Evaluating the Performance of Training Algorithms in Active Noise Control Using MLP Neural Network

Abstract:

Passive methods are costly and ineffective in noise reduction at low frequencies. Active noise control has been suggested because of these problems. Active noise control (ANC) is based on the destructive interference between the noise source waves and a controlled secondary source. In this paper, various training algorithms are compared in active cancellation of modeled sound noise using MLP neural network. Colored noise signals are used as a model of sound noise instead of noise signals from databases. An MLP neural network with different architectures is used in simulation procedure. The effect of number of neurons on the convergence speed of various training algorithms is investigated in this paper. Levenberg-Marquardt (LM), scaled conjugate gradient (SCG), BFGS quasi-Newton (BFG), resilient back-propagation (RP) and variable learning rate back-propagation (GDX) are used for training the network. Simulation results show that Levenberg-Marquardt (LM) and scaled conjugate gradient (SCG) are the fastest training algorithms.

• Periodical: Advanced Materials Research (Volumes 468-471)
• Pages: 1613-1617
• DOI: https://doi.org/10.4028/www.scientific.net/AMR.468-471.1613
• Online since: February 2012
• Authors: Mehrshad Salmasi, Homayoun Mahdavi-Nasab
• Keywords: Active Noise Control (ANC), Modeled Sound Noise, Multi-Layer Perceptron (MLP) Neural Network, Training Algorithms

References

[1] S. M. Kuo, and D. R. Morgan, "Active noise control: a tutorial review," Proc. IEEE, vol. 87, no.6, pp.943-973, June 1999.

DOI: 10.1109/5.763310

[2] S. J. Elliott, and P. A. Nelson, "Active noise control," IEEE Signal Processing Mag., vol. 10, pp.12-35, Oct 1993.

DOI: 10.1109/79.248551

[3] T. Habib, and M. Kepesi, "Open issues of active noise control applications," In Proc. Int. Conf. Radioelektronika, pp.1-4, April 2007.

DOI: 10.1109/radioelek.2007.371462

[4] C. H. Hansen, "Current and future industrial applications of active noise control," Noise Control Engineering Journal, vol. 53, pp.181-196, 2005.

DOI: 10.3397/1.2839255

[5] K. K. Das, and J. K. Satapathy, "New neural network algorithms for nonlinear active noise cancellation with nonlinear secondary path," In Proc. Int. Conf. on Signal Processing, Communication, Computing and Networking Technologies (ICSCCN), pp.286-290, July 2011.

DOI: 10.1109/icsccn.2011.6024561

[6] H. Zhao, and J. Zhang, "Filtered-X Lyapunov algorithm for nonlinear active noise control using second-order Volterra filter", In Proc. IEEE Int. Conf. on Communication Technology, Vancouver, pp.497-500, Nov. 2008.

DOI: 10.1109/icct.2008.4716090

[7] Y. L. Zhou, Q. Z. Zhang, X. D. Li and W. S. Gan, "Analysis and DSP implementation of an ANC system using a filtered–error neural network," Journal of Sound and Vibration, vol. 285, Issue 1-2, pp.1-25, Aug. 2004.

DOI: 10.1016/j.jsv.2004.08.007

[8] R. T. Bambang, R. Yacoub, and R. Hertanza "Recent progress in adaptive nonlinear active noise control," In Proc. Int. Conf. on Electrical Engineering and Informatics, pp.1-8, July 2011.

DOI: 10.1109/iceei.2011.6021848

[9] W. S. Gan, S. Mitra, and S. M. Kuo, "Adaptive feedback active noise control headset: Implementation, evaluation and its extensions," IEEE Transactions on Consumer Electronics, vol. 51, no. 3, pp.975-982, August 2005.

DOI: 10.1109/tce.2005.1510511

[10] C.K. Chen, T.D. Chiueh and J.H. Chen "Active cancellation system of acoustic noise in MR Imaging," IEEE Trans. on Biomedical Engineering, vol. 46, no.2 , pp.186-191, Feb. 1999..

DOI: 10.1109/10.740881

[11] A. Siravara, N. Magotra, and P. Loizou, "A Novel Approach for Single Microphone Active Noise Cancellation," Proc. Int. Symp. Circuits and Systems, Oklahama, vol. 3, pp.469-472, Aug. 2002.

DOI: 10.1109/mwscas.2002.1187075

[12] M. T. Hagan, H. B. Demuth, and M. H. Beale, Neural network design, PWS Publishing Company, USA, 1996.