A deep learning-based method for deviation status detection in intelligent conveyor belt system

Abstract

Belt deviation is one of the most common faults of belt conveyors . Its occurrence not only causes materials to be scattered and affect the environment but also results in abnormal wear of equipment and increased energy consumption, which severely affects the green production and sustainable development of enterprises. Therefore, the rapid and timely detection of the deviation state of conveyor belts is of great significance for ensuring the safe and efficient operation of transportation systems. In view of the disadvantages of the available technology in terms of detection speed, a novel conveyor belt deviation monitoring method based on deep learning is proposed in this paper, which is realized by improving the output results of a general target detection network, YOLOv5, such that the network is enhanced with the ability to detect straight lines instead of bounding box , which effectively solves the problem of rapid feature extraction and deviation judgment of the edges of the conveyor belt of a belt conveyor against a complex background. Experiments show that the proposed method balances detection accuracy and speed, with a detection accuracy of up to 90% and a detection speed of up to 67 frames per second (FPS), and shows good real-time performance. The method greatly simplifies the process of straight-line feature extraction in complex environments, helps realize the intellectualization of conveyors, and achieves unmanned operation and energy savings in coal mines to realize green, energy-saving, and sustainable development while ensuring safe and efficient transportation. • General target detection network-based straight line detection method. • Efficient conveyor belt edge detection under complex scenes. • New detection method of belt deviation to ensure safe and clean transportation.