首页> 外文期刊>IFAC PapersOnLine >Data-driven Extraction Method of Belief Rule for Reagent Addition in Antimony Rougher Flotation
【24h】

Data-driven Extraction Method of Belief Rule for Reagent Addition in Antimony Rougher Flotation

机译:锑粗选浮选试剂信度规则的数据驱动提取方法

获取原文
           

摘要

For the problem of reagent addition control in antimony rougher flotation, belief rule base (BRB) method can be adopted to express the human knowledge and to address the uncertainty in the operator experience and historical data. However, it is difficult to efficiently establish a valid initial BRB even with the assistance of experienced operators. To address this issue, this paper proposes a data-driven approach to directly extract the belief rules of reagent addition from sample data. In this approach, a novel state transition algorithm-based fuzzy c-means clustering algorithm (STAFCM) is designed for clustering of the sample data. Then the obtained fuzzy clustering centers are adopted in an extended belief rule base (EBRB) method to generate the belief rules, rather than the manually selected samples utilized in original EBRB method. The generated reagent addition rule can be then applied in antimony rougher floatation to replace the labor-intensive and arbitrary manual operations.
机译:对于锑粗浮中试剂添加控制的问题,可以采用信念规则库(BRB)方法来表达人类的知识并解决操作者经验和历史数据中的不确定性。但是,即使在有经验的操作员的协助下,也很难有效地建立有效的初始BRB。为了解决这个问题,本文提出了一种数据驱动的方法,可以直接从样品数据中提取试剂添加的置信度规则。在这种方法中,针对样本数据的聚类设计了一种新颖的基于状态转移算法的模糊c均值聚类算法(STAFCM)。然后,将获得的模糊聚类中心用于扩展置信规则库(EBRB)方法中,以生成置信规则,而不是原始EBRB方法中人工选择的样本。然后可以将生成的试剂添加规则应用到锑的粗浮中,以替代劳动强度大的任意手动操作。

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