摘要
针对典型的工业过程控制对象,提出了一种基于神经网络的自适应内模PID(IMC-PID)控制方法。传统的IMC-PID控制器只有一个可调参数,可方便的调整闭环系统的响应速度和鲁棒性。但当控制对象参数发生变化或系统中存在不确定性因素时,则需要重新整定IMC-PID控制器参数。所提出的方法通过神经网络的在线学习功能实时地调整IMC-PID控制器参数,以增强系统的鲁棒性和控制性能,其中BP算法用于调整神经网络的权值,以保证控制系统的误差最小。仿真结果表明了它的有效性。
An adaptive IMC - PID control method based on neural networks is proposed for the typical industrial process. The conventional IMC - PID provides convenient tuning parameter to adjust the response speed and robustness of the closed-loop system because it has only one tuning parameter. But when the characteristics variation and uncertainty factors are included in the control system, we must retune the control parameter of IMC - PID. This method is used to adjust the parameter of IMC - PID controller through the online learning function of neural network, so as to enhance the robust and control performance of the system. The weights of the NN are adjusted by the Back Propagation method so that the control errorcan be minimized. Simulation results show the effectiveness of the scheme.
基金
山西省自然科学基金项目资助(2007011049)
