基于PSO-LSSVM的煤泥浮选药剂自动添加系统研究  

Research on automatic dosing system for coal slime flotation based on PSO-LSSVM

作　　者：董志勇[1] 王然风[1] 樊民强[1] 付翔[1] 

机构地区：[1]太原理工大学矿业工程学院,山西太原030024

出　　处：《煤炭工程》2017年第2期117-120,共4页Coal Engineering

基　　金：国家自然科学基金资助项目(50974094)

摘　　要：针对煤泥浮选过程手动加药存在加药方式粗放、随意性较强、药剂消耗大、工人劳动强度高等问题,提出了一种基于最小二乘支持向量机(LS-SVM)的浮选药剂量预测及自动添加方法。选择煤泥浮选过程主要过程变量作为模型输入变量,药剂添加量作为输出变量,建立了一个基于LSSVM的多输入多输出模型,同时利用粒子群算法(PSO)对模型内部参数进行优化选择,并进行了仿真验证。应用效果表明:在保证产品质量情况下,系统能够有效地降低药剂消耗,其中捕收剂消耗量降低了13.73%,起泡剂消耗量降低了12.67%,应用效果良好。Aiming at the problems caused by manual dosing in coal slime flotation, such as randomness of dosing, high reagent consumption and high labor intensity of workers. In this paper, a new method based on least square support vector machine （LS-SVM） for the predictive control of flotation reagents addition is proposed. The main process variables are selected as the input variables of the LS-SVM model, the reagents dosage are the output variables. Meanwhile, the particle swarm optimization algorithm （PSO） is used to optimize the internal parameters of the model and the simulation is carried out. The application in Hongtong Coal Preparation Plant shows that, under the premise of ensuring the product quality, the system can effectively reduce the reagent consumption, in which the collector consumption is reduced by 13.73%, Frother consumption is reduced by 12. 67%. The favorable performance is achieved.

关 键 词：煤泥浮选 自动加药 最小二乘支持向量机 粒子群优化算法 

分 类 号：TD94[矿业工程—选矿]