| 超声缺陷回波信号的小波包降噪及特征提取 |
| |
| 引用本文： | 张海燕,周全,夏金东.超声缺陷回波信号的小波包降噪及特征提取[J].仪器仪表学报,2006,27(1):94-98. |
| |
| 作者姓名： | 张海燕 周全 夏金东 |
| |
| 作者单位： | 1. 上海大学通信与信息工程学院,上海,200072
2. 中国科学院声学研究所,北京,100080 |
| |
| 基金项目： | 中国科学院资助项目;上海市教委资助项目 |
| |
| 摘 要： | 根据非稳态超声检测信号的特点，将小波包变换用于缺陷信号的降噪及特征提取问题的研究，并利用类别可分性判据和RBF神经网络分别对特征值提取结果进行评价。引入了平均阈值的概念，在此基础上研究了小波包降噪效果。提出了以选取小波包分解频带的能量作为缺陷信号特征值的方法。实际焊接缺陷的实验结果表明，小波包降噪效果明显；在特征数据得以压缩的同时，分类的可分性较高。
|
| 关 键 词： | 超声检测 小波包变换 降 噪 小波包特征提取 类别可分性判据 神经网络 |
| 修稿时间： | 2004年8月1日 |
Wavelet Packet Denoising and Feature Extraction for Flaw Echo Signal in Ultrasonic Testing |
| |
| Zhang Haiyan,Zhou Quan,Xia Jindong.Wavelet Packet Denoising and Feature Extraction for Flaw Echo Signal in Ultrasonic Testing[J].Chinese Journal of Scientific Instrument,2006,27(1):94-98. |
| |
| Authors: | Zhang Haiyan Zhou Quan Xia Jindong |
| |
| Abstract: | It contributes to the application of wavelet packet transform in denoising and feature extraction of non-stationary ultrasonic flaw signals, and the sort separability criterion and RBF neural network are respectively used for evaluating the validity of feature classification. Mean threshold is introduced on which wavelet packet denoising is studied. The energy of the frequency domain selected based on wavelet packet decomposition is taken as the feature information. The experimental results over welding flaw signals demonstrate the effectiveness of the proposed schemes. |
| |
| Keywords: | Ultrasonic testing Wavelet packet transform Denoising Wavelet packet feature extraction Sort separability criterion Neural network |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
