Ensemble Joint Sparse Low-Rank Matrix Decomposition for Thermography Diagnosis System

Composite is widely used in the aircraft industry and it essential for manufacturers to monitor its health quality. The most commonly found defects of composite are debonds delamination. Different inner with complex irregular shape difficult diagnosed by using conventional thermal imaging methods. In this article, an ensemble joint sparse low-rank matrix decomposition algorithm proposed applying optical pulse thermography (OPT) diagnosis system. jointly models pattern concatenated feature space. particular, weak information can be separated from strong noise resolution contrast has significantly been improved. Ensemble iterative modeling conducted further enhance as well reducing computational cost. order show robustness efficacy model, experiments detect debond on multiple carbon fiber reinforced polymer composites. A comparative analysis presented general OPT algorithms. Notwithstanding above, model evaluated synthetic data compared other