东北大学学报（自然科学版）

东北大学学报(自然科学版) ›› 2010, Vol. 31 ›› Issue (9): 1345-1348.DOI: -

• 论著 • 上一篇    下一篇

基于DE-SVM的岩层可钻性预测研究

邢军;姜谙男;邱景平;孙晓刚;   

  1. 东北大学资源与土木工程学院;大连海事大学交通与物流工程学院;
  • 收稿日期:2013-06-20 修回日期:2013-06-20 出版日期:2010-09-15 发布日期:2013-06-20
  • 通讯作者: -
  • 作者简介:-
  • 基金资助:
    国家自然科学基金资助项目(50508007);;

On the DE-SVM-based forecast of rock stratum drillability

Xing, Jun (1); Jiang, An-Nan (2); Qiu, Jing-Ping (1); Sun, Xiao-Gang (1)   

  1. (1) School of Resources and Civil Engineering, Northeastern University, Shenyang 110004, China; (2) School of Traffic and Logistics Engineering, Dalian Maritime University, Dalian 116026, China
  • Received:2013-06-20 Revised:2013-06-20 Online:2010-09-15 Published:2013-06-20
  • Contact: Xing, J.
  • About author:-
  • Supported by:
    -

RichHTML

0

PDF (PC)

558

摘要： 鉴于试验确定深部岩层可钻性指标成本很高,而且测井信息神经网络模型往往存在过学习问题,利用遵循结构风险最小化的统计学习理论工具——支持向量机(SVM)建立可钻性预测模型,通过支持向量机对样本的学习,建立岩层可钻性与诸多测井信息的复杂非线性映射.为解决支持向量机参数选取问题,引入全局优化算法——差异进化算法(DE),建立DE-SVM的进化模型,进一步提高模型预测精度.算例表明,差异进化算法收敛快速,该方法预测精度高于传统方法,对新井钻头选型和钻速确定有重要意义.

关键词: 岩层可钻性, 测井资料, 支持向量机, 差异进化算法, 预测精度

Abstract: The support vector machine (SVM), as a statistical learning algorithm to minimize structure risk, is used to develop a forecasting model of drillability, thus avoiding the high-cost testing for determining plutonic rock stratum drillability and the overlearning which is often found in the application of neural network model of logging data. Learning the samples with SVM, the complex nonlinear mapping between rock stratum drillability and many logging data is given. To select the SVM parameters, the difference evolution (DE) algorithm as a global optimization algorithm is introduced to develop the DE-SVM evolutionary model so as to improve further the forecast precision by modeling. The numerical example indicates that the DE algorithm converges rapidly and its forecasting precision is higher than other conventional methods. The method proposed is of importance to selecting drill-bits for new oilwell and determining the drilling speed.

中图分类号: