# A New Hybrid Adaptive Self-Loading Filter and GRU-Net for Active Noise Control in a Right-Angle Bending Pipe of an Air Conditioner

## TL;DR

This paper introduces a new hybrid system combining a self-loading filter and a neural network to reduce noise in air conditioner pipes, aiming to improve patient comfort in rehabilitation rooms.

## Contribution

The novel hybrid ANC system combines ASL-FxLMS with a CNN-GRU network for improved real-time noise attenuation in complex harmonic environments.

## Key findings

- The hybrid ANC system effectively attenuates complicated harmonic noise in a right-angle bending pipe.
- The CNN-GRU network with multi-head attention improves performance for harmonic noises with varying frequencies.
- The convex combination structure balances attenuation, robustness, and tracking performance effectively.

## Abstract

The air-conditioner noise in a rehabilitation room can seriously affect the mental state of patients. However, the existing single-layer active noise control (ANC) filters may fail to attenuate the complicated harmonic noise, and the deep recursive ANC method may fail to work in real time. To solve the problem, in a bending-pipe model, a new hybrid adaptive self-loading filtered-x least-mean-square (ASL-FxLMS) and convolutional neural network-gate recurrent unit (CNN-GRU) network is proposed. At first, based on the recursive GRU translation core, an improved CNN-GRU network with multi-head attention layers is proposed. Especially for complicated harmonic noises with more or fewer frequencies than harmonic models, the attenuation performance will be improved. In addition, its structure is optimized to decrease the computing load. In addition, an improved time-delay estimator is applied to improve the real-time ANC performance of CNN-GRU. Meanwhile, an adaptive self-loading FxLMS algorithm has been developed to deal with the uncertain components of complicated harmonic noise. Moreover, to achieve balance attenuation, robustness, and tracking performance, the ASL-FxLMS and CNN-GRU are connected by a convex combination structure. Furthermore, theoretical analysis and simulations are also conducted to show the effectiveness of the proposed method.