基于统计学习理论的山前构造带推覆带钻具失效预测  

Study on Piedmont Nappe Drill Stem Failure Based on Statistical Learning Theory

作　　者：张殿锋[1] 闫相祯[2] 

机构地区：[1]中国石油大学(华东)机电工程学院,山东青岛266555 [2]中国石油大学(华东)储运与建筑工程学院,山东青岛266555

出　　处：《石油矿场机械》2012年第8期7-10,共4页Oil Field Equipment

基　　金：国家高技术研究发展计划(863计划)"深井钻井钻柱失效项目"(2008AA06A2260)

摘　　要：山前构造带推覆带钻具失效影响因素多,隐蔽性强。应用统计学习理论和支持向量机技术,建立了基于统计学习理论的山前推覆带钻具失效学习模型,通过对小样本数据的学习进行优化,分析钻具失效问题。应用该模型对现场钻井数据进行模拟,获得了和实际情况相一致的预测结果。In this paper,the statistical learning theory and the SVM technology are introduced and Piedmont nappe drill stem failure learning model based on statistical learning theory is established by learning small data samples to optimize the model in order to study the drill stem failure in drilling engineering. On the basis, the model is applied to the classification of the drilling data from spot for predication experiment;the results consistent with the actual situation are obtained. The results indicate that the SVM technology and its learning model are applicable in drilling engineering.

关 键 词：钻具事故 统计分析 支持向量机 最优分类面 核函数 

分 类 号：TE921.201[石油与天然气工程—石油机械设备]