存在时延、丢包和量化误差的网络化控制系统故障检测方法

Fault Detection of Networked Control Systems with Time-Varying Delay,Packet Dropout and Quantization Error

研究了同时存在未知长时延、丢包和量化误差条件下的网络化控制系统(Networked control systems,NC-Ss)的故障检测问题。通过将网络诱导时延的影响转化为polytopic不确定性,并将丢包和量化误差的影响描述成模型的未知输入,把最优残差发生器的设计等效为一个模型匹配问题,并采用基于参考模型的方法求得最优解。实验结果显示,当存在丢包、时延和量化误差时,本文的方法可以快速准确地检测到故障。

The problem of fault detection is studied for a class of networked control systems （NCSs） with unknown long time-varying delay, quantization error and packet dropout. The design of the optimal residual generator is formulated as a model match problem by transforming the network-induced delay into time-varying polytopic uncertainty and describing quantization error and packet dropout as unknown model inputs respectively, and solved by utilizing the so-called reference-model based method. Experimental results show that the proposed method can quickly and exactly detect the fault when these network factors exist.