Identification for the Active Noise Control System Based on Neural Network

Abstract:

This paper mainly explore application of neural network on self-adaptation system. An framework model of self-adaptation based on theory of artificial network. An active silencing control system is made which adopts a motional feedback loudspeaker as not a noise controlling source but a detecting sensor. The working fundamentals and the characteristics of the motional feedback loudspeaker are analyzed in detail. By analyzing each sound channel, identification of neural network is made. This kind of identifying method can be achieved conveniently, and it wouldn’t bring distribution to working environment. The estimated result of each sound channel matches well with its real sound character, respectively.

• Periodical: Applied Mechanics and Materials (Volumes 239-240)
• Pages: 422-425
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.239-240.422
• Online since: December 2012
• Authors: Bing Wang
• Keywords: Active System, Neural Network (NN), Self-Adaptation

References

[1] Nelson PA, Elliott S J. Active Control of Sound. London: Academic Press, 1992.

[2] Kim H S, Hong JS, Development of an active muffler system for reducing exhaust noise and flow restriction in a heavy vehicle. Noise Control Engineering Journal, 1999,47(2):57-63

DOI: 10.3397/1.599288

[3] Quan-Ke Pan, P.N. Suganthan, Ling Wang. A differential evolution algorithm with self-adapting strategy and control parameters. Computers and operation research,2011,38(1),394-408

DOI: 10.1016/j.cor.2010.06.007

[4] Hans-Georg Beyer. Evolutionary algorithms in noise environments:theoretical issues and guidelines for practice. Computer Methods in applied mechanics and engineering, 186(2-3), 2000, 239-267.

DOI: 10.1016/s0045-7825(99)00386-2

[5] Tsuyoshi Usagawa, Hideo Furukawa. Active control of engine exhaust noise using motional feedback loudspeaker. Second Conference on Recent Advances in active Control of Sound and Vibration, 1993:837-847.