基于Smith补偿与神经网络的网络控制系统PD控制

摘要

In order to compensate the time-delay, the plant and network are regarded as one time-varying system, which is predicted by least square estimation. Based on this, a Smith compensator is used to compensate the time delay of the system. The complex controller including a cerebellar model articulation controller of neural networks and a PD controller is applied to the system to weaken the prediction error further, while the control performance can be improved. The simulation results show the method can improve the control performance.%为减小网络时延给系统控制性能带来的负面影响,把传输网络以及被控对象看作是一个时变的被控系统,用Smith补偿器对时延进行补偿,并用遗忘因子递推最小二乘法对Smith补偿器中的参数进行估计,初步减小网络传输时延给系统带来的影响.将小脑模型控制器与PD控制相结合,组成复合控制器,进一步减小由时延预估误差带给系统的控制偏差,优化系统控制效果.最后,对该控制方法进行仿真实验,结果表明该方法能有效改善系统的控制性能.