Analysis of Shaping Coal Mine Roof Surge Capacity Based on Quantitative Prediction Model and Early Warning System
In the process of coal mining,it faces the problem of complex mechanism of roof water breakout and variable influencing factors,and the uncertainty of interconnection of various factors increases the difficulty of roof water damage prevention and control.In order to improve the accuracy and reliability of the prediction of water-yielding capacity(WYC)of coal mine roof,the main controlling factors of coal seam roof water burst were analyzed,and a quantitative prediction model of WYC based on SAA-CNN algorithm was constructed,and the WYC of the roof of 13-coal mining in Shaping coal mine was predicted,and the training and error comparison were carried out by using the BP,RF,SVM,CNN,and SAA-CNN models,respectively,and Shaping coal mine 13102 working face was selected.Coal mine 13102 working face,using a variety of physical exploration methods and drilling holes combined with overdetection,to construct the dynamic monitoring and early warning system for the risk of water breakout on the roof of the coal seam.The results show that the accuracy of WYC prediction model is SAA-CNN>RF>CNN>SVM>BP,and the average absolute error of SAA-CNN model is 0.87 m3/h,and the average relative error is 3.56%.
万方数据
维普
