Abstract: Aiming at the issues of random delay and delay uncertainty in both the before channel and feedback channel for networked control system, the root causes of random delay influence closed-loop control system by case are analyzed, and the predictive control method based on neural network to solve the feasibility of existence network random delay in control system closed-loop control is provided. Simulation results show that the method can reflect and predict the delay characteristics between the network paths which are presented by measurement data, and can effectively substitute for the actual network in the design of closed-loop control system based on Internet to research. The method is fast and accurate, can be used for online learning network model and forecast the network delay value, provides a new way to remote closed-loop control based on Internet.

Key words: network time-delay, model predictive control, networked control system

摘要： 针对网络控制系统中前向通道和反馈通道同时存在随机延迟及延时不确定的问题，通过实例分析了随机延时对闭环控制系统影响的根源，提出了通过基于神经网络的预测控制方法解决存在网络随机延时的控制系统闭环控制的可行性。仿真结果表明该方法能够反映并预测该测量数据所代表的网络路径之间的时延特性，并能在基于Internet的闭环控制系统的设计中有效地替代实际网络进行研究；而所用的方法具有快速、准确的特点，能用于在线学习网络模型并对网络的时延值进行预测，为基于Internet的远程闭环控制提供了新的思路。

关键词: 网络时延, 模型预测控制, 网络控制系统