摘要
为满足原煤煤质变化对重介质悬浮液密度大范围调节的需求,在重介质分选过程中采用反分流工艺,设计了一种重介质悬浮液密度宽域智能控制系统。利用BP神经网络建立了合格介质桶液位预测模型,以悬浮液密度实际值与设定值的偏差、合格介质桶液位实际值、分流阀开度及补水阀开度作为模型输入变量,经模型计算得出合格介质桶液位预测值;依据合格介质桶液位偏差与密度偏差,通过基于支持向量机的一对一多分类算法实现加介质、稳态、密度阶跃上升、密度阶跃下降控制模式切换,并依据控制模式自动调整分流阀、补水阀、加水阀开度及浓介质泵、反分流泵开启时间,从而实现密度大范围调节。该系统应用后密度波动范围稳定在±0.005g/cm~3,密度调节时间短。
In order to meet demand of adjusting dense medium suspension density in wide range due to change of raw coal quality,an intelligent control system for dense medium suspension density with wide domain was designed by using reverse split technology in dense medium separation process.BP neural network is used to establish liquid level prediction model of qualified medium barrel.Deviation between actual value and set value of suspension density,actual liquid level of qualified medium barrel and opening degree of shunt valve and water replenished valve are taken as input variables of the model,and predicted liquid level of qualified medium barrel is calculated through the model.According to liquid level deviation of qualified medium barrel and the density deviation,control mode switching of adding medium,steady state,density step up and density step down is realized through one-to-one multi-classification algorithm based on support vector machine.Opening degree of shunt valve,water replenished valve and water adding valve and opening time of thick medium pump and reverse shunt pump are automatically adjusted according to control mode,so as to realize wide range adjustment of density.Density fluctuation range is stable within±0.005 g/cm~3 and density adjustment time is short after application of the system.
引文
[1]刘彦丽,樊民强.从煤矸石中回收煤系高岭岩的重介分选技术[J].中国矿业,2017,26(10):142-145.LIU Yanli,FAN Minqiang.Separation of coal bearing kaolinite using dense medium cyclone[J].China Mining Magazine,2017,26(10):142-145.
[2]周明磊,张德鹏.原煤的可选性及其入洗可行性分析[J].煤矿安全,2012,43(5):173-177.ZHOU Minglei,ZHANG Depeng.Feasibility analysis of raw coal washability and its washing[J].Safety in Coal Mines,2012,43(5):173-177.
[3]孔繁苗,徐康,陈浙锐,等.基于模糊控制的重介质悬浮液密度控制方法[J].工矿自动化,2018,44(6):101-104.KONG Fanmiao,XU Kang,CHEN Zherui,et al.Density control method for dense-medium suspension based on fuzzy control[J].Industry and Mine Automation,2018,44(6):101-104.
[4]郭西进,邵宏清,杨春宝,等.重介悬浮液密度与液位PFC-PID控制算法研究[J].工矿自动化,2018,44(1):89-95.GUO Xijin,SHAO Hongqing,YANG Chunbao,et al.Research on PFC-PID control algorithm of density and liquid level in heavy medium suspension[J].Industry and Mine Automation,2018,44(1):89-95.
[5]薛东彪,杨洁明.QP-DMC算法在重介液密度控制中的应用[J].机械设计与制造,2017(4):169-172.XUE Dongbiao,YANG Jieming.Application of QPDMC algorithm in the heavy medium suspension density control system[J].Machinery Design &Manufacture,2017(4):169-172.
[6]赵春祥,叶桂森.重介质选煤过程控制模型及控制算法的研究[J].煤炭学报,2000,25(增刊1):196-200.ZHAO Chunxiang,YE Guisen.Study of heavy medium coal preparation process control model and control algorithm[J].Journal of China Coal Society,2000,25(S1):196-200.
[7]董志勇,王然风,樊民强,等.重介分选过程分流自动控制系统设计[J].工矿自动化,2017,43(7):23-27.DONG Zhiyong,WANG Ranfeng,FAN Minqiang,et al.Design of automatic shunt control system in dense-medium separation process[J].Industry and Mine Automation,2017,43(7):23-27.
[8]李停.基于无模型自适应的重介悬浮液密度控制[D].徐州:中国矿业大学,2016.
[9]曹珍贯.重介选煤过程中重介质的密度预测控制研究[D].徐州:中国矿业大学,2014.
[10]付翔.重介选煤灰分自动控制系统的设计与实现[D].太原:太原理工大学,2012.
[11]王波,张致维,王然风.重介悬浮液密度自动控制系统的设计[J].控制工程,2011,18(增刊1):67-69.WANG Bo,ZHANG Zhiwei,WANG Ranfeng.Design of automation system for heavy medium suspension[J].Control Engineering of China,2011,18(S1):67-69.
[12]郭西进,高警卫,岳广礼,等.重介选煤工艺多参数模糊控制方法研究[J].工矿自动化,2012,38(9):1-4.GUO Xijin,GAO Jingwei,YUE Guangli,et al.Research of fuzzy control method for multi-parameter in dense-medium separation process[J].Industry and Mine Automation,2012,38(9):1-4.
[13]王功鹏,段萌,牛常勇.基于卷积神经网络的随机梯度下降算法[J].计算机工程与设计,2018,39(2):441-445.WANG Gongpeng,DUAN Meng,NIU Changyong.Stochastic gradient descent algorithm based on convolution neural network[J].Computer Engineering and Design,2018,39(2):441-445.
[14]张晋晶.基于随机梯度下降的神经网络权重优化算法[D].重庆:西南大学,2018.
[15]梁斌昌,赵建章,田树丹,等.基于BP神经网络的循环介质密度控制系统设计[J].选煤技术,2017(2):62-66.LIANG Binchang,ZHAO Jianzhang,TIAN Shudan,et al.Design of circulating medium density control system based on BP neural network[J].Coal Preparation Technology,2017(2):62-66.
[16]张智焕,王树青.基于多模型切换的大范围预测函数控制[J].浙江大学学报(工学版),2002,36(3):290-292.ZHANG Zhihuan,WANG Shuqing.Global predictive function control based on the switching of multiple models[J]. Journal of Zhejiang University(Engineering Science),2002,36(3):290-292.
[17]荆双喜,华伟.基于小波-支持向量机的矿用通风机故障诊断[J].煤炭学报,2007,32(1):98-102.JING Shuangxi,HUA Wei.The mine ventilator fault diagnosis based on wavelet packet and support vector machine[J].Journal of China Coal Society,2007,32(1):98-102.