基于SVM的冲击地压分级预测模型及R语言实现  

Grading prediction model of rock burst based on SVM and its R language description

作　　者：张曼 陈建宏[1] 周智勇[1] ZHANG Man;CHEN Jianhong;ZHOU Zhiyong(School of Resource and Safety Engineering,Central South University,Changsha,Hunan 410083,China)

机构地区：[1]中南大学资源与安全工程学院,湖南长沙410083

出　　处：《中国地质灾害与防治学报》2018年第4期64-69,共6页The Chinese Journal of Geological Hazard and Control

基　　金：国家自然科学基金:地下金属矿采掘计划可视化优化方法与技术研究(51374242);国家自然科学基金:基于属性驱动的矿体动态建模及更新方法研究(51504286)

摘　　要：采场冲击地压的分级预测对保障矿山安全具有重要的意义。在综合考虑采场冲击地压等级判别的各类影响因素之后,引入支持向量机(SVM)理论,建立了采场冲击地压等级判别的SVM模型。通过借助R语言实现了分层随机抽样的技术,保证了训练集与测试集样本数据的随机性和差异性。研究表明:基于SVM理论的采场冲击地压分级预测模型,可靠性强、预测准确率高。同时,采场冲击地压分级预测模型程序化语言的实现,对保障工程后期的研究预测的可持续性具有重大的意义。The grading prediction of rock burst of stope is of great significance to mine safety. Considering the influencing factors of rock burst,the prediction model is established based on the vector machine theory. the technology of stratified random sampling is realized by using R language,and the randomness and diversity of training set and testing set are guaranteed. The result shows that the prediction model of rock burst grading based on SVM theory has strong reliability and high prediction accuracy. At the same time,the realization of the programming language for the prediction model of the rock burst grading is of great significance to the sustainability of the prediction at the later stage of project.

关 键 词：冲击地压 支持向量机 R语言 分层随机抽样 

分 类 号：TD324[矿业工程—矿井建设] X936[环境科学与工程—安全科学]