针对具有随机时延的网络控制系统,提出一种自适应预测控制方法.利用Elman神经网络对网络控制系统的随机时延进行在线预测,然后采用一种增加微分作用的改进隐式广义预测控制方法对网络时延进行补偿,实现了随机时延网络控制系统的自适应预测控制.仿真结果表明,该方法对网络随机时延有很好的补偿效果,可明显改善系统输出性能,保证控制的稳定性与快速性.
This paper proposes an adaptive predictive control method for networked control systems with random time-delay. By using the Elman neural network, online prediction of the random time-delay of network is realized. Compensation of time-delay is done using an improved implicit generalized predictive control algorithm with derivative functions. Finally, adaptive predictive control for the networked control system with random time-delay is achieved. Simulation results show that the method has a good compensation effect. It can improve the system output performance and ensure stability and rapidity.