局域波神经网络海洋平台AE信号识别研究

为了研究海洋平台结构声发射信号的特征,将近期发展的局域波法和神经网络相结合应用于提取识别中.首先,将海洋平台结构声发射信号进行局域波分解,得到自适应的基本模式分量,然后从各基本模式分量中提取能量特征参数作为神经网络的输入参数来识别海洋平台结构的声发射信号.通过对海洋平台结构模型声发射信号的实验数据分析表明,以局域波法提取各频带能量作为特征参数的神经网络方法可以准确、有效地识别海洋平台结构声发射信号,从而为海洋平台结构声发射信号特征提取识别提供了一种新的方法.

Identification of acoustic emission signals of offshore structures with both local wave method and neural network

This paper presented a new approach for extraction and identification of acoustic emission(AE) signals from offshore structures by using both local wave method and neural network.First the local wave method was used to decompose the acoustic emission signals of offshore structures into a number of intrinsic mode functions(IMFs);then the energy feature parameters extracted from IMFs were employed as the input parameters of the neural network to identify the acoustic emission signals of the offshore structures.Through the analysis on the experimental data of acoustic emission signals of offshore platform,it showed that neural network method in conjunction with local wave method will effectively recognize the offshore structure's AE signals,thus providing a new and effective tool for feature extraction and identification of acoustic emission signal from offshore structures.