A Secondary Path-Decoupled Active Noise Control Algorithm Based on Deep Learning

• Published in: IEEE Signal Processing Letters Vol. 29; pp. 234 - 238
• Main Authors: Chen, Daocheng, Cheng, Longbiao, Yao, Dingding, Li, Junfeng, Yan, Yonghong
• Format: Journal Article
• Language: English; Japanese
• Published: New York IEEE 2022; Institute of Electrical and Electronics Engineers (IEEE); The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Active noise control; Actuators; Adaptation models; Adaptive control; adaptive filter; Adaptive filters; Algorithms; Control algorithms; Control theory; Deep learning; Error signals; Machine learning; Mathematical models; Modelling; Noise control; nonlinear secondary path; Nonlinearity; Signal processing; Signal processing algorithms; Time-domain analysis; Training
• ISSN: 1070-9908; 1558-2361
• DOI: 10.1109/LSP.2021.3130023

Active noise control (ANC) systems are widely used to cancel unwanted noise. However, for high-level noise, the residual error signal cannot be fully eliminated because of the nonlinearity of the secondary path, resulting in the diverging of the adaptive filter. In this letter, we propose a secondary path-decoupled ANC (SPD-ANC) algorithm based on deep learning. Specifically, the secondary path decoupled module consisting of two time-domain convolutional recurrent networks, one for modeling the nonlinear secondary path and the other for modeling the reverse process, is employed to calculate the secondary path-decoupled (SPD) error signal. The control signal is then generated by an adaptive filter that is optimized towards minimizing the SPD error signal. Simulation results indicate that the proposed method outperforms the conventional ANC methods under different conditions.