NEURAL BASED ACTIVE NOISE CONTROLLER

摘要：

A neural based controller with adaptive algorithm is presented in this paper to cancel the nonlinear broadband noise of an active noise control (ANC) system.The ways to avoid the premature saturation of backpropagation algorithm and design the optimal learning rate are also included in the paper to improve the noise reduction performance.The proposed neural filter can be easily implemented and also versatile to the other applications.Simulation results of canceling narrowband and nonlinear broadband noise show that the proposed method can effectively cancel the noise in an ANC system.

关键词： Neural Adaptive Active noise cancellation Aaturation Backpropagation Optimal learning rate

作者: CHENG-YUAN CHANG SHING-TAI PAN

作者单位: Department of Electrical Engineering, Chung Yuan Christian University, Taiwan 320, R.O.C.;Department Department of Computer Science and Information Engineering, National University of Kaohsiung, Taiwan

会议类型: 国际会议

会议名称: 2007 International Conference on Machine Learning and Cybernetics(IEEE第六届机器学习与控制论国际会议)

会议地点: 香港

会议语种:英文

页码: 425-430

在线出版日期: 2007-08-19（万方平台首次上网日期，不代表论文的发表时间）