摘要
采用自组织特征映射神经网络(SOFM)对采空区煤自然发火与否进行了识别分类。在此基础上,建立了通过分析采空区抽放孔气体成分和抽放孔位置参数来预报煤炭自燃的BP神经网络模型。对模型预测结果与实际情况进行了对比分析,结果表明,用人工神经网络方法识别和预报采空区煤自燃是可行的。为煤自燃程度的识别和预报探索出了一种新的方法。
SOFM （Self-Organizing Feature Maps） neural network is used to identify the classification of the coal spontaneous combustion in goaf. On this basis, the BP neural network model to predict the spontaneous combustion of coal is set up by analyzing the gas composition of drainage hole and drainage hole location parameters. The predicted results of the model and the actual situation are compared and analyzed, the reslut shows that it is feasible to identify and predict the spontaneous combustion of coal in mined-out area by ANN technology. The approach proposed in this paper also provides a new way of solving the identification and prediction of coal spontaneous combustion.
出处
《西安科技大学学报》
CAS
北大核心
2009年第4期410-414,共5页
Journal of Xi’an University of Science and Technology
关键词
神经网络
自然发火
煤矿安全
artificial neural network
spontaneous combustion
mine safety
作者简介
徐杨（1986-），男，安徽宿州人，硕士研究生，主要从事矿井防灭火方面的研究．
