Natural gas pre-pumping in coal seam can improve the efficiency of underground mining and the utilization rate of natural gas,and the drilling depth is the key parameter of natural gas pre-pumping.Therefore,the drilling pipe counting method is studied in detail.The working state data set of drilling rig is established as the data basis of the drilling pipe counting method,the counting method of drill pipe under different environment of coal mine is studied.A solution based on improved MobileNetV2(P-MobileNetV2)is proposed to solve the problem of low precision of drill pipe counting in stable working environment of drill rig.The results show that P-MobileNetV2 is superior to other 7 classical image recognition models in the task of rig status recognition,and has certain application feasibility in coal mine underground.
关键词
煤与瓦斯突出/图像处理/钻杆计数/MobileNetV2
Key words
coal and gas outburst/image processing/drill pipe counting/MobileNetV2
维普
万方数据