Delamination detection in concrete decks using numerical simulation and UAV-based infrared thermography with deep learning
Date
2024-12-19
Authors
Journal Title
Journal ISSN
Volume Title
Publisher
Automation in Construction
Abstract
The potential of concrete bridge delamination detection using infrared thermography (IRT) has grown with technological advancements. However, most current studies require an external input (subjective threshold), reducing the detection's objectivity and accuracy. Deep learning enables automation and streamlines data processing, potentially enhancing accuracy. Yet, data scarcity poses a challenge to deep learning applications, hindering their performance. This paper aims to develop a deep learning approach using supervised learning object detection models with extended data from real and simulated images. The numerical simulation image supplementation seeks to eliminate the limited data barrier by creating a comprehensive dataset, potentially improving model performance and robustness. Mask R-CNN and YOLOv5 were tested across various training data and model parameter combinations to develop an optimal detection model. Lastly, when tested, the model showed a remarkable ability to detect delamination of varying properties accurately compared to currently employed IRT techniques.
Highlights
• Employs Infrared Thermography with an Unmanned Aerial Vehicle (IRT-UAV) and deep learning for concrete delamination detection.
• Addresses the challenge of limited training data for deep learning by integrating real and simulated images
• Utilizes Mask R-CNN and YOLOv5 models, evaluated in four phases, to develop a robust delamination detection model.
• Collects data from a mockup slab, two in-service bridges, and 39 numerical simulation scenarios for comprehensive analysis.
Description
This article was originally published in Automation in Construction. The version of record is available at: https://doi.org/10.1016/j.autcon.2024.105940.
© 2024 Published by Elsevier B.V.
This article will be embargoed until 12/19/2026.
Keywords
delamination, Infrared Thermography (IRT), Unmanned Arterial Vehicle (UAV), deep learning, detection automation, instance segmentation, image processing, Mask R-CNN, YOLOv5, Augmentation
Citation
Aljagoub, Dyala, Ri Na, and Chongsheng Cheng. “Delamination Detection in Concrete Decks Using Numerical Simulation and UAV-Based Infrared Thermography with Deep Learning.” Automation in Construction 170 (February 2025): 105940. https://doi.org/10.1016/j.autcon.2024.105940.