Open Access

Abstract

This paper presents a neural-based filtered-X least-mean-square algorithm (NFXLMS) active noise control (ANC) system. The saturation of the power amplifier in ANC system is considered. A method for compensating the saturation is proposed. On line dynamic learning algorithms based on the error gradient descent method is carried out. The convergence of the algorithm is proven using a discrete Lyapunov function. Simulation results are provided for illustration.