Using very large arrays of intelligent sensors

Abstract

Recently several authors have turned their attention to the design problems of very large arrays of intelligent sensors, such as would be suitable for inclusion as an integral part of a 'smart structure'. Such systems have architectural and data throughput advantages, but to be used effectively need to be designed so as to be 'controllerless' and 'decentralised'. This paper looks at the system level issues of how neural network based analytical and diagnostic capabilities may be integrated into such an array of sensors. Event based models of the interactions of the system are presented, using the /spl pi/-calculus. The neural network diagnostics are modeled at a systems interface level.