时滞系统的模糊神经网络补偿控制

Fuzzy neural network control method with compensation for time-delay system

针对传统的模糊神经网络(FNN)在线控制方法用于控制时滞对象时存在调节时间较长的问题,分析产生这一现象的原因,对传统的模糊神经网络在线控制进行改进,给出一种新的确定补偿量的方法.基于递推最小二乘(RLS)法在线辨识对象模型,通过时滞对象模型预测对象输出的变化,利用补偿方法得到控制量的补偿量.设计二维输入的带补偿的模糊神经网络控制器,进行实验与仿真研究.仿真结果表明,该补偿方法调节时间短,控制精度高,比传统的模糊神经网络的控制效果明显.

The traditional fuzzy neural network（FNN） controller has the disadvantage of long setting time for time-delay system.A new method was proposed to obtain the compensation value aimed at the problem.The parameters for time-delay model were identified online based on the recursive least square（RLS） algorithm.Then the output of the system can be predicted,and the compensation value was obtained.An FNN controller of two-dimension input with compensation was designed.Simulation results show that the method has the characteristic of short setting time,high control precision and obvious improvement compared with the traditional FNN controller.