作　　者： ; ; ; ; ;

机构地区： 中南大学资源与安全工程学院

出　　处： 《煤炭学报》 2009年第4期487-491,共5页

摘　　要： 为了从理论上对煤层底板突水问题进行分析,选取对底板突水影响最大的有无含水层、水压、隔水层厚度、底板采动破坏深度及断层落差等作为基本判别因子,选取国内15个有代表性的采煤工作面底板突水资料作为训练样本,利用距离判别分析理论,建立了煤层底板突水量预测的距离判别分析模型.用所建立的模型对4个待检验的底板突水案例进行了分析,与实际情况吻合良好,计算结果与最小二乘支持向量机(SVM)、人工神经网络(ANN)等方法所得到的结果一致或更好. In order to analyze the phenomenon of water inrush from coal floor theoretically, it is essential to make simplification and takes only the most significant factors related to the problem into the theoretic model, such as existence of water source, water pressure, mining failure thickness of seam floor, and fault displacement etc. Fifteen representative engineering cases of water inrush from coal floor were taken as training samples. A correspondent forecast model of water inrush quantity was established based on the principle of Mahalanobis distance discriminant analysis theory. The forecast model was applied and tested in four actual water inrush cases, both the validity and the feasibility were approved. The result is same or better than the results with the least squares SVM, ANN or other methods.

关 键 词： 底板突水 突水量 距离判别分析理论 预测方法

领　　域： [矿业工程]