Application of artificial neural network technology to predicting small faults and folds in coal seams, China

Abstract

Small geologic structures pose a great threat to production safety of the coal mines in China. Many water hazards and rock collapses are related to these small geologic structures. Accurate prediction of these structures relies on multiple lines of evidence including coal seam dip, thickness change, amount of gas accumulated, water flow changes, temperature, fracture type and degree of fragmentation of coal seams. Through the use of artificial neural network technology, this article presents a working method for forecasting small geologic structures in coal mines. The methods are applied to Zhangcun Coal Mine, China. A nonlinear model consisting of coal seam dip and thickness is constructed to predict the small structures in the front of working faces. The predictions are verified by field data. The distribution characteristics of the small structures can be accurately predicted in the coal seam extraction process as long as data of the controlling factors are accurately collected.

Numerical analysis of the effects induced by normal faults and dip angles on rock bursts

“…The overall structures of many mining areas in China are relatively simple, largely exhibiting small and medium normal faults [8,9]. Hence, in this study, the effects of a normal fault on mining in front of a working face are studied.…”