...
  • 主题
高级搜索  >
历史搜索 清空历史
首页> 外文期刊>Fuel >Explaining relationships between coke quality index and coal properties by Random Forest method
【24h】

Explaining relationships between coke quality index and coal properties by Random Forest method

机译：用随机森林法解释焦炭质量指标与煤性质的关系。

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

In this study was shown that random forest (RF) can be used as a sensible new data mining tool for variable importance measurements (VIMs) through various coal properties for prediction of coke quality (Free Swelling Index (FSI)). The VIMs of RF within coal analyses (proximate, ultimate, and petrographic analyses) were applied for the selection of the best predictors of FSI over a wide range of Kentucky coal samples. VIMs assisted by Pearson correlation through proximate, ultimate, and petrographic analyses indicated that volatile matter, carbon, vitrinite, and R-max (coal rank parameters) are the most effective variables for the prediction of FSI. These important predictors have been used as inputs of RF model for the FSI prediction. Outputs in the testing stage of the model indicated that RF can predict FSI quite satisfactorily; the R-2 was 0.93 and mean square error from actual FSIs was 0.15 (had less than interval unit of FSI; 0.5). According to the result, by providing nonlinear inter-dependence approximation among parameters for variable selection and also non-parametric predictive model RF can potentially be further employed as a reliable and accurate technique for the determination of complex relationship through fuel and energy investigations. (C) 2016 Elsevier Ltd. All rights reserved.
机译：在这项研究中，随机森林（RF）可以用作明智的新数据挖掘工具，用于通过各种煤炭特性预测焦炭质量（自由膨胀指数（FSI））进行可变重要性测量（VIM）。煤炭分析（近程分析，最终分析和岩相分析）中RF的VIM被用于选择肯塔基州各种煤炭样本中FSI的最佳预测因子。通过近，最终和岩石学分析得到的皮尔逊相关性辅助的VIM表明，挥发性物质，碳，镜质和R-max（煤阶参数）是预测FSI的最有效变量。这些重要的预测变量已用作FSI预测的RF模型的输入。在模型测试阶段的输出表明，RF可以非常令人满意地预测FSI。 R-2为0.93，实际FSI的均方误差为0.15（小于FSI的间隔单位； 0.5）。根据结果​​，通过为变量选择提供参数之间的非线性相互依存近似，并且非参数预测模型RF可以潜在地进一步用作通过燃料和能量调查确定复杂关系的可靠且准确的技术。 （C）2016 Elsevier Ltd.保留所有权利。

著录项

  • 来源
    《Fuel》 |2016年第15期|754-760|共7页
  • 作者

    Chelgani S. Chehreh; Matin S. S.; Hower James C.;

  • 作者单位

    Univ Michigan, Dept Elect Engn & Comp Sci, Ann Arbor, MI 48109 USA;

    Islamic Azad Univ, Sci & Res Branch, Environm & Energy Dept, Tehran, Iran;

    Univ Kentucky, Ctr Appl Energy Res, 2540 Res Pk Dr, Lexington, KY 40511 USA;

  • 收录信息 美国《科学引文索引》(SCI);美国《工程索引》(EI);
  • 原文格式 PDF
  • 正文语种 eng
  • 中图分类
  • 关键词

    Coke quality; Swelling index; Coal rank; Random forest; Variable importance;

    机译：焦炭质量;溶胀指数;煤级;随机森林;变量重要性;

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