摘要
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.
出处
《华东理工大学学报（自然科学版）》
CAS
CSCD
北大核心
1998年第3期347-353,共7页
Journal of East China University of Science and Technology
基金
国家自然科学基金
关键词
小波变换
神经网络
故障检测
动态过程
控制系统
wavelet transform
neural network
suboptimal filter
fault dection
dynamic process
