Abstract

As the backbone of transportation networks, the structural integrity of bridges is paramount for ensuring public safety and the efficient flow of goods and people. The traditional method that is Manual inspection methods for crack detection are labor intensive and often subjected to human error. This research explores an innovative approach to address this challenge by leveraging Convolutional Neural Networks for automated crack identification in bridge infrastructure. The proposed model employs a dataset encompassing concrete bridge conditions, and crack manifestations to train and evaluate the selected model. The accuracy of the prediction was verified by the test sets. The introduced model demonstrated a crack detection accuracy of 99% without relying on pre-training. Experimental results indicated that, when compared to existing classification models, the suggested model exhibited superior performance. Notably, the proposed model surpassed the ResNet50 model in terms of effectiveness.