摘要
针对钻具失效影响因素多,隐蔽性强的特点,提出了一种运用支持向量机技术分析钻具失效的新方法;建立了基于支持向量机技术的钻具失效模型,通过小样本数据优化,利用该模型对现场数据进行了模拟预测实验.实验结果与实际情况相吻合.
In this paper,the basal contents and methods of the SVM technology are introduced and a drill stem failure learning model based on the SVM technology is established by learning small data samples to optimize the model in order to study the drill stem failure in drilling engineering.In addition,the model is applied to the classification of the drilling data from spot for predication experiment,the very similar results are obtained.The results indicate that the SVM technology and its learning model are applicable in drilling engineering.
出处
《大庆石油学院学报》
CAS
北大核心
2006年第1期70-72,共3页
Journal of Daqing Petroleum Institute
基金
黑龙江自然科学基金资助(E200507)
关键词
钻井工程
钻具失效
统计学习理论
支持向量机
最优分类面
核函数
drilling engineering
drill stem failure
statistical learning theory
support vector machine
optimal separating hyper-plane
kernel function
