立井井筒非采动破裂的遗传-支持向量机预测模型  

Forecast model of GA-SVM for shaft-lining non-mining fracture

作　　者：袁志刚[1] 王宏图[1,2] 胡国忠[3] 刘年平[1] 范晓刚[1] 

机构地区：[1]重庆大学西南资源开发及环境灾害控制工程教育部重点实验室,重庆400030 [2]重庆大学复杂煤气层瓦斯抽采国家地方联合工程实验室,重庆400030 [3]中国矿业大学矿业工程学院,江苏徐州221116

出　　处：《煤炭学报》2011年第3期393-397,共5页Journal of China Coal Society

基　　金：国家自然科学基金资助项目(50774106);国家自然科学创新群体基金资助项目(5092106);川煤集团科技项目(2009-08)

摘　　要：选取表土层厚度、底板含水层厚度、底板含水层水位速降、井筒外径、井壁厚度、井筒投入使用时间6个立井井筒非采动破裂的特征属性作为判别因子,以工程实测数据作为学习样本,利用遗传算法优化支持向量机参数,建立了煤矿立井井筒非采动破裂的遗传-支持向量机预测模型,并对工程实例进行测试。研究结果表明,该模型预测精度高,回判估计的错误率低,为快速准确地预测立井井筒非采动破裂提供了一种新的方法和途径。The parameters of support vector machine were optimized by using genetic algorithm;six factor indexes,including thickness of surface soil,thickness of basal aquifers,falling rate of basal aquifer water level,outer diameters of wellbore,thickness of shaft wall and service time of wellbore were regarded as attributes of shaft-lining fracture.The GA-SVM forecast model for shaft-lining non-mining fracture of mine was trained by training samples which received from a set of engineering data,and was tested by test samples.The results show that the model has high prediction accuracy and low error rate.It provides a new method and approach for the accurate forecast of shaft-lining non-mining fracture.

关 键 词：立井井筒 非采动破裂 遗传算法 支持向量机 

分 类 号：TD262.5[矿业工程—矿井建设]