Drone-Based Intelligent Bridge Damage Detection and Maintenance Decision-Making System

With the rapid advancement of technology, drone technology has demonstrated significant potential in the field of bridge inspection and maintenance. However, traditional bridge inspection methods, which rely on visual inspections by human inspectors, suffer from issues such as time consumption, high costs, and difficulty in achieving comprehensive monitoring. To address these challenges, this paper proposes and implements an intelligent bridge damage detection and maintenance decision-making system based on drones. The system integrates high-resolution cameras, advanced communication technologies, and deep learning-based damage detection algorithms to enable efficient and accurate monitoring of bridge structures. By optimizing and combining the ShuffleNetV2 and YOLOv8 algorithms, the system maintains high detection accuracy under various lighting and environmental conditions. Additionally, the system employs big data analysis and machine learning techniques to provide scientifically informed maintenance decision support. Experimental results demonstrate that the proposed system excels in bridge damage identification and assessment, significantly improving detection efficiency and accuracy. This research provides an effective technological approach for bridge health management and holds substantial engineering application value.