勘探阶段可采煤层顶底板岩体质量分类模型

发布时间：2018-01-06 00:34

本文关键词：勘探阶段可采煤层顶底板岩体质量分类模型　出处：《应用基础与工程科学学报》2016年03期 　论文类型：期刊论文

【摘要】：提出了在煤田勘探阶段利用主要物理力学性质指标和岩体质量指标进行可采煤层顶底板岩体质量分类的模型.以新疆伊犁州尼勒克县某煤矿为研究背景,选取了天然单轴抗压强度、饱和单轴抗压强度、天然抗拉强度、饱和抗拉强度、天然抗剪强度、饱和抗剪强度、天然密度、含水率、孔隙率、软化系数和RQD值等11项因子作为分类指标,以该煤矿8个可采煤层顶底板的50组岩样样品作为学习样本,首先采用因子分析和Q型聚类分析方法对样品进行综合评价分类,分类结果理想;然后分别计算每一类别样品11项分类指标的平均值并进行对比分析,结果表明,11项指标选取合理;最后采用Fisher判别分析方法对50组样品进行训练,建立了相应的Fisher判别模型,经检验正确率达到98%;将该判别模型应用到乌鲁木齐市某一煤矿对岩样进行分类,其分类结果与神经网络模型、因子和聚类联合分析的分类结果一致,有3个分类结果与规范分类出现偏差,经分析认为新建的判别模型分类结果更为真实可靠.
[Abstract]:This paper presents a model for classification of rock mass quality of coal seam roof and floor by means of main physical and mechanical properties and rock mass quality indexes in coalfield exploration stage, taking a coal mine in Nilake County, Yili Prefecture, Xinjiang as the research background. Natural uniaxial compressive strength saturated uniaxial compressive strength natural tensile strength saturated tensile strength natural shear strength saturated shear strength natural density moisture content porosity. Eleven factors, such as softening coefficient and RQD value, are used as classification indexes, and 50 rock samples from 8 minable coal seam roof and floor in this coal mine are taken as study samples. Firstly, factor analysis and Q cluster analysis were used to evaluate and classify the samples, and the classification results were satisfactory. Then, the average value of 11 classification indexes for each category of samples is calculated and compared, the results show that the selection of 11 indexes is reasonable. Finally, the Fisher discriminant analysis method was used to train 50 groups of samples, and the corresponding Fisher discriminant model was established. The discriminant model is applied to the classification of rock samples in a coal mine in Urumqi. The classification results are consistent with those of neural network model, factor and clustering analysis. Three classification results deviate from the standard classification, and it is considered that the new discriminant model is more reliable.
【作者单位】：新疆大学地质与矿业工程学院;中国矿业大学资源与地球科学学院;新疆煤炭设计研究院;新疆维吾尔自治区地质矿产研究所;
【基金】：中国地质调查局资助项目(基[2013]01-002-015)
【分类号】：TD327.2
【正文快照】：

【相似文献】