基于PSO和CBR优化粒度的磨矿过程设定控制

发布时间：2018-10-24 19:47

【摘要】：磨矿产品粒度直接关系到选矿厂的金属回收率、精矿品位等技术指标,针对磨矿过程滞后时间长、参数时变严重、强非线性、强耦合等特性,采用案例推理技术(CBR)实现磨矿粒度优化。相似度计算是CBR中案例检索的关键环节,直接关系到案例检索的精度。传统采用欧式距离计算相似度的方法,通常假设案例各属性的权重固定且相互独立,而该假设往往不能满足实际应用。针对此问题,提出一种基于粒子群优化算法(PSO)的自学习相似度计算方法,并将其引入案例推理中,构成粒度指标智能优化设定系统,并联合常规的基础控制系统,构建了磨矿过程优化设定控制系统,保证磨矿过程整体优化稳定运行。应用到某大型选矿厂的磨矿流程,取得了明显成效,具有推广应用价值。
[Abstract]:The granularity of grinding products is directly related to the technical indexes such as metal recovery, concentrate grade and so on. Aiming at the characteristics of grinding process, such as long lag time, serious time-varying parameters, strong nonlinearity and strong coupling, etc. The CBR technology (CBR) is used to optimize the grinding granularity. Similarity calculation is the key link of case retrieval in CBR, which is directly related to the accuracy of case retrieval. The traditional Euclidean distance method for similarity calculation usually assumes that the weight of each attribute is fixed and independent of each other, but the assumption can not meet the practical application. In order to solve this problem, a self-learning similarity calculation method based on particle swarm optimization (PSO) algorithm is proposed, and it is introduced into Case-Based reasoning (CBR) to form an intelligent optimization system for granularity index, and to combine with the conventional basic control system. The optimal setting control system of grinding process is constructed to ensure the whole optimum and stable operation of grinding process. The grinding process applied to a large concentrator has achieved remarkable results and is worth popularizing and applying.
【作者单位】：周口师范学院机械与电气工程学院;周口师范学院物理与电信工程学院;
【基金】：国家自然科学基金(11547227) 河南省自然科学基金(152300410134) 河南省科技攻关计划项目(132102210179.132102210577,142102210599) 高校微课教学活动在网络学习空间中的实效研究(15A880023) 河南省教育技术装备和实践教育研究项目(GZS310)
【分类号】：TD921.4;TP18

【相似文献】