基于余弦基神经网络的FIR滤波器设计

Design of FIR Filter Based on Cosine-basis Neural Network

提出了一种基于余弦基神经网络F IR滤波器的设计方法。根据线性相位F IR滤波器的幅频特性是有限项的傅里叶级数,构造了一个三层余弦基神经网络模型,并给出了最优隐层神经元的个数。经模拟仿真,滤波器性能非常理想,具有同时输出低通、高通、带通、带阻各种功能,通带、阻带无过冲无波动,边界频率可以精确控制。

A method of design of FIR filter based on neural network is proposed in this paper. Amplitude-frequency FIR filter with linear phase is characteristic of finite fourier progression. So a neural mode of cosine basis with three layers is set up, and optional net nodes are discussed. Simulation result shows that better result can be achieved to all kinds of digital filter. There is no fluctuating, frequency value is easy to control precisely.