TY - JOUR
T1 - Ensemble Joint Sparse Low Rank Matrix Decomposition for Thermography Diagnosis System
AU - Ahmedtl, Junaid
AU - Gao, Bin
AU - Woo, Wai Lok
AU - Zhu, Yuyu
N1 - Research funded by National Natural Science Foundation of China (61527803)
PY - 2021/3
Y1 - 2021/3
N2 - Composite is widely used in the aircraft industry and it is essential for manufacturers to monitor its health and quality. The most commonly found defects of composite are debonds and delamination. Different inner defects with complex irregular shape is difficult to be diagnosed by using conventional thermal imaging methods. In this paper, an ensemble joint sparse low rank matrix decomposition (EJSLRMD) algorithm is proposed by applying the optical pulse thermography (OPT) diagnosis system. The proposed algorithm jointly models the low rank and sparse pattern by using concatenated feature space. In particular, the weak defects information can be separated from strong noise and the resolution contrast of the defects has significantly been improved. Ensemble iterative sparse modelling are conducted to further enhance the weak information as well as reducing the computational cost. In order to show the robustness and efficacy of the model, experiments are conducted to detect the inner debond on multiple carbon fiber reinforced polymer (CFRP) composites. A comparative analysis is presented with general OPT algorithms. Not withstand above, the proposed model has been evaluated on synthetic data and compared with other low rank and sparse matrix decomposition algorithms.
AB - Composite is widely used in the aircraft industry and it is essential for manufacturers to monitor its health and quality. The most commonly found defects of composite are debonds and delamination. Different inner defects with complex irregular shape is difficult to be diagnosed by using conventional thermal imaging methods. In this paper, an ensemble joint sparse low rank matrix decomposition (EJSLRMD) algorithm is proposed by applying the optical pulse thermography (OPT) diagnosis system. The proposed algorithm jointly models the low rank and sparse pattern by using concatenated feature space. In particular, the weak defects information can be separated from strong noise and the resolution contrast of the defects has significantly been improved. Ensemble iterative sparse modelling are conducted to further enhance the weak information as well as reducing the computational cost. In order to show the robustness and efficacy of the model, experiments are conducted to detect the inner debond on multiple carbon fiber reinforced polymer (CFRP) composites. A comparative analysis is presented with general OPT algorithms. Not withstand above, the proposed model has been evaluated on synthetic data and compared with other low rank and sparse matrix decomposition algorithms.
KW - CFRP composites
KW - optical thermography
KW - eigen decomposition
KW - low rank sparse decomposition
KW - concatenated matrix factorization
KW - weak signal detection
UR - https://www.mendeley.com/catalogue/368ec601-38af-38de-9406-14def3a96969/
U2 - 10.1109/tie.2020.2975484
DO - 10.1109/tie.2020.2975484
M3 - Article
SN - 0278-0046
VL - 68
SP - 2648
EP - 2658
JO - IEEE Transactions on Industrial Electronics
JF - IEEE Transactions on Industrial Electronics
IS - 3
ER -