ADAPTIVE NEURAL NETWORK FOR FEEDBACK ACTIVE NOISE CONTROL SYSTEM

2009 ◽  
Vol 12 (12) ◽  
pp. 86-93
Author(s):  
Tuan Van Huynh ◽  
Phuong Huu Nguyen ◽  
Long Ngoc Nguyen
Keyword(s):  
Noise Control ◽  
Active Noise Control ◽  
Descent Method ◽  
Gradient Descent Method ◽  
Least Mean Square ◽  
Dynamic Learning ◽  
Active Noise ◽  
On Line ◽  
Least Mean Square Algorithm ◽  
Feedback Active Noise Control

This paper presents a neural-based filtered-X least-mean-square algorithm (NFXLMS) active noise control (ANC) system. The saturation of the power amplifier in ANC system is considered. A method for compensating the saturation is proposed. On line dynamic learning algorithms based on the error gradient descent method is carried out. The convergence of the algorithm is proven using a discrete Lyapunov function. Simulation results are provided for illustration.

All-pass filtered x least mean square algorithm for narrowband active noise control

2018 ◽  
Vol 142 ◽  
pp. 1-10 ◽  
Author(s):  
Kuheli Mondal (Das) ◽  
Saurav Das ◽  
Aminudin Bin Hj Abu ◽  
Nozomu Hamada ◽  
Hoong Thiam Toh ◽  
...  
Keyword(s):  
Noise Control ◽  
Active Noise Control ◽  
Mean Square ◽  
Least Mean Square ◽  
Active Noise ◽  
Least Mean Square Algorithm

scholarly journals Multirate Audio-Integrated Feedback Active Noise Control Systems Using Decimated-Band Adaptive Filters for Reducing Narrowband Noises

Sensors ◽  
2020 ◽  
Vol 20 (22) ◽  
pp. 6693
Author(s):  
Antonius Siswanto ◽  
Cheng-Yuan Chang ◽  
Sen M. Kuo
Keyword(s):  
Computational Complexity ◽  
Real Time ◽  
Adaptive Filters ◽  
Noise Control ◽  
Sampling Rate ◽  
Active Noise Control ◽  
Least Mean Square ◽  
Real Time System ◽  
Active Noise ◽  
Feedback Active Noise Control

Audio-integrated feedback active noise control (AFANC) systems deliver wideband audio signals and cancel low frequency narrowband noises simultaneously. The conventional AFANC system uses single-rate processing with fullband adaptive active noise control (ANC) filter for generating anti-noise signal and fullband audio cancelation filter for audio-interference cancelation. The conventional system requires a high sampling rate for audio processing. Thus, the fullband adaptive filters require long filter lengths, resulting in high computational complexity and impracticality in real-time system. This paper proposes a multirate AFANC system using decimated-band adaptive filters (DAFs) to decrease the required filter lengths. The decimated-band adaptive ANC filter is updated by the proposed decimated filtered-X least mean square (FXLMS) algorithm, and the decimated-band audio cancelation filter can be obtained by the proposed on-line and off-line decimated secondary-path modeling algorithms. The computational complexity can be decreased significantly in the proposed AFANC system with good enough noise reduction and fast convergence speed, which were verified in the analysis and computer simulations. The proposed AFANC system was implemented for an active headrest system, and the real-time performances were tested in real-time experiments.

Feedforward active noise control using wavelet frames: simulation and experimental results

2016 ◽  
Vol 23 (4) ◽  
pp. 555-573 ◽  
Author(s):  
Mahdi Akraminia ◽  
Mohammad J Mahjoob ◽  
Amir H Niazi
Keyword(s):  
Noise Control ◽  
Active Noise Control ◽  
Back Propagation ◽  
Experimental Results ◽  
Superior Performance ◽  
Infinite Impulse Response ◽  
Gradient Descent Method ◽  
Least Mean Square ◽  
Wavelet Frames ◽  
Active Noise

Wavelet frames are an appropriate alternative approach for signal approximation especially for noise/vibration signals. This paper presents an active noise control scheme using various wavelet frames with an innovative structure. In this structure, the authors employ a nonlinear static mapping cascaded with an infinite impulse response filter to model the dynamic part of the network. Online dynamic back propagation learning algorithms are applied based on the gradient descent method to adjust the network parameters. Simulations are carried out to compare the performance of filtered-x least mean square and filtered-x back propagation neural network algorithms with the proposed method. Experiments are then designed and conducted to evaluate the developed algorithms. Both simulation and experimental results show the superior performance of the proposed method in terms of a fast convergence rate and noise attenuation while avoiding the curse of dimensionality.

A narrowband active noise control algorithm considering the harmonic distortion of the loudspeaker

2020 ◽  
Vol 64 (1-4) ◽  
pp. 229-235
Author(s):  
Yinshan Cai ◽  
Longlei Dong ◽  
Yanxin Zhou
Keyword(s):  
Noise Reduction ◽  
Control Algorithm ◽  
Detrimental Effect ◽  
Noise Control ◽  
Active Noise Control ◽  
Harmonic Distortion ◽  
Least Mean Square ◽  
Active Noise ◽  
Least Mean Square Algorithm ◽  
Conventional Algorithm

Electrodynamic loudspeakers are the main actuators of the active noise control system, and their harmonic distortion has a detrimental effect on the noise reduction of the system. To improve the performance, this paper proposes a novel narrowband active noise control algorithm with compensating the nonlinearity of the loudspeaker. In the proposed algorithm, the parameters of the controller are obtained by iteration through the filtered-x least mean square algorithm. Meanwhile, they are adjusted in real-time by establishing the online inverse model of the loudspeaker using the Volterra expansion. The simulation experiments for the typical loudspeaker model show that the proposed algorithm can dramatically improve noise reduction compared to the conventional algorithm.

Sign in / Sign up

Export Citation Format

Share Document