基于模糊RBF神经网络的PID控制方法及应用

PID Control Method Based on Fuzzy-RBF Neural Network and Its Applicaiton

针对常规PID控制参数固定难于满足时变不确定非线性系统的控制要求,利用模糊控制的良好收敛性和对模糊量的运算优势,以及神经网络自学习、自适应的特性,将常规PID控制与模糊控制、神经网络结合起来,提出一种基于模糊RBF神经网络的PID控制方法,实现了对PID参数的实时在线整定。将算法运用到柴油发电机调速系统的PID参数寻优中,MATLAB仿真试验结果表明,模糊RBF神经网络的PID控制具有更好的动静态特性和抗干扰性能,提高了对非线性时变被控对象的控制效果。

Because the conventional PID control parameters are difficult to meet the control requirements of time-varying uncertain nonlinear systems,this paper uses the good convergence of fuzzy control and the computing advantages of fuzzy quantity,and the self-learning and self-adapting characteristics of neural network to combine the traditional PID control and fuzzy control and neural network and proposes a PID control strategy based on fuzzy-RBF neural network,which is used to achieve real-time online tuning of PID parameters.Simultaneously the algorithm is applied to PID parameter optimization of the diesel generators speed control system.The results of MATLAB simulation show that the fuzzy-RBF neural network PID control has better dynamic and static characteristics and anti-jamming performance than the conventional PID control,so it can be used to improve the control effect of the nonlinear time-varying controlled object.