Yolo-EV2: An Industrial Mining Conveyor Belt Tear Detection Model Based on Improved Yolov5 Algorithm for Efficient Backbone Networks

Real-time detection of conveyor belt tearing is of great significance to ensure mining in the coal industry. The longitudinal tear damage problem of conveyor belts has the characteristics of multi-scale, abundant small targets, and complex interference sources. To address these characteristics, we propose a visual detection method Yolo-EV2 based on deep learning. Firstly, a multi-case conveyor belt tear datasets is developed for complex interference and small-size detection. Secondly, the conveyor belt tear detection method Yolo-EV2 is designed, which utilizes the EfficientNetV2 to improve the network Backbone, so as to enhance the feature fusion ability of the model for small tear targets and reduce the computational volume of the overall detection model. A large number of compartment experiments with existing target detection networks on conveyor belt tear detection show that Yolo-EV2 has a better performance in both Map value and FPS, which can meet the demand of real-time detection and is expected to be used in industrial practice.