Active control of nonlinear noise processes using cascaded adaptive nonlinear filter

A novel nonlinear adaptive filter based on a cascade combination of a functional link artificial neural network (FLANN) and a Legendre polynomial has been proposed in this paper for nonlinear active noise control (ANC). The performance of the new controller has been compared with that obtained by a FLANN based ANC system trained using a filtered-s least mean square (FsLMS) algorithm as well as with a Legendre neural network (LeNN) based ANC system trained using a filtered-l LMS (FlLMS) algorithm. The training of the cascaded controller has been achieved using a filtered-sl LMS (FslLMS) algorithm, which simultaneously adapts the weights of both the component adaptive controllers. The new controller has been shown to achieve improved noise mitigation capability in comparison to its constituent filters.

► Develops a novel nonlinear ANC system.
► Based a cascade of a FLANN filter and a Legendre polynomial.
► Simulation study reveals improved performance over FLANN based ANC systems.