The current existing problem of deep learning framework for the detection and segmentation of electrical equipment is dominantly related to low precision.Because of the reliable,safe and easy-to-operate technology pro...The current existing problem of deep learning framework for the detection and segmentation of electrical equipment is dominantly related to low precision.Because of the reliable,safe and easy-to-operate technology provided by deep learning-based video surveillance for unmanned inspection of electrical equipment,this paper uses the bottleneck attention module(BAM)attention mechanism to improve the Solov2 model and proposes a new electrical equipment segmentation mode.Firstly,the BAM attention mechanism is integrated into the feature extraction network to adaptively learn the correlation between feature channels,thereby improving the expression ability of the feature map;secondly,the weighted sum of CrossEntropy Loss and Dice loss is designed as the mask loss to improve the segmentation accuracy and robustness of the model;finally,the non-maximal suppression(NMS)algorithm to better handle the overlap problem in instance segmentation.Experimental results show that the proposed method achieves an average segmentation accuracy of mAP of 80.4% on three types of electrical equipment datasets,including transformers,insulators and voltage transformers,which improve the detection accuracy by more than 5.7% compared with the original Solov2 model.The segmentation model proposed can provide a focusing technical means for the intelligent management of power systems.展开更多
Being a safe and highly-efficient mining method, fully mechanized mining with sublevel caving （FMMSC） was extensively employed in Chinese coal mines with thick seam. In order to make drawing top-coal furthest to par...Being a safe and highly-efficient mining method, fully mechanized mining with sublevel caving （FMMSC） was extensively employed in Chinese coal mines with thick seam. In order to make drawing top-coal furthest to parallel work with shearer cutting coal, decrease failure ratio of rear scraper conveyor and increase safe production capacity of equipments, based on production technology, set up the mating model of safe production capacity of equipments for the system of drawing top-coal and shearer cutting coal in coal face with sublevel caving. It is mean capability of drawing top-coal adapted to the capability of shearer cutting coal in a working circle in the coal face that was deduced. The type selection of equipment of rear scraper conveyor can be tackled with this mating model. The model was applied in FMMSC in Yangcun Coal Mine, Yima Coal Group of China. With the mating light-equipments, the coal output in coal face attained 1.05 Mt in 2004. It gained better technical-economic benefit.展开更多
This paper describes the state-of-the-art and Outlook of coal mining and clean coal technology in China. As the major mining method,underground mining accounts for 96% of the total production. Among the state own mine...This paper describes the state-of-the-art and Outlook of coal mining and clean coal technology in China. As the major mining method,underground mining accounts for 96% of the total production. Among the state own mines, the percentage of mechanized mining reached 71 %. A rapid development of high-productive and high-profitable mines,especially those with longwall sublevel caving method, is described. The issues of heavy duty equipment, roof bolting,mine safety are also addressed. The Chinese government is paying more and more attention on the environmental problems inducing from coal mining,processing and utilization. A basic framework of clean coal technology is being formed and a wide range of technology is included.展开更多
基金Jilin Science and Technology Development Plan Project(No.20200403075SF)Doctoral Research Start-Up Fund of Northeast Electric Power University(No.BSJXM-2018202).
文摘The current existing problem of deep learning framework for the detection and segmentation of electrical equipment is dominantly related to low precision.Because of the reliable,safe and easy-to-operate technology provided by deep learning-based video surveillance for unmanned inspection of electrical equipment,this paper uses the bottleneck attention module(BAM)attention mechanism to improve the Solov2 model and proposes a new electrical equipment segmentation mode.Firstly,the BAM attention mechanism is integrated into the feature extraction network to adaptively learn the correlation between feature channels,thereby improving the expression ability of the feature map;secondly,the weighted sum of CrossEntropy Loss and Dice loss is designed as the mask loss to improve the segmentation accuracy and robustness of the model;finally,the non-maximal suppression(NMS)algorithm to better handle the overlap problem in instance segmentation.Experimental results show that the proposed method achieves an average segmentation accuracy of mAP of 80.4% on three types of electrical equipment datasets,including transformers,insulators and voltage transformers,which improve the detection accuracy by more than 5.7% compared with the original Solov2 model.The segmentation model proposed can provide a focusing technical means for the intelligent management of power systems.
文摘Being a safe and highly-efficient mining method, fully mechanized mining with sublevel caving （FMMSC） was extensively employed in Chinese coal mines with thick seam. In order to make drawing top-coal furthest to parallel work with shearer cutting coal, decrease failure ratio of rear scraper conveyor and increase safe production capacity of equipments, based on production technology, set up the mating model of safe production capacity of equipments for the system of drawing top-coal and shearer cutting coal in coal face with sublevel caving. It is mean capability of drawing top-coal adapted to the capability of shearer cutting coal in a working circle in the coal face that was deduced. The type selection of equipment of rear scraper conveyor can be tackled with this mating model. The model was applied in FMMSC in Yangcun Coal Mine, Yima Coal Group of China. With the mating light-equipments, the coal output in coal face attained 1.05 Mt in 2004. It gained better technical-economic benefit.
文摘This paper describes the state-of-the-art and Outlook of coal mining and clean coal technology in China. As the major mining method,underground mining accounts for 96% of the total production. Among the state own mines, the percentage of mechanized mining reached 71 %. A rapid development of high-productive and high-profitable mines,especially those with longwall sublevel caving method, is described. The issues of heavy duty equipment, roof bolting,mine safety are also addressed. The Chinese government is paying more and more attention on the environmental problems inducing from coal mining,processing and utilization. A basic framework of clean coal technology is being formed and a wide range of technology is included.
