基于WaveARX神经网络的非线性动态过程故障检测

Fault Detection of Nonlinear Dynamic Process Based on WaveARX Neural Network

研究了利用ＷａｖｅＡＲＸ神经网络构造非线性动态过程的非参数化逼近模型，在分析其逼近偏差的基础上提出了一种非线性次优滤波器设计方法，用于非线性动态过程的故障检测。理论分析和仿真研究证实了其可行性和有效性。

This paper has studied a means to approximate the nonlinear dynamic process based on WaveARX neural network. After a nonparametric approximate model was constructed from a priori experiment, a nonlinear suboptimal filter has been designed to generate the residuals for fault detection based on the analysis of the upper bound approximate error. The theoritical analysis and simulation results have proved the feasibility and effectiveness of the method.