With the aim of solving the problem of coal congestion caused by big coal blocks in underground mine scraper conveyors, in this paper we proposed the use of a YOLO-BS (YOLO-Big Size) algorithm to detect the abnormal phenomenon of coal blocks on scraper conveyors. Given the scale of the big coal block targets, the YOLO-BS algorithm replaces the last layer of the YOLOv4 algorithm feature extraction backbone network with the transform module. The YOLO-BS algorithm also deletes the redundant branch which detects small targets in the PAnet module, which reduces the overall number of parameters in the YOLO-BS algorithm. As the up-sampling and down-sampling operations in the PAnet module of the YOLO algorithm can easily cause feature loss, YOLO-BS improves the problem of feature loss and enhances the convergence performance of the model by adding the SimAM space and channel attention mechanism. In addition, to solve the problem of sample imbalance in big coal block data, in this paper, it was shown that the YOLO-BS algorithm selects focal loss as the loss function. In view of the problem that the same lump coal in different locations on the scraper conveyor led to different congestion rates, we conducted research and proposed a formula to calculate the congestion rate. Finally, we collected 12,000 image datasets of coal blocks on the underground scraper conveyor in Daliuta Coal Mine, China, and verified the performance of the method proposed in this paper. The results show that the processing speed of the proposed method can reach 80 fps, and the correct alarm rate can reach 93%. This method meets the real-time and accuracy requirements for the detection of abnormal phenomena in scraper conveyors.

Road extraction in open-pit mine is one of the important tasks of intelligent dispatching and manless driving. However, traditional methods for extracting open-pit roads cannot capture detailed information about roads, such as shape and surrounding environment. An MD-LinkNeSt (Multi Dilation-LinkNeSt) network is proposed to extract the open-pit road. First, the classification of UAV remote sensing image in mining area was completed based on mine road features. Second, ResNeSt and LinkNet are used for the encoding and decoding of MD-LinkNeSt network. The MD module includes encoding and decoding to form MD-LinkNeSt network.MD-LinkNeSt, a network framework for road extraction from open-pit mines, is constructed. Third, to enhance the extraction effect of MD-LinkNeSt network on open-pit road, the road loss function is added to MD-LinkNeSt network. Compared with the networks of Unet, DUnet, LinkNet and D-LinkNet, the network in this paper has higher IOU (Intersection over Union) and better continuity. Finally, the road network model is generated by using the open-pit mine road extraction method. The results show that this method can not only extract the road details better than the traditional method, but also meet the intelligent extraction accuracy requirements of the main road network in the open-pit mine.

Aiming at the problem of serious shutdowns of conveyors caused by abnormal coal flow of scraper conveyors, a coal flow monitoring method based on speckle structured light is proposed. The point cloud data of the coal body on the scraper conveyor is collected through the speckle structured light acquisition system. Then, the proposed PDS-Algorithm (Planar Density Simplification Algorithm) is used to complete the simplification and differentiation of the collected point cloud data, which provides a basis for constructing geometric characteristics of coal flow lineament. This paper uses the processed point cloud data to calculate the volume of the coal mass and monitor the coal flow of the scraper conveyor. Finally, this method is used in the detection of abnormal coal flow of a coal mine scraper conveyor, and the results show that the proposed abnormal flow monitoring method can meet the accuracy and real-time requirements of coal mine abnormal alarms.