Fault Detection for a Class of Unknown Nonlinear Systems via Associative Memory Networks

Wang, H., Brown, M. and Harris, C.J. (1994) Fault Detection for a Class of Unknown Nonlinear Systems via Associative Memory Networks. Proceedings of the Institution of Mechanical Engineers, Part I: Journal of Systems and Control Engineering, 208 (2), 101--108. (doi:10.1243/PIME_PROC_1994_208_314_02).

Record type: Article

Abstract

This paper presents a novel approach for the detection of faults for a class of nonlinear systems whose parameters are unknown nonlinear functions of both the measurable operating point and the faults of the system. Neural networks are used to estimate the healthy model's parameters, based on the measurable operating points, when no fault occurs within the system (this procedure is called the training of a healthy system). For this purpose, a modified version of recursive least squares algorithm with normalised signals and an output dead zone are employed. After the training of the healthy system, this recursive algorithm remains on-line to estimate the system parameters which, together with trained neural networks, are used to recognise, and differentiate, parameter changes which are caused either by the variation of the operating points or by faults.

This record has no associated files available for download.