DocumentCode :
1609812
Title :
Single channel blind source separation for defect identification using Eddy Current Pulsed Thermography
Author :
Bin Gao ; Libing Bai ; Woo, Wai L. ; Gui Yun Tian ; Yuhua Cheng
Author_Institution :
Sch. of Autom., Univ. of Electron. Sci. & Technol. of China, Chengdu, China
fYear :
2013
Firstpage :
97
Lastpage :
101
Abstract :
A single channel blind source separation is proposed to process the Eddy Current Pulsed Thermography (ECPT) image sequences. The proposed method enables the detection automatically extract valuable spatial and time patterns according to the whole transient response behavior without any training knowledge. In addition, it has the potential to automatically identify defect patterns and quantify the defects. In this study, both mathematical and physical models are discussed and linked. The basis of the selection of separated spatial and time patterns is also presented. In addition, a natural crack is applied to validate the proposed method.
Keywords :
blind source separation; computerised instrumentation; crack detection; eddy currents; electric sensing devices; image sequences; infrared imaging; mathematical analysis; ECPT; crack; defect identification; eddy current pulsed thermography image sequence; mathematical model; physical model; single channel blind source separation; spatial pattern extraction; time pattern extraction; transient response behavior; Blind source separation; Coils; Eddy currents; Fatigue; Heating; Principal component analysis; Vectors; Eddy Current Pulsed Thermography; Non-destructive evaluation; Pattern extraction; single channel blind source separation;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Nondestructive Evaluation/Testing: New Technology & Application (FENDT), 2013 Far East Forum on
Conference_Location :
Jinan
Print_ISBN :
978-1-4673-6018-0
Type :
conf
DOI :
10.1109/FENDT.2013.6635536
Filename :
6635536
Link To Document :
بازگشت