Wavelet Integrated Alternating Sparse Dictionary Matrix Decomposition in Thermal Imaging CFRP Defect Detection

Ahmed, Junaid, Gao, Bin and Woo, Wai Lok (2019) Wavelet Integrated Alternating Sparse Dictionary Matrix Decomposition in Thermal Imaging CFRP Defect Detection. IEEE Transactions on Industrial Informatics, 15 (7). pp. 4033-4043. ISSN 1551-3203

Full text not available from this repository. (Request a copy)

Abstract

With the increasing importance of using carbon fiber reinforced polymer (CFRP) composite in the aircraft industry, it becomes ever more critical to monitor the quality and health of CFRP during the manufacturing process as well as the in-service procedure. Most common types of defects in the CFRP are debonds and delaminations. It is difficult to detect the inner defects on a complex shaped specimen by using conventional Nondestructive Testing (NDT) methods. In this paper, an unsupervised machine learning method based on wavelet integrated alternating sparse dictionary matrix decomposition (WIASDMD) is proposed to extract the weaker and deeper defects information for CFRP by using the optical pulse thermography (OPT) system. We propose to model the low rank and sparse decomposition jointly in an alternating manner. By incorporating the low rank information into the sparse matrix and vice versa, the weaker defects will be more efficiently extracted from noise and background. In addition, the integrated of wavelet analysis with dictionary factorization enables an efficient time-frequency mining of information and significantly removes the high frequency noise as well as boosts the speed of computations. To investigate the efficacy and robustness of the proposed method, experimental studies have been carried out for inner debond defects on both regular and irregular shaped CFRP specimens. A comparative analysis has also been undertaken to study the proposed method against the general OPT nondestructive testing (OPTNDT) methods. The Matlab demo code can be linked: http://faculty.uestc.edu.cn/gaobin/zh_CN/lwcg/153392/list/index.htm

Item Type:	Article
Uncontrolled Keywords:	CFRP composites, Data mining, Heating systems, Matrix decomposition, Optical pulses, Optimized production technology, Sparse matrices, Wavelet transforms, low rank decomposition, optical thermography, sparse matrix factorization, wavelet analysis, weak signal detection
Subjects:	G400 Computer Science J500 Materials Technology not otherwise specified
Department:	Faculties > Engineering and Environment > Computer and Information Sciences
Depositing User:	Paul Burns
Date Deposited:	02 Apr 2019 10:59
Last Modified:	10 Oct 2019 17:05
URI:	http://nrl.northumbria.ac.uk/id/eprint/38686

Downloads