论文部分内容阅读
运用灰色关联分析影响潘一东矿井瓦斯含量的各因素,得出煤层标高、顶板岩性、煤厚、地质构造是影响瓦斯赋存的主要因素。选取这四种因素作为神经网络的神经元进行建模预测,结果表明,基于灰色关联度的神经网络模型预测瓦斯含量,预测精度高,证明了基于灰色理论与神经网络预测模型的可靠性。
By using the gray correlation analysis of various factors affecting the gas content in Pan Yidong Mine, it is concluded that the coal seam elevation, roof lithology, coal thickness and geological structure are the main factors affecting the gas occurrence. The four factors are selected as the neurons of the neural network for modeling prediction. The results show that the neural network model based on gray relational degree predicts the gas content and the prediction accuracy is high, which proves the reliability based on gray theory and neural network prediction model.