Optimal sensor placement for fault detection

This paper describes an approach to fault detection and classification using neural networks and methods of combinatorial optimisation. Given the existence of an effective fault detection procedure, the problem arises as to how the sensors should be placed for optimal efficiency of the detector. In this paper, a neural network is used to locate and classify faults and a number of different methods are applied to determine an optimal (or near optimal) sensor distribution. A survey of recent work on sensor placement is given. (C) 2001 Elsevier Science Ltd. All rights reserved.