基于神经网络优化的迭代学习控制方法的研究及应用

聚合反应的动态特性具有时变性、非线性等特点,应用传统的控制方法已不能满足实际的控制要求,且达不到需要的控制精度,急需提出一种先进的控制方法.本文提出了一种新的基于神经网络优化的迭代学习控制方法,介绍了由迭代学习控制理论设计迭代学习控制器,提出用神经网络对控制器参数进行优化计算,找出最优的学习增益;并将该方法应用于ABS树脂聚合反应过程的温度控制中,仿真结果表明了该方法的有效性,且能在较少的迭代次数下,以最快的收敛速度、较高的跟踪精度逼近期望轨迹.

Research of ILC based on neural network optimization and its application

The dynamic characteristic of polymeric reaction is time-variant,nonlinear and so on.The traditional control algorithms cannot satisfy these requests and requisite tracking precision.A new iterative learning control(ILC) algorithm based on neural network optimization is proposed in this paper.It introduced how to design the iterative learning controller according to ILC theory,and proposed that BP neural network optimizes and calculates the parameters of the iterative learning controller.Meanwhile,the optimal iterative control algorithm is used to the temperature control of ABS resin polymerization reactor.The simulation result indicates that the algorithm is much effective and can approach anticipant contrail with less iterative,double-quick convergence and lofty tracking precision.