A genetic based control structure for active control

Abstract

Presents a genetic based control structure for active control. The proposed active control structure has an adaptive system whose controller is an infinite impulse response (IIR) filter and the adaptive mechanism is a genetic algorithm. Adaptive filtering schemes based on a genetic algorithm have been studied, but their application is limited to the system that is able to know desired signals directly. In general active noise and vibration control systems are not able to sense desired signals directly, so they have some difficulties or problems in that the learning sample set is proportional to the population size. The proposed active controller is composed of genetic controllers that can be learned by one sample set per one generation. Also this structure can be properly applied to an active control system. Computer simulation shows that proposed genetic structured IIR active controller gives a good result for feedforward active noise control systems.