• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文期刊>Surveys in Geophysics: An International Review Journal of Geophysics and Planetary Sciences >Fuzzy Logic Determination of Lithologies from Well Log Data: Application to the KTB Project Data set (Germany) (Review)
【24h】

Fuzzy Logic Determination of Lithologies from Well Log Data: Application to the KTB Project Data set (Germany) (Review)

机译：根据测井数据对岩性进行模糊逻辑确定：应用于KTB项目数据集（德国）（综述）

获取原文
获取原文并翻译 | 示例
           
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

Fuzzy logic has been used for lithology prediction with remarkable success. Several techniques such as fuzzy clustering or linguistic reasoning have proven to be useful for lithofacies determination. In this paper, a fuzzy inference methodology has been implemented as a MATLAB routine and applied for the first time to well log data from the German Continental Deep Drilling Program (KTB). The training of the fuzzy inference system is based on the analysis of the multi-class Matthews correlation coefficient computed for the classification matrix. For this particular data set, we have found that the best suited membership function type is the piecewise linear interpolation of the normalized histograms; that the best combination operator for obtaining the final lithology degrees of membership is the fuzzy gamma operator; and that all the available properties are relevant in the classification process. Results show that this fuzzy logic-based method is suited for rapidly and reasonably suggesting a lithology column from well log data, neatly identifying the main units and in some cases refining the classification, which can lead to a better interpretation. We have tested the trained system with synthetic data generated from property value distributions of the training data set to find that the differences in data distributions between both wells are significant enough to misdirect the inference process. However, a cross-validation analysis has revealed that, even with differences between data distributions and missing lithologies in the training data set, this fuzzy logic inference system is able to output a coherent classification.
机译：模糊逻辑已成功地用于岩性预测。事实证明，模糊聚类或语言推理等多种技术可用于岩相确定。在本文中，模糊推理方法已作为MATLAB例程实现，并首次应用于德国大陆深层钻探计划（KTB）的测井数据。模糊推理系统的训练基于对分类矩阵计算的多类Matthews相关系数的分析。对于这个特定的数据集，我们发现最合适的隶属函数类型是归一化直方图的分段线性插值。获得最终岩性的最佳组合算子是模糊伽玛算子;并且所有可用的属性都与分类过程相关。结果表明，这种基于模糊逻辑的方法适用于从测井数据中快速合理地建议岩性柱，整洁地识别主要单元并在某些情况下完善分类，从而可以更好地解释。我们已经使用由训练数据集的属性值分布生成的综合数据对训练后的系统进行了测试，以发现两口井之间数据分布的差异足以显着误导推理过程。但是，交叉验证分析表明，即使训练数据集中的数据分布和缺少的岩性之间存在差异，该模糊逻辑推理系统也能够输出一致的分类。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱：kefu@zhangqiaokeyan.com

京公网安备：11010802029741号 ICP备案号：京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有

  • 客服微信

  • 服务号