Application of reinforcement learning for active noise control

Authors

SEYED AMIR HOSEINI SABZEVARI
MAJID MOAVENIAN

DOI

10.3906/elk-1602-189

Abstract

Active noise control (ANC) systems are used to reduce the sound noise level by generating antinoise signals. M-Estimators are widely employed in ANC systems for updating the adaptive FIR filter taps used as the system controller. Observing the state-of-the-art M-estimators design shows that there is a need for further improvements. In this paper, a feedback ANC based on the reinforcement learning (RL) method is proposed. The sensitivity of the constant parameter in the RL method is checked. The effectiveness of the proposed method is proven by comparing the results with previous feedforward studies through computer simulations.

Keywords

Active noise control, M-estimator, reinforcement learning

First Page

2606

Last Page

2613

Recommended Citation

SABZEVARI, SEYED AMIR HOSEINI and MOAVENIAN, MAJID (2017) "Application of reinforcement learning for active noise control," Turkish Journal of Electrical Engineering and Computer Sciences: Vol. 25: No. 4, Article 5. https://doi.org/10.3906/elk-1602-189
Available at: https://journals.tubitak.gov.tr/elektrik/vol25/iss4/5