Please use this identifier to cite or link to this item:
|Title:||A novel ANC system using nonlinear error LMS algorithm|
|Keywords:||Active noise control|
Non-linear learning algorithm
|Abstract:||The conventional Filtered-x Least Mean Square (FxLMS) shows poor performance in the presence of non linearities present in the primary and the secondary path. The functional link artificial neural network (FLANN) has been successfully applied to tackle the nonlinearity in the primary and secondary paths. However, all these methods of active noise control use a linear model to obtain an estimate of the non linear secondary path. This paper proposes a FLANN based nonlinear model to obtain an estimate of thenon linear secondary path. In addition, a FLANN based controller is also developed to generate anti noise. A new update rule nonlinear-error least mean square (NELMS) is derived and used for updating the weights of the first FLANN model by utilizing the intermediate signals of the second FLANN model. The simulation results presented exhibit superior performance of the proposed method compared to that of FsLMS-ANC method. � 2015 IEEE.|
|Appears in Collections:||Research Publications|
Files in This Item:
There are no files associated with this item.
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.