A bilinear functional link artificial neural network filter for nonlinear active noise control and its stability condition

Since the functional link artificial neural network (FLANN) filter using trigonometric expansions do not exploit cross-terms (products of input samples and /or past output samples with different time shifts), its performance for nonlinear active noise control (ANC) can be considerably degraded, especially in strong nonlinearity environment. In order to overcome this drawback, a novel bilinear FLANN (BFLANN) filter for the nonlinear ANC is proposed in this paper. In addition, a sufficient condition that guarantees the stability of the BFLANN filter is also presented. Simulation results demonstrate that the proposed BFLANN filter based nonlinear ANC can achieve better performance than the FLANN and generalized FLANN (GFLANN) filters based nonlinear ANC in the presence of strong nonlinearity.