摘要
浮选过程关键工艺指标精矿品位和尾矿品位难于在线测量,且与控制回路输出之间的动态特性具有如下综合复杂性:强非线性、强耦合,难以用精确的数学模型描述,随生产边界条件而变化,因此采用传统的基于数学模型的优化控制方法难以保证品位指标在合格的范围内.通过将基于案例推理的预设定模型与基于RBF神经网络的软测量模型以及基于规则推理的前馈、反馈补偿模型相结合,实现了在工况发生变化时对磁铁矿浮选过程设定值的优化控制.该方法成功应用于某选矿厂浮选过程,应用效果表明了该方法的有效性.
In the flotation process, the concentrate grade and the tailing grade are crucial technical indices which reflect the product quality and efficiency. There are strong nonlinearity and uncertainties in such technical indices dynamic behaviors, which can hardly be described accurately with mathematical models. The technical indices which cannot be measured online continuously vary with boundary conditions. Therefore conventional control methods are incapable of keeping the actual concentrate grade and tailing grade within their target ranges. An intelligent control method comprised of a pre-setting model based on the case-based reasoning （CBR） method, a feedback compensator and a feed forward compensator based on the rule-based reasoning （RBR） method, and a soft sensors using RBF neural network was presented. The approach proposed has successfully been applied to the flotation process of a hematite ore processing plant, and its effectiveness is proved evidently.
出处
《东北大学学报（自然科学版）》
EI
CAS
CSCD
北大核心
2012年第1期1-5,共5页
Journal of Northeastern University(Natural Science)
基金
国家重大基础研究发展计划项目(2009CB320604)
关键词
优化设定
案例推理
规则推理
工艺指标
软测量
神经网络
optimal index setting
case-based reasoning
rule-based reasoning
techniques indices
soft sensor
neural network
