Crack detection and recognition using an eddy current differential probe

被引:54
作者
Chady, T
Enokizono, M
Sikora, R
机构
[1] Oita Univ, Fac Engn, Oita 8701192, Japan
[2] Tech Univ Szczecin, Dept Theoret Electrotech, PL-70310 Szczecin, Poland
关键词
eddy current testing; neural network applications; flaw reconstruction;
D O I
10.1109/20.767393
中图分类号
TM [电工技术]; TN [电子技术、通信技术];
学科分类号
0808 ; 0809 ;
摘要
This paper proposes a new eddy current differential sensor and a system for multi-frequency testing of conducting plates. Precise crack imaging was achieved by the use of spectrograms obtained from an eddy-current probe multifrequency response and application of a neural network. Results of experiments with test specimens made of SUS304 showing very good sensitivity and spatial resolution are presented. The possibility of detection of an opposite side 20% crack was also confirmed.
引用
收藏
页码:1849 / 1852
页数:4
相关论文
共 4 条
  • [1] [Anonymous], P IEEE INT C NEUR NE
  • [2] Hertz J., 1991, Introduction to the Theory of Neural Computation
  • [3] KAY S, 1975, MODERN SPECTRAL ESTI
  • [4] *U STUTTG, 1995, SNNS SUTTG NEUR NETW