Application of deep learning in damage classification of reinforced concrete bridges

Abstract

Inspecting Reinforced Concrete (RC) Bridges is crucial to ensure their safety and perform essential maintenance. The current research introduces the knowledge base for applying deep learning to classify and detect RC bridges' five most common defects (cracks, corrosion, efflorescence, spalling, and exposed steel reinforcement). The image classification process was carried out using Xception & Vanilla models based on convolutional neural networks (CNN). A comparative study between the two models is presented for multi-class, multi-target image classification. The concrete defect bridge image (CODEBRIM) dataset was used to train and test the models. The outcomes showed the potential application of deep learning models (Xception & Vanilla) for defect classification of concrete bridges and the superiority of the Xception model in defect classification with an accuracy of 94.95%, compared to 85.71% accuracy for the Vanilla model.

Keywords

• Convolutional Neural Networks (CNNs)
• RC
• Condition assessment
• Concrete defects
• Image classification