神经网络法分析煤层瓦斯含量的影响因素

Prediction of Gas Contents By Artificial Neural Network

用人工神经网络模型分析了影响因素对瓦斯含量的定量影响,结果表明:瓦斯含量随煤层底板标高值的减小而增大;随与最近剥蚀面间距离的增加而增大;顶板砂岩比越低,瓦斯含量越高;顶板岩性为泥岩时,瓦斯含量高,为砂岩时,瓦斯含量低;到断层距离(m)越大,瓦斯含量越高;煤厚越高,瓦斯含量越低。

Back-propagation artificial neural network was developed to predict the gas contents.'Leave-one out' method was used to train and vali-date the ANN model.Both scatter diagram and statistical criteria showed that the prediction performance is satisfactory.