Single channel blind source separation for defect identification using Eddy Current Pulsed Thermography

Bin Gao; Libing Bai; W. L. Woo; Gui Yun Tian; Yuhua Cheng

doi:10.1109/FENDT.2013.6635536

Single channel blind source separation for defect identification using Eddy Current Pulsed Thermography

Bin Gao, Libing Bai, W. L. Woo, Gui Yun Tian, Yuhua Cheng

Computer and Information Sciences Department

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

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.

Original language	English
Title of host publication	FENDT 2013 - Proceedings of 2013 Far East Forum on Nondestructive Evaluation/Testing
Subtitle of host publication	New Technology and Application
Publisher	IEEE
Pages	97-101
Number of pages	5
ISBN (Electronic)	9781467360203
ISBN (Print)	9781467360180
DOIs	https://doi.org/10.1109/FENDT.2013.6635536
Publication status	Published - 17 Oct 2013
Event	2013 Far East Forum on Nondestructive Evaluation/Testing: New Technology and Application, FENDT 2013 - Ji'nan, China Duration: 17 Jun 2013 → 20 Jun 2013

Conference

Conference	2013 Far East Forum on Nondestructive Evaluation/Testing: New Technology and Application, FENDT 2013
Country/Territory	China
City	Ji'nan
Period	17/06/13 → 20/06/13

Keywords

Eddy Current Pulsed Thermography
Non-destructive evaluation
Pattern extraction
single channel blind source separation

Access to Document

10.1109/FENDT.2013.6635536

Cite this

@inproceedings{638f8c4c24a54686bc46ebda25aa1be4,

title = "Single channel blind source separation for defect identification using Eddy Current Pulsed Thermography",

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 = "Eddy Current Pulsed Thermography, Non-destructive evaluation, Pattern extraction, single channel blind source separation",

author = "Bin Gao and Libing Bai and Woo, {W. L.} and Tian, {Gui Yun} and Yuhua Cheng",

year = "2013",

month = oct,

day = "17",

doi = "10.1109/FENDT.2013.6635536",

language = "English",

isbn = "9781467360180",

pages = "97--101",

booktitle = "FENDT 2013 - Proceedings of 2013 Far East Forum on Nondestructive Evaluation/Testing",

publisher = "IEEE",

address = "United States",

note = "2013 Far East Forum on Nondestructive Evaluation/Testing: New Technology and Application, FENDT 2013 ; Conference date: 17-06-2013 Through 20-06-2013",

}

Gao, B, Bai, L, Woo, WL, Tian, GY & Cheng, Y 2013, Single channel blind source separation for defect identification using Eddy Current Pulsed Thermography. in FENDT 2013 - Proceedings of 2013 Far East Forum on Nondestructive Evaluation/Testing: New Technology and Application., 6635536, IEEE, pp. 97-101, 2013 Far East Forum on Nondestructive Evaluation/Testing: New Technology and Application, FENDT 2013, Ji'nan, China, 17/06/13. https://doi.org/10.1109/FENDT.2013.6635536

Single channel blind source separation for defect identification using Eddy Current Pulsed Thermography. / Gao, Bin; Bai, Libing; Woo, W. L. et al.
FENDT 2013 - Proceedings of 2013 Far East Forum on Nondestructive Evaluation/Testing: New Technology and Application. IEEE, 2013. p. 97-101 6635536.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Single channel blind source separation for defect identification using Eddy Current Pulsed Thermography

AU - Gao, Bin

AU - Bai, Libing

AU - Woo, W. L.

AU - Tian, Gui Yun

AU - Cheng, Yuhua

PY - 2013/10/17

Y1 - 2013/10/17

N2 - 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.

AB - 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.

KW - Eddy Current Pulsed Thermography

KW - Non-destructive evaluation

KW - Pattern extraction

KW - single channel blind source separation

U2 - 10.1109/FENDT.2013.6635536

DO - 10.1109/FENDT.2013.6635536

M3 - Conference contribution

AN - SCOPUS:84889686588

SN - 9781467360180

SP - 97

EP - 101

BT - FENDT 2013 - Proceedings of 2013 Far East Forum on Nondestructive Evaluation/Testing

PB - IEEE

T2 - 2013 Far East Forum on Nondestructive Evaluation/Testing: New Technology and Application, FENDT 2013

Y2 - 17 June 2013 through 20 June 2013

ER -

Single channel blind source separation for defect identification using Eddy Current Pulsed Thermography

Abstract

Conference

Keywords

Access to Document

Fingerprint

Cite this