No abstract

In order to solve the problem of low accuracy and efficiency in printed circuit board(PCB) defect detection using reference methods, a Transformer-YOLO network detection model is proposed. Firstly, an imporved clustering algorithm is used to generate the anchor box suitable for the PCB defect data set of this paper. Secondly, abandoning the traditional idea of using convolutional neural network to extract image feature, Swin Transformer is used as the feature extraction network, which can effectively establish the dependency between image features. Finally, to modify the order of the channels in the feature map and enable the network to more effectively focus on the information with greater value, the convolution and attention mechanism module is added to the feature detection network component. Comparing the network model proposed in this paper with Faster R-CNN, SSD, YOLOv3, YOLOv4 and YOLOv5, the experimental results show that the proposed model improves the accuracy by 23.90%, 15.51%, 10.70%, 7.83% and 6.12% respectively, which is better than other most mainstream target detection models and has relatively small volume.

No abstract

No abstract

Deep coal seam mining often leads to water resource loss due to bedrock water entering the workings of the mine and is discharged adjacent to the mining area. Using the geological conditions of the Maiduoshan coal mine, this paper applied a physical simulation experiment. The specified rock above the coal seam was hydraulically fractured in advance to form a postmining grouted fracture network, followed by grouting to construct a flexible isolation layer that blocked the infiltration of groundwater from the aquifer into the water-conducting fracture zone. Stress sensors, flow sensors and strata displacement monitoring technology were deployed inside the experimental material to study the spatial distribution characteristics and evolution law of the water-conducting fracture zone in the overlying rocks. Analysis of the water-conducting fracture zone development law, stress variation, overburden evolution characteristics, fracturing and grouting sequence of the flexible isolation layer and the effect of postmining grouting on the water barrier was conducted. These experiments verified the feasibility of fracture and grouting of the flexible isolation layer. These research results will provide practical guidance for the transition from the current safe and efficient mining methods to safe and green mining methods of deep coal mining in the western mining areas of China.