摘要
针对水电机组的非线性和结构参数易变化且具有时变和非最小相位的特点,依据神经网络的自学习特性和小波分析的逼近能力,提出了一种基于小波神经网络(WNN)的水电机组自适应逆控制方法.该方法用小波神经网络逼近被控对象的正、逆模型,通过构造控制加权的广义目标函数,推导出一种对非最小相位系统能实现有效控制的小波神经网络自适应逆控制律,理论分析和对水电机组仿真实验均表明,文中提出的控制策略比采用神经网络控制能更好地改善水电机组的动态性能,证明了该方法的有效性.
By considering the nonlinear, time-variable and non-minimum phase character and the easy variance of hydraulic power unit＇s structure and parameters, a new adaptive inverse control method of hydraulic power units based on the learning characteristic of neural networks and the function approximation ability of the wavelet analysis was presented. It approximates the model and its inversion of plant by wavelet neural networks, and then through constructing an aim function of broad sense, a wavelet neural networks adaptive inverse law is put forward that is effective to the nonlinear non-minimum phase system. The theory and simulation to hydraulic generator units demonstrate that the control strategy can more effectively improve the dynamic performance than those based on neural networks. It is shown that the scheme is valid.
出处
《中国计量学院学报》
2007年第2期151-154,共4页
Journal of China Jiliang University
基金
浙江省教育厅科研计划项目(No.20050385)
关键词
自动控制技术
水电机组
小波神经网络
自适应逆控制
automatic control technique
hydraulic power units
wavelet neural networks
adaptive inverse control
