| 支持向量机算法用于水淹层测井识别 |
| |
| 引用本文： | 程鹏飞 赵军 唐谢 付洪. 支持向量机算法用于水淹层测井识别[J]. 国外测井技术, 2007, 22(4): 29-32 |
| |
| 作者姓名： | 程鹏飞 赵军 唐谢 付洪 |
| |
| 作者单位： | 西南石油大学，西南石油大学，西南石油大学，西南石油大学 四川 成都 610500，四川 成都 610500，四川 成都 610500，四川 成都 610500 |
| |
| 摘 要： | 支持向量机(SVM)算法是特别适合于用有限已知样本训练建模,进而预报未知样本属性的模式识别新算法。本文旨在尝试将Vapnik提出的支持向量机算法用于水淹层测井识别。本文总结了P油田水淹层的声波时差、自然电位、深感应电阻率、中感应电阻率及密度测并曲线与水淹程度的对应关系,建立了基于支持向量分类机的识别模型,并将上述参数作为训练样本的输入,油气特征作为训练样本的输出,对支持向量机进行训练。对于P油田水淹层的实际预测结果表明:支持向量机可以成为一种用于水淹层识别的有效工具。
|
| 关 键 词： | 水淹层 测井识别 数学模型 模式识别 支持向量机 |
The Support Vector Machine Algorithm Applied to Identification of Water-Flooded Zone with Well Logging |
| |
| Cheng Pengfei Zhao Jun Tang Xie Southwest University of Petroleum. The Support Vector Machine Algorithm Applied to Identification of Water-Flooded Zone with Well Logging[J]. World Well Logging Technology, 2007, 22(4): 29-32 |
| |
| Authors: | Cheng Pengfei Zhao Jun Tang Xie Southwest University of Petroleum |
| |
| Affiliation: | Cheng Pengfei Zhao Jun Tang Xie Southwest University of Petroleum |
| |
| Abstract: | Support vector machine (SVM) algorithm proposed by Vapnik is a newly developed technique for data mining.It is suitable for the data processing based on finite number of training samples,with special technique to restrict overfitting.In this work,support vector classifica- tion technique is used to make modeling on the relationship among acoustictime,SP,deep induction resistivity,medium induction resistivi- ty,density and the water-flooded grade.These parameters are taken as imput and the character of oil and gas as export.It has been used in P oilfiel and found that SVM can give efficient modeling results. |
| |
| Keywords: | water-flooded zone well logging identification mathematical model pattern recognition support vector machine |
| 本文献已被 CNKI 维普 等数据库收录！ |
