用灰关联分析和神经网络方法预测煤与瓦斯突出

coal and gas outburst forecast by ANN and grey correlation

本文应用灰色系统理论的灰色关联分析,对煤与瓦斯突出影响因素进行灰关联分析,得出了各影响因素对煤与瓦斯突出影响程度的大小排序,选择灰关联分析的五个优势因子:瓦斯放散初速度、坚固性系数、瓦斯压力、煤体破坏类型和开采深度,作为输入参数,用计算机对神经网络编写程序,建立了煤与瓦斯突出预测的神经网络模型。用我国典型突出矿井的煤与瓦斯突出实例作为学习样本,对网络进行训练学习,并以云南恩洪煤矿的煤与瓦斯突出实例作为预测样本进行验证。

This thesis applied grey correlation analysis of grey system theory to analyze grey correlation about influence factors of coal and gas outburst, and got the order arrange of each influence factor according to the influence degree of coal and gas outburst, choosing five advantage factors of grey correlation analysis ： initial speed of methane diffusion, coal rigidity, pressure of gas, geologic destroy degree and excavation depth, as the input parameters, neural network function storehouse of MATLAB was adopted to write the procedure, and neural network forecasting model of coal and gas outburst was built. The network was trained by using the study samples which came from the instances of typical coal and gas outburst mines of our country, and coal and gas outburst instances of Yunnan En-hong mine were used as forecasting samples. Comparing the results from network forecasting with the results of the traditional methods, it nroved that this method can meet the forecasting requirement of coal and gas outburst.