果表明,RBFNN-BSMC能够很好地稳定风电机组的输出功率,具有较强的鲁棒性。
In this paper, a variable pitch backstepping sliding mode controller of wind turbine based on radial basic function neural network was proposed for wind turbines with great uncertainties. The scheme conducted the original nonlinear system model of the global linearization first Then, on the basis of radial basic function neural network, the uncertainties were approached. And sliding mode control was combined with backstepping method to design backstepping sliding mode controller. The designed controller guaranteeds the stability of wind turbine under high wind speed and restraines the effects of uncertainties on the system, and the explosion of complexity in traditional backstepping design is avoided. Comparing with traditional sliding mode controller, the results of the simulation indicate that the designed controller can stabilize the output power of wind turbines and behave robustly.
出处
《计算机仿真》
CSCD
北大核心
2015年第1期122-126,共5页
Computer Simulation
基金
贵州电网公司重大科技项目(12H0594)
四川省科技支撑项目(2011GZ0036)
关键词
风电机组
变桨距控制
精确反馈线性化
径向基函数神经网络
滑模控制
反推法
Wind turbine generator
Variable pitch control
Exact feedback linearization
Radial basic function neural network
Sliding-mode control
Backstepping method
