Abstract:

As in some situations the control objects are nonlinear or variable,the traditional PID control can not meet the requirements and the PID parameters need to be constantly adjusted by empirical knowledge.
A new neural network adaptive control algorithm modified by PSO was proposed herein.It consisted of the traditional PID,BP neural network and the PSO global optimization algorithm which was used to optimize the initial weights of BP neural network.The optimized BP neural network was then used to adjust PID parameters on-line.Variation operation was introduced to the optimization process and the comprehensive influence on PSO and BP introduced by the choice of the activation function gain and the number of hidden layers was considered.The algorithm can improve the problem more effectively that neural network goes easily into the local minimum value and has slow convergence speed.Simulation results show that the proposed method has greatly improved in accuracy and real-time performance.

Key words: particle swarm optimization(PSO) algorithm, BP neural network, PID control, adaptive control

摘要：

针对一些非线性场合或者控制对象可变的条件下,传统PID控制达不到要求且需要靠经验不断地调整PID参数的情况,提出了一种基于粒子群优化(particle swarm optimization,PSO)的神经网络自适应控制算法。该算法结合传统PID控制、BP神经网络和PSO全局优化算法,用PSO算法优化BP神经网络的初始权值,然后用优化后的BP神经网络在线调整PID参数。优化过程中引入了变异操作,并考虑激活函数增益及隐含层数的选择对PSO算法和BP神经网络的综合影响。该算法克服了神经网络容易陷入局部极小值以及收敛速度慢的缺陷,仿真结果表明,该算法在精确性和实时性上有很大的改进。


关键词: PSO算法, BP神经网络, PID控制, 自适应控制