基于最小二乘支持向量机的岩石可钻性研究

DRILLABILITY BASED ON LEAST SQUARES SUPPORT VECTOR MACHINE

岩石可钻性的确定直接影响钻头选型和钻速预测,国内外各主要油田虽对地层岩性的测定相当重视,但适合于油气井钻井条件的岩石可钻性问题仍未彻底解决。针对目前国内在钻头选型方面存在的困难和问题,提出了利用LS-SVM最小二乘支持向量机求取岩石可钻性的实用方法。该方法以测井资料为参数,利用LS-SVM支持向量机技术建立岩石可钻性的数学模型。该模型在SC油田DU4井中的应用中取得了较好效果。

Drillability has a direct impact on the determination of drill bit type selection and drilling rate forecast,the major oil fields at home and abroad for the determination of lithology are very serious.However,suitability for the conditions of oil and gas wells drillability has not yet been completely resolved.In the bit type selection,based on the current domestic difficulties and problems that exist,the use of LS-SVM to strike a drillability practical method is presented.Logging data are selected as parameter,with LS-SVM Support Vector Machine technology,drillability mathematical model is built,and the model is applied to well DU4 SC Oilfield and good result achieved.