Subsurface damage detection of a steel bridge using deep learning and uncooled micro-bolometer. (30th November 2019)

• Record Type: Journal Article
• Authors: Ali, Rahmat; Cha, Young-Jin
• Is Part Of: Construction & building materials. Volume 226(2019)
• Page Start: 376
• Page End: 387
• Publication Date: 2019-11-30
• Subjects: Infrared thermography -- Damage detection -- Deep learning -- Subsurface damage -- Bridge -- Non-destructive evaluation -- Steel structure; Building materials -- Periodicals; 624.18
• DOI: 10.1016/j.conbuildmat.2019.07.293
• Languages: English
• ISSNs: 0950-0618

Abstract

Highlights: A novel deep learning-based subsurface damage detection method was developed. The damage detection method was carefully integrated with passive infrared thermography. Various types of subsurface damage in steel members of real steel bridge were investigated. The deep learning method was modified for this specific research objective. The results of the proposed method were validated by ultrasonic pulse velocity tests. The accuracy of the proposed method were very high (96% accuracy and 97.79% specificity). Abstract: A new deep learning-based method is proposed to detect subsurface damage of steel members in a steel truss bridge using infrared thermography (IRT). To reduce computation costs, the original deep inception neural network (DINN) is modified for transfer learning. The proposed method provides bounding boxes for detecting and localizing subsurface damage such as corrosion and debonding between paint with coating and steel surface. Robustness and accuracy were tested on 200 thermal images (640 × 480 pixels), and 96% accuracy and 97.79% specificity was achieved. The results were validated with ultrasonic pulse velocity (UPV) tests.