RBF网络在履带车辆舱室内有源降噪的实验研究

Active Noise Control in Military Vehicle Cabin Using RBF Neural Network

针对履带车辆舱室内的噪声危害,讨论了有源噪声控制(ANC)问题,提出了一种基于变结构的RBF神经网络的噪声自适应控制方案,给出了滤波-X算法(即FX-RBF).通过实验研究,体现了RBF神经网络作为一种局部全连接网络,训练速度快,克服了BP网络的局部极小点问题.实验结果表明,降噪效果在100～400Hz频段上平均降噪量达到10dB.

Aiming at noise suppression within military vehicle cabins, active noise control is studied, An adaptive noise control project based on RBF networks is proposed, and an algorithm FX-RBF is given. Experimental study showed that as a local and whole conjunction neural network RBF network can be trained very quickly, and can overcome shortcomings of local minimum pole in BP networks. Experimental results showed that the average effect of canceling noise is up to 10 dB in the frequency range from 100～400 Hz.