热连轧多加热炉设定模型自学习参数计算及优化  

Calculation and optimization of self-learning parameters of set models in multi-heating furnace for hot strip mill

作　　者：奚小玲[1] 周新亮 吴胜田 

机构地区：[1]辽宁科技大学应用技术学院,辽宁鞍山114011 [2]鞍山钢铁集团有限公司

出　　处：《冶金自动化》2014年第2期71-75,共5页Metallurgical Industry Automation

摘　　要：在有多座加热炉的热连轧生产线中,加热炉之间存在较大的工况差异,给产品精度和生产的稳定性带来不利影响。为有效解决上述问题,笔者提出对热连轧设定模型自学习参数分炉进行计算,并采用指数平滑法平滑震荡的参数,在上述基础上对不同的自学习参数分别采用长遗传、短遗传方法进行优化处理。实践证明,采用该方法后,针对不同产品规格和不同工艺制度,过程控制系统能够按照加热炉进行很好的自适应,提高了产品精度。In the hot rolling production process,there is a big difference between the multi-heating furnace operating conditions,which may adversely affect the accuracy and stability of the production. To effectively solve the above problems, self-learning parameters are proposed for setting model in multi-heating furnace for hot strip mill. The oscillating parameters are smoothed with exponential smoothing method. Then the different self-learning parameters are optimized with genetic method. Practice has proved that the proposed control system could be well adapted to the different specifica-tions and different process system for heating furnace. The accuracy of the production is improved.

关 键 词：热连轧 过程计算机控制系统 设定模型 自学习 

分 类 号：TG333[金属学及工艺—金属压力加工]