Deep-learning-based multistate monitoring method of belt conveyor turning section

Abstract

During transportation, bulk materials are susceptible to spillage due to equipment instability and environmental factors, resulting in increased maintenance costs and environmental pollution. Thus, intelligent and efficient condition monitoring is crucial for maintaining operational efficiency of transfer equipment. It facilitates the timely identification of potential safety hazards, preventing accidents from occurring or their impact from spreading, thereby minimizing production and maintenance costs. This study presents a deep-learning-based multioperation synchronous monitoring method suitable for belt conveyors that integrate target segmentation and detection networks to simultaneously diagnose belt deviation, measure conveying load, identify idlers, and do other tasks on a self-made dataset. This method effectively reduces the complexity of multistate simultaneous monitoring and monitoring costs, thereby avoiding environmental pollution caused by transportation accidents. Experimental results show that the segmentation accuracy of the proposed method can be up to 88.72%, with a detection accuracy of 91.3% and an overall inference speed of 90.9 frames per second. Furthermore, by extending the dataset, the proposed method can incorporate additional tasks, such as belt damage, scattered material, and foreign object identifications. This study has practical significance in ensuring the normal and eco-friendly operation of bulk material transportation. Our source dataset is available at https://github.com/zhangzhangzhang1618/dataset-for-turnning-section