Efficient filter structures for active noise, LMS controllers

Abstract

Two new controller configurations for broad band adaptive noise control have been examined. In the proposed structures, a certain amount of the properties of the acoustic system are modelled by a fixed part of the controller which is therefore less flexible than a completely adaptive control system. The benefit with these configurations are that the adaptive part can be small and can therefore obtain a higher efficiency in terms of attenuation per adaptive weight. It is assumed that the acoustic impulse response has a short term mean value that is stationary or almost stationary and that the variations are small around the mean value. The controller configurations presented here are general and the actual filter implementation may consist of finite impulse response (FIR) filters or infinite impulse response (IIR) filters as dictated by the properties of the acoustic system. The configurations discussed in this paper are especially useful in applications where long impulse responses are needed in order to obtain a high attenuation over a large bandwidth. Instead of using a completely adaptive IIR filter, the combination of a fixed part with a sufficiently long impulse response and a small adaptive part allows us to maintain the transversal controller structure and a very simple adaptive algorithm, such as the LMS algorithm, can be used to control the adaptive weights. Two realisations have been examined and compared with the ordinary transversal filter configuration in a computer simulation study. The results show that it is possible to obtain a significant reduction in the controller complexity if prior knowledge about the acoustic system is built into the controller.