Neuro-Fuzzy Network-Based Nonlinear Hybrid Active Noise Control Systems

Active noise control (ANC) technology has extensive applications in suppressing sound pollution in the real-world environment. In this paper, a new adaptive neuro-fuzzy network (ANFN)-based controller is presented and integrated into hybrid active noise control (HANC) systems to improve the robustness and effectiveness of active noise suppression. Specifically, an adaptive neural network is constructed to minimize the mean square error information with respect to the residual noise. Moreover, a fuzzy logic strategy is proposed to address the manual fine-tuning and nonlinearities encountered in a complex environment. Finally, the stability of the proposed control method is proved by using the Lyapunov theorem. Comparative numerical simulations are given to verify the effectiveness and superiority of the proposed method under different noise signals.