摘要
针对反浮选过程中浮选槽液位指标难以建立精确的数学模型、常规检测方法不能有效控制问题,提出一种将粗糙集与BP神经网络理论相结合方法[1],建立反浮选液位软测量模型。从浮选过程积累的数据中获取过程知识,通过粗糙集属性约简对训练样本数据进行处理,根据结果确定BP网络的输入、输出、隐层神经元数,从得到的优化设定自动更新浮选槽液位控制回路的设定值,避免了人工控制的不稳定性和不精确性。此方法应用于某浮选厂,满足了液位预测要求的精度,在液位控制、经济指标提高及浮选过程稳定等方面取得了明显的效果。
Anti-flotation process for the flotation level indicator is difficult to establish an accurate mathematical model,and the conventional method of detection and control is difficult to control.A new recovery prediction method based on rough set theory with the combination of BP neural network is proposed in this paper.The experience of flotation process can be grasped more profoundly from lots of historical process data,the sample data is processed by rough set attribute reduction,which determines the input,output,hidden layer neurons of BP network.We also automatic updates the set values of control loop in flotation cell liquid level,which avoids the instability and non-precision of manual methods.This approach has been successfully applied to a flotation process in a mineral processing plant and achieved remarkable results in the liquid level control,economic indicators and the flotation process to improve stability.
出处
《辽宁科技大学学报》
CAS
2010年第5期525-529,共5页
Journal of University of Science and Technology Liaoning
基金
辽宁省高校创新团队支持计划项目(2008T091)
关键词
浮选槽液位
粗糙集
BP神经网络
模型预测
flotation cell liquid level
rough sets
BP neural network
model prediction
