• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文会议>The First AusIMM International Geometallurgy Conference 2011. >Predicting Finished Product Properties in the Mining Industry from Pre-Extraction Data
【24h】

Predicting Finished Product Properties in the Mining Industry from Pre-Extraction Data

机译：根据预提取数据预测采矿业的成品属性

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

An essential requirement of product quality control in the mining industry is to be able to reliablyrnpredict key quality properties of fi nished product from the data available before the extraction ofrnthe ore. From a production viewpoint, the unit of data collection is generally the input and outputrndata set for each shift of crusher production, but could be any period where mine precrusher datarncan be reliably matched with product data.rnThis paper demonstrates that linear regression models can be used to predict crush grades fromrnblast grades, even where the crush material is blended from multiple sources or pits for each ofrnwhich differing regression models might apply. The advantage of using increasingly complexrnregressions models to match the available data to give increasingly more powerful models isrnexamined. The best model for any application will be a balance between required predictability,rnavailable data and the business’ tolerance for complex models.rnThe regression modelling approach has several advantages over the more classic method of runof-rnmine (ROM) crusher trials, which will be discussed.rnThe models can use any predictor variable such as grade, geotype and in situ density providedrnthe preextraction data set can be reliably matched with post-crusher data and is signifi cant as arnpredictor. The models have been used extensively in the generation of the daily crusher plan withrnthe aim of maintaining fi nished product grade. This approach has also been used associated withrnexploration drilling and long-term planning.rnIt is acknowledged that there are inherent problems in fi tting lump and fi nes grade to a linearrnmodel. However, these problems are minor when they are used for interpolation within thernwindow spanned by the shift blend records used to produce the model. This paper discusses somernof the issues limiting linear regression models in this application, and suggests methods enablingrnconsistent models to be formulated.
机译：采矿业产品质量控制的一项基本要求是能够从提取矿石之前的可用数据中可靠地预测成品的关键质量特性。从生产的角度来看，数据收集的单位通常是破碎机生产的每个班次的输入和输出数据集，但是可以是矿山预破碎机数据可以与产品数据可靠匹配的任何时期。本文证明了可以使用线性回归模型从爆破品级预测压碎品级，即使对于每种碎料从多种来源或矿坑进行混合的情况下，也可能适用不同的回归模型。研究了使用越来越复杂的回归模型来匹配可用数据以提供越来越强大的模型的优势。对于任何应用程序来说，最佳模型都是在所需的可预测性，可用数据与企业对复杂模型的容忍度之间取得平衡。rn回归建模方法具有比传统的runner-rnmine（ROM）破碎机试验更为经典的方法，该方法具有以下几个优点：该模型可以使用任何预测变量，例如坡度，地理类型和原位密度，前提是提取前的数据集可以与破碎机后的数据可靠地匹配，并且对于预测者而言意义重大。该模型已广泛用于每日破碎机计划的生成中，目的是保持成品等级。这种方法也已与勘探钻探和长期计划结合使用。公认的是，将块和细度分级拟合到线性模型存在固有的问题。但是，当这些问题用于在窗口中进行插值时，这些问题很小，这些窗口由用于生成模型的班次混合记录跨越。本文讨论了限制此应用程序中的线性回归模型的问题，并提出了能够建立一致模型的方法。

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