摘要
由于电石冶炼过程存在较大的滞后性,当预判错误或操作延迟,容易出现电流波动,会影响生产效率,损害电石炉。基于采集的某厂电石炉的大量现场数据,利用极限学习算法建立该电石炉的系统模型。基于现场操作经验,利用模糊迭代学习控制设计针对该电石炉的电极控制策略。
The large hysteresis in calcium carbide smelting and the misjudgment or operation delay easily causes current fluctuation and may affect the production efficiency or brings damage to the calcium carbide furnaces. In this paper, basing on a large number of data of calcium carbide furnace collected in a factory, the extreme learning algorithm was adopted to establish the model of calcium carbide furnace system, including having the experience of field operation based and the fuzzy iterative learning control used to design an electrode control strategy for the calcium carbide furnace.
引文
[1] 李磊,毛志忠.基于近似模型的电弧炉解耦控制器[J].控制理论与应用,2013,30(1):101~110.
[2] Odenthal H J,Kemminger A,Krause F,et al.Review on Modeling and Simulation of the Electric Arc Furnace(EAF)[J].Steel Research International,2018,89(1):1700098.
[3] Chang G W,Chen C I,Liu Y J.A Neural-Network-Based Method of Modeling Electric Arc Furnace Load for Power Engineering Study[J].IEEE Transactions on Power Systems,2010,25(1):138~146.
[4] 张恺伦,陈宏伟,江全元.电弧炉负荷的三相综合建模与参数辨识[J].电力系统保护与控制,2012,40(16):77~82.
[5] Huang G B,Zhu Q Y,Siew C K.Extreme Learning Machine:Theory and Applications[J].Neuro Computing,2006,70(1-3):489~501.
[6] Huang G B,Chen L.Enhanced Random Search Based Incremental Extreme Learning Machine[J].Neuro Computing,2008,71(16-18):3460~3468.
[7] Lozynskyy O,Lozynskyy A,Paranchuk Y,et al.Analysis and Synthesis of Intelligent System for Electric Mode Control in Electric Arc Furnace[J].Analysis and Simulation of Electrical and Computer Systems,2018,452:111~130.
[8] 张豫川.浅述新一代电弧炉电极调节智能控制系统的开发[J].工业加热,2017,46(4):70~72.
[9] Ghiormez L,Prostean O,Filip I,et al.Fuzzy Logic Control Strategy for a Three-Phase Electric Arc Furnace[J].Soft Computing Applications,2016,634:253~264.
[10] 刘超.迭代学习控制原理浅述[J].智慧工厂,2017,(12):78~79.
[11] 王坤.综合智能控制策略在电弧炉控制中的应用[J].科技与企业,2015,(13):206.
[12] 范其明.电渣炉的模糊迭代学习控制研究[D].沈阳:东北大学,2011.