Real-time classification of longitudinal conveyor belt cracks with deep-learning approach

Abstract

Long tunnels are a necessary means of connectivity due to topological conditions across the world. In recent years, various technologies have been developed to support construction of tunnels and reduce the burden on construction workers. In continuation, mountain tunnel construction sites especially pose a major problem for continuous long conveyor belts to remove crushed rocks and rubbles out of tunnels during the process of mucking. Consequently, this process damages conveyor belts quite frequently, and a visual inspection is needed to analyze the damages. Towards this, the paper proposes a model to configure the damage and its size on conveyor belt in real-time. Further, the model also localizes the damage with respect to the length of conveyor belt by detecting the number markings at every 10 meters of the belt. The effectiveness of the proposed framework confirms superior real-time performance with optimized model detecting cracks and number markings with mAP of 0.850 and 0.99 respectively, while capturing 15 frames per second on edge device. The current study marks and validates the versatility of deep learning solutions for mountain tunnel construction sites.