Active Noise Control Method Using Time Domain Neural Networks for Path Decoupling

TL;DR

This paper introduces a hybrid neural network and adaptive filtering approach for decentralized active noise control, effectively reducing crosstalk and modeling errors in real-time acoustic environments.

Contribution

It proposes a novel time-domain neural network method combined with LMS adaptive filters for improved path decoupling in ANC systems, addressing crosstalk and prefiltering issues.

Findings

Outperforms traditional ANC algorithms in simulations

Effectively reduces crosstalk and modeling errors

Operates in real-time with causality guaranteed

Abstract

In decentralized active noise control (ANC) systems, crosstalk between multichannel secondary sources and error microphones significantly degrades control accuracy. Moreover, prefiltering reference signals in filtered-x (Fx) type algorithms may further introduce modeling errors. A theoretical analysis of the Fx-based decentralized control algorithm was performed, which reveals how prefiltering and crosstalk affect the control performance. Then, a hybrid method combining fixed-value neural networks and adaptive strategies was proposed for efficient decentralized ANC. The adaptive filter models the primary path of its own channel online using the least mean square (LMS) algorithm while the neural network (named DecNet) is used for secondary paths inverting and decoupling. The hybrid DecNet-LMS algorithm was implemented in the time domain to guarantee causality and avoid latency. Simulation results with measured acoustic paths show that the proposed method outperforms the existing ANC algorithms using either traditional adaptive filters or neural network-based fixed-coefficient methods under different acoustic conditions.