Open Access Open Access  Restricted Access Subscription or Fee Access

System Identification using Combined FIR and Functional Link Neural Networks: Application to ANC Secondary Path

R. Y. Redi, Riyanto T. Bambang


The finite impulse response (FIR) filter with least mean square (LMS) algorithm has widely used in linear active noise control (ANC) system because it is relatively simple to design and implement. For nonlinear case, such as when the control signals excite the secondary speaker saturation, their performances are known to be deteriorating, we must modify linear structure and develop proper algorithm for both the control and model structures employed in ANC. Recently, adaptive combination of finite impulse response filter and functional link artificial neural networks (CFFLANN) structure was proposed by Zhao and Zhang (2009) to compensate linear and nonlinear distortions in nonlinear communication channel. This paper presents a real-time implementation of CFFLANN structure to model the secondary path of nonlinear active noise control system by using DSP TMS320C6713. To examine the performance of this structure, we apply the various types of functional expansion to model linear and nonlinear distortions in the nonlinear secondary path by comparing it with LMS based FIR filter. Identification results show that the CFFLANN can model the nonlinear secondary path with satisfied modeling error.


Identification, CFFLANN, Secondary path nonlinearity, ANC.

Full Text:



  • There are currently no refbacks.

Disclaimer/Regarding indexing issue:

We have provided the online access of all issues and papers to the indexing agencies (as given on journal web site). It’s depend on indexing agencies when, how and what manner they can index or not. Hence, we like to inform that on the basis of earlier indexing, we can’t predict the today or future indexing policy of third party (i.e. indexing agencies) as they have right to discontinue any journal at any time without prior information to the journal. So, please neither sends any question nor expects any answer from us on the behalf of third party i.e. indexing agencies.Hence, we will not issue any certificate or letter for indexing issue. Our role is just to provide the online access to them. So we do properly this and one can visit indexing agencies website to get the authentic information.