基于BP神经网络在线整定参数的预测滤波PID控制

Predictive Filtering PID Control Based on BP Neural Network Parameter on Line Parameter Setting

针对复杂非线性系统采用常规PID控制品质不良的问题,通过引入辅助变量的紧格式动态线性化逼近系统模型,采用BP神经网络实现增量式预测滤波PID控制参数的在线整定算法,基于直接极小化指标函数优化算法进行BP神经网络连接权的在线学习,提出基于BP神经网络在线整定参数的预测滤波PID控制算法。仿真研究表明,因算法具有在线整定PID控制参数和预测控制性能,故提出的智能PID控制具有比常规PID控制更优的性能。

In connection with performance shortcoming of complex nonlinear system employing conventional PID control,using the BP neural network structures identifier of system output variable and adding the incremental constraints set into optimization parameter of object function,Newtons method with overcoming algorithmic-ill was developed,based on incremental predictive filtering PID control,and using it’s on line learning connection weight of BP neural network,linear unequal constraint conditions of PID control parameter satisfying was deduced.In the end,PID control parameter setting was attributed to linear unequal constraint problem,based on BP neural network,an on line optimization parameter predictive filtering PID control algorithm was obtained.Simulation results indicate that the control performace of algorithm is better than that of the conventional PID control due to the algorithm with functions of on line optimization parameter and predictive-control.