Sensor Optimisation using an Ant Colony Metaphor
G. Christian Overton, Keith Worden · Strain · 2004
Abstract: This paper describes an approach to impact detection and location using neural networks and an ant colony metaphor. 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 impacts on a composite panel and the ant colony metaphor is used to determine an optimal (or near optimal) sensor distribution. The results are compared with those from a previous study which used a genetic algorithm for the optimisation phase.