基于动态神经网络(DNN)的多通道有源消声仿真分析

Simulation of Multi-channel Active Noise Control Based on Dynamic Neural Network

为了克服传统的多通道自适应有源消声FXLMS算法稳定性、泛化能力等方面的不足,尝试把动态神经网络应用于控制器算法和抵消路径的辨识。文中提出了多通道动态神经网络(MDNN)算法,该算法把控制器算法和抵消路径的辨识结合在一起考虑,并都用动态神经网络来实现。通过理论分析和仿真实验证明该算法有比FXLMS优越的性能。

The traditional adaptive active noise control （AANC） models that we know appear to be not quite satisfactory in robustness and extensiveness. We applied dynamic neural network algorithm to the controller and the err path. This paper provides multi - channel dynamic neural network algorithm （MDNN）. From the theoretical analysis and computer simulations, it is shown that MDNN algorithm has advantages over FXLMS algorithm.