基才PSO—BP神经网络的PID控制器参数优化方法

针对传统PID控制系统参数整定过程存在的在线整定困难和控制品质不理想等问题，结合BP神经网络自学习和自适应能力强等特点，提出采用BP神经网络优化PID控制器参数。其次，为了加快BP神经网络学习收敛速度，防止其陷入局部极小点，提出采用粒子群优化算法来优化BP神经网络的连接权值矩阵。最后，给出了PSO—BP算法整定优化PID控制器参数的详细步骤和流程图。并通过一个PID控制系统的仿真实例来验证本文所提算法的有效性。仿真结果证明了本文所提方法在控制品质方面优于其它三种常规整定方法。

PID controller parameters optimization based on PSO-BP neural networks

Due to the strong self-learning and self-adaptive ability of BP neural networks,it can be used to solve the problems that existing in traditional PID controller parameters tuning methods.In order to accelerate the convergence speed of BP neural network and prevent it from falling into local minimum point,the particle swarm optimization algorithm is proposed to optimize the connection weight matrix of BP neural networks.At last,detailed steps and flow chart of the proposed method are given and the simulation results demonstrated that the control quality of the proposed method is superior to the conventional methods.