It is important to understand the development of joints and fractures in rock masses to ensure drilling stability and blasting effectiveness.Traditional manual observation techniques for identifying and extracting fra...It is important to understand the development of joints and fractures in rock masses to ensure drilling stability and blasting effectiveness.Traditional manual observation techniques for identifying and extracting fracture characteristics have been proven to be inefficient and prone to subjective interpretation.Moreover,conventional image processing algorithms and classical deep learning models often encounter difficulties in accurately identifying fracture areas,resulting in unclear contours.This study proposes an intelligent method for detecting internal fractures in mine rock masses to address these challenges.The proposed approach captures a nodal fracture map within the targeted blast area and integrates channel and spatial attention mechanisms into the ResUnet(RU)model.The channel attention mechanism dynamically recalibrates the importance of each feature channel,and the spatial attention mechanism enhances feature representation in key areas while minimizing background noise,thus improving segmentation accuracy.A dynamic serpentine convolution module is also introduced that adaptively adjusts the shape and orientation of the convolution kernel based on the local structure of the input feature map.Furthermore,this method enables the automatic extraction and quantification of borehole nodal fracture information by fitting sinusoidal curves to the boundaries of the fracture contours using the least squares method.In comparison to other advanced deep learning models,our enhanced RU demonstrates superior performance across evaluation metrics,including accuracy,pixel accuracy(PA),and intersection over union(IoU).Unlike traditional manual extraction methods,our intelligent detection approach provides considerable time and cost savings,with an average error rate of approximately 4%.This approach has the potential to greatly improve the efficiency of geological surveys of borehole fractures.展开更多
Minerals are the material foundation for advancing human civilization,the starting point of the manufacturing supply chain,and strategic resources essential for national security and economic progress.In recent years,...Minerals are the material foundation for advancing human civilization,the starting point of the manufacturing supply chain,and strategic resources essential for national security and economic progress.In recent years,deep learning and big data have strongly supported improving mining efficiency and safety in underground hard rock mines.Against this backdrop,this paper focuses on the production processes and vital auxiliary aspects of underground mining in hard rock mines.It delves into six aspects:driling,blasting,transportation,hoisting,ventilation,and support and flling.The paper elaborates on the latest advancements in intelligent technology research for each aspect and provides a summary and outlook on the key technologies relevant to these processes.Research results show that the current intelligent technology used in underground mining not only improves production efficiency but also further improves the safety production level of mining enterprises.To achieve intelligent unmanned mining,bottleneck problems in each primary process must be further addressed.展开更多
基金supported by the National Natural Science Foundation of China(No.52474172).
文摘It is important to understand the development of joints and fractures in rock masses to ensure drilling stability and blasting effectiveness.Traditional manual observation techniques for identifying and extracting fracture characteristics have been proven to be inefficient and prone to subjective interpretation.Moreover,conventional image processing algorithms and classical deep learning models often encounter difficulties in accurately identifying fracture areas,resulting in unclear contours.This study proposes an intelligent method for detecting internal fractures in mine rock masses to address these challenges.The proposed approach captures a nodal fracture map within the targeted blast area and integrates channel and spatial attention mechanisms into the ResUnet(RU)model.The channel attention mechanism dynamically recalibrates the importance of each feature channel,and the spatial attention mechanism enhances feature representation in key areas while minimizing background noise,thus improving segmentation accuracy.A dynamic serpentine convolution module is also introduced that adaptively adjusts the shape and orientation of the convolution kernel based on the local structure of the input feature map.Furthermore,this method enables the automatic extraction and quantification of borehole nodal fracture information by fitting sinusoidal curves to the boundaries of the fracture contours using the least squares method.In comparison to other advanced deep learning models,our enhanced RU demonstrates superior performance across evaluation metrics,including accuracy,pixel accuracy(PA),and intersection over union(IoU).Unlike traditional manual extraction methods,our intelligent detection approach provides considerable time and cost savings,with an average error rate of approximately 4%.This approach has the potential to greatly improve the efficiency of geological surveys of borehole fractures.
基金supported by the National Natural Science Foundation of China (No.U21A20106)the Chinese Academy of Engineering Project (Nos.2022-33-29 and 2023-XY-44).
文摘Minerals are the material foundation for advancing human civilization,the starting point of the manufacturing supply chain,and strategic resources essential for national security and economic progress.In recent years,deep learning and big data have strongly supported improving mining efficiency and safety in underground hard rock mines.Against this backdrop,this paper focuses on the production processes and vital auxiliary aspects of underground mining in hard rock mines.It delves into six aspects:driling,blasting,transportation,hoisting,ventilation,and support and flling.The paper elaborates on the latest advancements in intelligent technology research for each aspect and provides a summary and outlook on the key technologies relevant to these processes.Research results show that the current intelligent technology used in underground mining not only improves production efficiency but also further improves the safety production level of mining enterprises.To achieve intelligent unmanned mining,bottleneck problems in each primary process must be further addressed.
