Adaptive ANC System with Nonlinear Secondary Path Based on Recurrent Neural Network

In this paper, the active noise control system based on an adaptively trained recurrent neural network (RNN) is proposed. In our research, we assume that secondary path is modelled by nonlinear transfer function, i.e. linear filter followed by a saturation nonlinearity. To compare commonly used filtered-X LMS (FXLMS) and filtered-X RLS (FXRLS) algorithms with the proposed RNN-based scheme, computer simulations are carried out. Results of experiments have shown that the adaptively trained recurrent neural network provides a significant improvement in an operation of the adaptive ANC systems in the steady-state in comparison with classically used FXLMS and FXRLS algorithms.