基于改进MobileNetV2的钻杆计数方法研究

Research on Drill Pipe Counting Method Based on Improved MobileNetV2

煤层天然气预抽可提高煤矿井下开采效率和天然气利用率,而钻孔深度是天然气预抽的关键参数。为此,对钻杆计数方法展开了详细研究。建立钻机工作状态数据集作为钻杆计数方法的数据基础,探究了煤矿井下不同环境中的钻杆计数方法。针对钻机稳定工作环境中钻杆计数精度低的问题,提出了基于改进MobileNetV2(P-MobileNetV2)的解决方案。结果表明,P-MobileNetV2在钻机工作状态识别任务上优于其他7种经典图像识别模型,在煤矿井下具有一定的应用可行性。

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.