改进的GPC在基于以太网的网络控制系统时延中的应用

Improved GPC Applied in Network Control System Based on Ethernet Induced Delay

针对基于以太网的网络控制系统(NCS)具有随机时延的特性,提出了将广义预测控制应用于网络控制系统中。为克服模型失配和系统不确定性的影响,基于BP神经网络建立一个误差的预测模型,用误差预测值对输出预测值进行补偿,构建了带误差补偿的广义预测控制算法。实验仿真验证了带误差补偿的广义预测控制在模型失配时具有更好的控制效果。

With regard to the characteristics of uncertain networked-induced delay based on Ethernet control systems,Generalized Predictive Control is proposed in network control systems.To overcome the influence of modeling mismatch and uncertainty of the system,an error predictive model is built based on BP neural network,an error predictive value is used to compensate output value,which forms a new control algorithm of GPC.GPC with BP error compensate is verified to have better performance in modeling mismatch system.