基于神经网络的小波分析及其在突发噪声识别中的应用

Wavelet Analysis Based on Neural Networks for Detecting Out-bursting Noise

神经网络具有良好的自适应性、自组织性及很强的学习功能，小波变换则提供了一种去除噪声的方法，但单纯基于此算法的软件往往缺少对于突发性噪声的自适应能力。本文将此二者有机结合，以神经网络原理和现代数学小波分析为依据，提出了基于神经网络思想的小波分析；以改进原有算法，识别工程技术测量中遇到的突发噪声．

Neural network has good ability of self--adapting, self--organizing and learning. Wavelet transformation provides a way to eliminate noise, but the software simply based on this arithmetic is usually lack of self--adaptability when meeting out--bursting noise. On the basis of moderm wavelet analysis and the principles of neural network, this paper proposes a method to recognize the type and specification of random signal automatically, so that the original arithmetic can be improved to identify the out-bursting noise detected in engineering measurement.