论文部分内容阅读
提出了矿区采空塌陷危险性预测的Bayes判别分析方法.首先分析了目前因采空区塌陷导致灾害事故发生的危害程度,随后介绍了Bayes判别分析方法的原理、判别准则和检验方法,在此基础上考虑采空区塌陷问题的具体特点和影响因素,选取北京西山某矿区的典型塌陷情况作为案例,对Bayes方法的运用进行了具体说明.分别选取了覆盖层类型、覆盖层厚度、地质构造复杂程度、矿层倾角、采空区体积率、采空区距地表的垂深和采空区空间叠置层数作为判别指标,以历史上17个典型塌陷资料作为学习样本进行训练,建立采空塌陷危险性预测的Bayes判别分析模型,并利用回代估计法对该模型进行检验.研究结果显示,训练后的模型判别结果完全符合实际情况.将该模型运用于7个预测样本的判别中,判别结果也和实际情况一致,说明Bayes判别分析模型具有良好的判别能力.
Bayes discriminant analysis method is proposed for the prediction of the mining collapse risk.Firstly, the damage degree of the disaster caused by the collapse of the goaf is analyzed. Then the principle, criterion and test method of the Bayesian discriminant analysis method are introduced. On the basis of considering the specific characteristics and influencing factors of the collapse of goaf, taking the typical collapse of a mining area in Xishan, Beijing as an example, the application of Bayes method is explained in detail.The types of overburden, the thickness of overburden and the geological structure Complexity, degree of seam dip, volume ratio of goaf, vertical depth of the goaf from the surface and the number of layers superposed in the goaf were used as discriminant indexes. Seventeen typical collapse data in history were used as training samples for training, and a mined-out Bayesian discriminant analysis model of collapse risk prediction is proposed, and the model is tested by using the back-estimation method.The results show that the discriminant results of the trained model are completely in accordance with the actual situation.This model is applied to the discrimination of seven prediction samples, Discriminant results are consistent with the actual situation, indicating that Bayes discriminant analysis model has good discriminating ability.