基于自适应神经模糊推理系统的噪声消除方法

针对信号处理领域噪声消除的实际问题,提出了一种基于模糊推理的自适应神经网络控制方法.通过自适应神经模糊推理系统(ANFIS)对非线性系统的结构和参数进行辨识与自学习,采用混合学习算法,对前向参数和结论参数分别辨识,在提高精度的同时可加快训练收敛的速度,使控制系统具有良好动静态性和鲁棒性,实现了消除通信系统中噪声的目标,最后对基于ANFIS的噪声消除系统进行了建模和仿真,并与自适应神经网络滤波方法的结果对比,其结果证明了该方法的有效性.

A Noise Cancellation Method Based on Adaptive Neuro-Fuzzy Inference System

An adaptive neuro-fuzzy control method of noise cancellation is proposed in this paper for solving the practical problems in signal processing. The structures and parameters of nonlinear system are identified and learned by ANFIS. This network uses hybrid learning algorithm to identify former parameters and conclusion parameters. The algorithm improves the precision as well as quickens the training speed, so the control systems have good activation character and robustness. The method realizes the objective of canceling noise in the communication systems. Finally, the ANFIS model is built and simulated, then compared with the result of adaptive neural network filtering, and the effectiveness of the proposed method is demonstrated by the obtained result.