Features extraction based on wavelet entropy of decomposed signals and flaws identification with support vector machine in ultrasonic inspection

被引：0

作者：

Che, Hongkun ^{[1
]}

Xiang, Zhanqin ^{[1
]}

Cheng, Yaodong ^{[1
]}

机构：

[1] Zhejiang Univ, Inst Modern Mfg Engn, Hangzhou 310027, Peoples R China

来源：

WCICA 2006: SIXTH WORLD CONGRESS ON INTELLIGENT CONTROL AND AUTOMATION, VOLS 1-12, CONFERENCE PROCEEDINGS | 2006年

关键词：

ultrasonic inspection; features extraction; support vector machine; flaws identification;

D O I：

暂无

中图分类号：

TP [自动化技术、计算机技术];

学科分类号：

0812 ;

摘要：

According to the characteristics of ultrasonic echo signals, a new features extraction method was presented base on calculating wavelet entropy of decomposed signals. The advantages and disadvantages of wavelet transform, wavelet packet transform and Gabor Transform in signal decomposing were discussed. The separability of features achieved by three methods above was compared, and the wavelet packet method is proved to be the best. The classification principle of SVM method was introduced. And it was adapted to identify the features achieved by three time-frequency decomposing methods. The features extraction method presented in this paper and the SVM algorithm are proved to be efficient to identify four typical flaws in oil casing pipe.

引用

页码：695 / 695

页数：1