Subsurface damage detection of a steel bridge using deep learning and uncooled micro-bolometer

被引:104
|
作者
Ali, Rahmat [1 ]
Cha, Young-Jin [1 ]
机构
[1] Univ Manitoba, Dept Civil Engn, Winnipeg, MB, Canada
关键词
Infrared thermography; Damage detection; Deep learning; Subsurface damage; Bridge; Non-destructive evaluation; Steel structure; INFRARED THERMOGRAPHY; CRACKS;
D O I
10.1016/j.conbuildmat.2019.07.293
中图分类号
TU [建筑科学];
学科分类号
0813 ;
摘要
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 x 480 pixels), and 96% accuracy and 97.79% specificity was achieved. The results were validated with ultrasonic pulse velocity (UPV) tests. (C) 2019 Elsevier Ltd. All rights reserved.
引用
收藏
页码:376 / 387
页数:12
相关论文
共 50 条
  • [41] Advanced crack detection and segmentation on bridge decks using deep learning
    Tran, Thai Son
    Nguyen, Son Dong
    Lee, Hyun Jong
    Tran, Van Phuc
    CONSTRUCTION AND BUILDING MATERIALS, 2023, 400
  • [42] Deep learning for plasma tomography using the bolometer system at JET
    Matos, Francisco A.
    Ferreira, Diogo R.
    Carvalho, Pedro J.
    Abhangi, M.
    Abreu, P.
    Aftanas, M.
    Afzal, M.
    Aggarwal, K. M.
    Aho-Mantila, L.
    Ahonen, E.
    Aints, M.
    Airila, M.
    Albanese, R.
    Alegre, D.
    Alessi, E.
    Aleynikov, P.
    Alfier, A.
    Alkseev, A.
    Allan, P.
    Almaviva, S.
    Alonso, A.
    Alper, B.
    Alsworth, I.
    Alves, D.
    Ambrosino, G.
    Ambrosino, R.
    Amosov, V.
    Andersson, F.
    Andersson Sunden, E.
    Angelone, M.
    Anghel, A.
    Anghel, M.
    Angioni, C.
    Appel, L.
    Apruzzese, G.
    Arena, P.
    Ariola, M.
    Arnichand, H.
    Arnoux, G.
    Arshad, S.
    Ash, A.
    Asp, E.
    Asunta, O.
    Atanasiu, C. V.
    Austin, Y.
    Avotina, L.
    Axton, M. D.
    Ayres, C.
    Bachmann, C.
    Baciero, A.
    FUSION ENGINEERING AND DESIGN, 2017, 114 : 18 - 25
  • [43] Steel railway bridge fatigue damage detection using numerical models and machine learning: Mitigating influence of modeling uncertainty
    Rageh, Ahmed
    Azam, Saeed Eftekhar
    Linzell, Daniel G.
    INTERNATIONAL JOURNAL OF FATIGUE, 2020, 134
  • [44] Indirect Identification and Analysis of Bridge Damage Using Vehicle-Bridge Coupled Vibration and Deep Learning
    Chen, Daihai
    Cui, Hua
    Li, Zheng
    Xu, Shizhan
    Zhang, Yu
    JOURNAL OF PERFORMANCE OF CONSTRUCTED FACILITIES, 2024, 38 (04)
  • [45] Damage detection of steel bridge by numerical simulations and measurements
    Svendsen, B. T.
    Froseth, G. T.
    Ronnquist, A.
    LIFE-CYCLE ANALYSIS AND ASSESSMENT IN CIVIL ENGINEERING: TOWARDS AN INTEGRATED VISION, 2019, : 237 - 243
  • [46] Fault Detection in Steel Surfaces Using Deep Learning Approaches
    Joshi, Shubham
    Mukte, Aditi
    Jaiswal, Snehal
    Khurana, Khushboo
    INTERNATIONAL JOURNAL OF NEXT-GENERATION COMPUTING, 2023, 14 (01): : 30 - 36
  • [47] A Shutter-less Micro-bolometer Thermal Imaging System using Multiple Digital Correlated Double Sampling for Mobile Applications
    Park, Seunghyun
    Cho, Tei
    Kim, Minsik
    Park, Hyungchul
    Lee, Kwyro
    2017 SYMPOSIUM ON VLSI CIRCUITS, 2017, : C154 - C155
  • [48] Detection of Deep Subsurface Cracks in Thick Stainless Steel Plate
    Kishore, M. B.
    Park, D. G.
    Jeong, J. R.
    Kim, J. Y.
    Jacobs, L. J.
    Lee, D. H.
    JOURNAL OF MAGNETICS, 2015, 20 (03) : 312 - 316
  • [49] An uncooled infrared sensor of dielectric bolometer mode using a new detection technique of operation bias voltage
    Noda, M
    Inoue, K
    Ogura, M
    Xu, HP
    Murakami, S
    Kishihara, K
    Okuyama, M
    SENSORS AND ACTUATORS A-PHYSICAL, 2002, 97-8 : 329 - 336
  • [50] Multimodal deep learning-based automatic generation of repair proposals for steel bridge shallow damage
    Song, Honghong
    Zhu, Xiaofeng
    Li, Haijiang
    Yang, Gang
    AUTOMATION IN CONSTRUCTION, 2025, 171