Establishment of grey-neural network forecasting model of coal and gas outburst
Procedia Earth and Planetary Science
Effect factors on coal and gas outburst are analyzed using grey correlation method so as to determine the input parameters of artificial neural network (ANN).Then using the improved BP algorithm, we choose five dominant factors of grey correlation analysis as the input parameters to establish neural network model for forecasting coal and gas outburst. This network was trained by using the learning samples collected from the instances of typical coal and gas outburst mines in China. Meanwhile,
... take coal and gas outburst instances of Yunnan Enhong coal mine as forecasting samples and compare the forecasting result from these samples with that from the conventional method, indicating that this model can meet the forecasting requirements of coal and gas outburst. The consistent coefficient of coal is a kind of relative indexes of coal particles' mechanical strength. Its value reflects coal's physical and mechanical properties and is also an important parameter involved in coal and gas outburst. Generally, the bigger the f is, the more difficult the outburst happens under the same gas pressure and ground stress. Gas pressure Ground stress controls gas pressure field and promotes coal-body to be destructed by gas. The increased pressure in surrounding rock determines ventilation property of coal seams and leads to increase pressure gradient which is favorable for the coal and gas outburst to happen. The content of gas pressure is an important symbol of gas compressive energy's value.