DE-RF与模糊模型在热轧带钢板坯弯曲控制中的应用  

Application of DE-RF and Fuzzy Model in Camber Control of Hot Rolled Strip

作　　者：魏志鹏 崔桂梅[1] 皮理想 李天豪 WEI Zhipeng;CUI Guimei;PI Lixiang;LI Tianhao(School of Information Engineering,Inner Mongolia University of Science and Technology,Baotou 014010,China)

机构地区：[1]内蒙古科技大学信息工程学院,内蒙古包头014010

出　　处：《哈尔滨理工大学学报》2023年第2期51-58,共8页Journal of Harbin University of Science and Technology

基　　金：国家自然科学基金(61763039)。

摘　　要：针对某厂2 250 mm热轧带钢粗轧过程产生板坯弯曲影响带钢质量的问题,提出基于数据与专家经验融合的方法应用于板坯弯曲控制系统。首先建立差分进化算法优化随机森林模型解决板坯检测滞后预测精度不够问题,该模型有效预测第三道次粗轧出口板坯弯曲值,估计误差在允许范围内板坯比例为96.3%。然后根据专家经验与数据建立模糊模型解决人工操作不确定问题,该模型分别得到两次辊缝倾斜值,实验结果表明模糊模型的计算值与实际值误差较小,能可靠地提供辊缝倾斜值。最后将两次辊缝倾斜值相加作为第二道次辊缝倾斜值,仿真分析结果表明,该方法能有效降低板坯弯曲,具有实际指导意义。In order to solve the problem of slab bending affecting strip quality in 2250mm hot strip rolling process,a method based on data fusion and expert experience is proposed to apply to slab bending control system.Firstly,the differential evolution algorithm is established to optimize the stochastic forest regression model to solve the problem of insufficient accuracy of slab detection lag prediction.The model can effectively predict the bending value of the slab at the exit of the third pass roughing mill,and the estimated error is 96.3%of the slab within the allowable range.Then a fuzzy model is established according to the expert experience and data to solve the manual operation uncertainty problem.The model gets the roll slit tilt value twice respectively,and the experimental results show that the calculated value of the fuzzy model has a small error compared to the actual value and it can provide the roll gap tilt value reliably.Finally,the two roll gap tilt values are added together as the second roll gap tilt value.The simulation results show that the method can effectively reduce the bending of slab,which has practical guiding significance.

关 键 词：热轧粗轧 板坯弯曲 差分进化 随机森林 模糊模型 

分 类 号：TP399[自动化与计算机技术—计算机应用技术]