• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文会议>Iron ore 2011 >Identifi cation of Shale and Ore Boundaries Using Gaussian Processes
【24h】

Identifi cation of Shale and Ore Boundaries Using Gaussian Processes

机译：使用高斯过程识别页岩和矿石边界

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

Shales form distinctive peaks in natural gamma downhole logs, which are used to manuallyrnidentify the location of ore boundaries. These shales form important lithology markers that canrnpotentially be automatically identifi ed using Gaussian processes. This approach is trialled usingrndata from a typical iron ore mine in Western Australia which contains the Marra Mamba sequencernof the Hamersley province.rnThe method uses Gaussian processes (GPs) with a single length scale squared exponentialrncovariance function. A library of 8 m sections, where natural gamma measurements were takenrnat 10 cm intervals down the hole, was used to train the GP model. This library was iterativelyrnimproved and was tested using natural gamma logs that were not included in the library. Areasrnthat were misclassifi ed or were not clearly classifi ed were added to the library. The new libraryrnwas then used to train the model and improve the results. The trials used a double gamma peakrnfrom the NS3 and NS4 shales at the boundary between the Newman 1 and Newman 2 ore zonesrnin the Newman member and the AS1 and AS2 shales at the base of the West Angelas member.rnThe results show that both boundaries can be identifi ed with an accuracy of over 99 per cent.rnThe classifi cation has the highest accuracy on undeformed shales. This method provides a fast,rnaccurate and objective identifi cation of shale and ore boundaries and can potentially replace therncurrent manual detection.
机译：页岩在天然伽马井下测井曲线中形成独特的峰，用于手动识别矿石边界位置。这些页岩形成了重要的岩性标志，可以利用高斯过程自动识别。该方法使用了来自澳大利亚西部一个典型铁矿石矿的数据进行了试验，该数据包含了Hamersley省的Mara Mamba序列。该方法使用了具有单长度比例平方平方协方差函数的高斯过程（GPs）。一个8 m截面的库用于训练GP模型，其中自然伽马测量以10 cm的间隔沿孔向下进行。该库经过反复改进，并使用未包含在库中的自然伽马测井进行了测试。将错误分类或未明确分类的区域添加到库中。然后使用新的库来训练模型并改善结果。试验使用了来自纽曼成员纽曼1和纽曼2矿带边界处的NS3和NS4页岩以及西安杰拉斯成员底部的AS1和AS2页岩的双重伽马峰-结果。准确度超过99％。rn该分类在未变形的页岩中具有最高的准确度。该方法可快速，准确，客观地识别页岩和矿石边界，并有可能替代当前的人工检测方法。

著录项

  • 来源
    《Iron ore 2011》|2011年|p.179-183|共5页
  • 会议地点 Perth(AU)
  • 作者

    K L Silversides; A Melkumyan; D A Wyman; P J Hatherly;

  • 作者单位

    The University of Sydney, Rose Street Building (J04), NSW 2006. Email: ksil8584@uni.sydney.edu.au;

    The University of Sydney, Rose Street Building (J04), NSW 2006. Email: a.melkumyan@usyd.edu.au;

    The University of Sydney, Madsen Building (F09), NSW 2006. Email: d.wyman@usyd.edu.au;

    The University of Sydney, Rose Street Building (J04), NSW 2006. Email: p.hatherly@usyd.edu.au;

  • 会议组织
  • 原文格式 PDF
  • 正文语种 eng
  • 中图分类 铁矿石;
  • 关键词

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