Active Noise Control Using a Functional Link Artificial Neural Network with the Simultaneous Perturbation Learning Rule

In practical active noise control (ANC) systems, the primary path and the secondary path may be nonlinear and time-varying. It has been reported that the linear techniques used to control such ANC systems exhibit degradation in performance. In addition, the actuators of an ANC system very often have...

Full description

Saved in:
Bibliographic Details
Main Authors: Ya-li Zhou, Qi-zhi Zhang, Tao Zhang, Xiao-dong Li, Woon-seng Gan
Format: Article
Language:English
Published: Wiley 2009-01-01
Series:Shock and Vibration
Online Access:http://dx.doi.org/10.3233/SAV-2009-0472
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849400405691203584
author Ya-li Zhou
Qi-zhi Zhang
Tao Zhang
Xiao-dong Li
Woon-seng Gan
author_facet Ya-li Zhou
Qi-zhi Zhang
Tao Zhang
Xiao-dong Li
Woon-seng Gan
author_sort Ya-li Zhou
collection DOAJ
description In practical active noise control (ANC) systems, the primary path and the secondary path may be nonlinear and time-varying. It has been reported that the linear techniques used to control such ANC systems exhibit degradation in performance. In addition, the actuators of an ANC system very often have nonminimum-phase response. A linear controller under such situations yields poor performance. A novel functional link artificial neural network (FLANN)-based simultaneous perturbation stochastic approximation (SPSA) algorithm, which functions as a nonlinear mode-free (MF) controller, is proposed in this paper. Computer simulations have been carried out to demonstrate that the proposed algorithm outperforms the standard filtered-x least mean square (FXLMS) algorithm, and performs better than the recently proposed filtered-s least mean square (FSLMS) algorithm when the secondary path is time-varying. This observation implies that the SPSA-based MF controller can eliminate the need of the modeling of the secondary path for the ANC system.
format Article
id doaj-art-87ca055ae79c427fbc23d034b3b54687
institution Kabale University
issn 1070-9622
1875-9203
language English
publishDate 2009-01-01
publisher Wiley
record_format Article
series Shock and Vibration
spelling doaj-art-87ca055ae79c427fbc23d034b3b546872025-08-20T03:38:05ZengWileyShock and Vibration1070-96221875-92032009-01-0116332533410.3233/SAV-2009-0472Active Noise Control Using a Functional Link Artificial Neural Network with the Simultaneous Perturbation Learning RuleYa-li Zhou0Qi-zhi Zhang1Tao Zhang2Xiao-dong Li3Woon-seng Gan4Department of Computer Science and Automation, Beijing Institute of Machinery, P.O. Box 2865, Beijing, 100192, ChinaDepartment of Computer Science and Automation, Beijing Institute of Machinery, P.O. Box 2865, Beijing, 100192, ChinaDepartment of Computer Science and Automation, Beijing Institute of Machinery, P.O. Box 2865, Beijing, 100192, ChinaInstitute of Acoustics, Academia Sinica, ChinaSchool of EEE, Nanyang Technological University, SingaporeIn practical active noise control (ANC) systems, the primary path and the secondary path may be nonlinear and time-varying. It has been reported that the linear techniques used to control such ANC systems exhibit degradation in performance. In addition, the actuators of an ANC system very often have nonminimum-phase response. A linear controller under such situations yields poor performance. A novel functional link artificial neural network (FLANN)-based simultaneous perturbation stochastic approximation (SPSA) algorithm, which functions as a nonlinear mode-free (MF) controller, is proposed in this paper. Computer simulations have been carried out to demonstrate that the proposed algorithm outperforms the standard filtered-x least mean square (FXLMS) algorithm, and performs better than the recently proposed filtered-s least mean square (FSLMS) algorithm when the secondary path is time-varying. This observation implies that the SPSA-based MF controller can eliminate the need of the modeling of the secondary path for the ANC system.http://dx.doi.org/10.3233/SAV-2009-0472
spellingShingle Ya-li Zhou
Qi-zhi Zhang
Tao Zhang
Xiao-dong Li
Woon-seng Gan
Active Noise Control Using a Functional Link Artificial Neural Network with the Simultaneous Perturbation Learning Rule
Shock and Vibration
title Active Noise Control Using a Functional Link Artificial Neural Network with the Simultaneous Perturbation Learning Rule
title_full Active Noise Control Using a Functional Link Artificial Neural Network with the Simultaneous Perturbation Learning Rule
title_fullStr Active Noise Control Using a Functional Link Artificial Neural Network with the Simultaneous Perturbation Learning Rule
title_full_unstemmed Active Noise Control Using a Functional Link Artificial Neural Network with the Simultaneous Perturbation Learning Rule
title_short Active Noise Control Using a Functional Link Artificial Neural Network with the Simultaneous Perturbation Learning Rule
title_sort active noise control using a functional link artificial neural network with the simultaneous perturbation learning rule
url http://dx.doi.org/10.3233/SAV-2009-0472
work_keys_str_mv AT yalizhou activenoisecontrolusingafunctionallinkartificialneuralnetworkwiththesimultaneousperturbationlearningrule
AT qizhizhang activenoisecontrolusingafunctionallinkartificialneuralnetworkwiththesimultaneousperturbationlearningrule
AT taozhang activenoisecontrolusingafunctionallinkartificialneuralnetworkwiththesimultaneousperturbationlearningrule
AT xiaodongli activenoisecontrolusingafunctionallinkartificialneuralnetworkwiththesimultaneousperturbationlearningrule
AT woonsenggan activenoisecontrolusingafunctionallinkartificialneuralnetworkwiththesimultaneousperturbationlearningrule