正在加载图片...
工程科学学报.第42卷,第6期:787-795.2020年6月 Chinese Journal of Engineering,Vol.42,No.6:787-795,June 2020 https://doi.org/10.13374/j.issn2095-9389.2019.08.26.001;http://cje.ustb.edu.cn 基于Copula函数的热轧支持辊健康状态预测模型 李天伦”,何安瑞,邵健)四,付文鹏2,强毅),谢向群 1)北京科技大学工程技术研究院.北京1000832)上海梅山钢铁股份有限公司热轧厂,南京2100393)机械科学研究总院,北京100044 ☒通信作者,E-mail:jianshao @ustb.edu.cn 摘要热轧支持辊的健康状态在带钢板形质量和轧制稳定性控制中起着关键作用,非线性、强耦合、少样本等特点使得热 轧支持辊健康状态的预测复杂,目前各大钢厂仍以定期维护和事后维修为主.本文提出了一种支持辊虚拟健康指数的构建 方法以及基于Copula函数的复杂工况健康状态预测模型.首先结合支持辊弯窜辊数据表征支持辊健康状态,再使用K- meas聚类方法对支持辊工况进行划分,将各工况下过程数据分别构建Copula预测模型,最后根据实际轧制计划的排布顺序 融合各工况模型的预测结果.提出的基于Copula函数的预测模型在某钢厂I780热连轧产线得到应用,结果表明,该模型能 够准确有效的按照轧制计划实现支持辊的健康状态预测,以更科学的策略指导支持辊更换维护 关键词支持辊:健康状态预测:Copula函数:数据驱动:板形 分类号TG333.7 Copula-based model for hot-rolling back-up roll health prediction LI Tian-lun,HE An-rui,SHAO Jian.FU Wen-peng.QIANG Yi.XIE Xiang-qun 1)Institute of Engineering Technology,University of Science and Technology Beijing,Beijing 100083,China 2)Hot Rolling Plant,Meishan Iron Steel Co.Ltd.,Nanjing 210039,China 3)China Academy of Machinery Science and Technology,Beijing 100044,China Corresponding author,E-mail:jianshao @ustb.edu.cn ABSTRACT The health condition of hot-rolling back-up rolls plays a key role in controlling the strip profile quality and rolling stability.The characteristics of nonlinearity,strong coupling,and the use of limited samples complicate the prediction of the back-up roll health state.The current back-up roll replacement strategy of each steel mill is generally determined according to a certain rolling time or rolling kilometer,and such a maintenance mode is based on experience.In actual experience,due to different strip specifications in each rolling cycle,the degrees of wear on the back-up rolls are different.Regular maintenance methods may easily lead to excessive wear of the back-up rolls and reduce the quality of the strip shape at the end of the unit,or premature roll replacement wastes the back-up roll performance.This paper proposed a construction method for the back-up roll virtual health index and a Copula function-based model for predicting the health condition of complex working conditions.The health condition of a pair of back-up rolls was characterized by combining roll bending and shifting data,and the back-up roll condition was divided by the K-means clustering method.The Copula prediction model was constructed using the process data under each working condition,and finally,according to the actual rolling schedule,the arrangement order combines the prediction results of the working conditions.The production performance data of a 1780- mm hot rolling line were used to verify the results.The results show that the proposed Copula-based prediction model can accurately and effectively predict the health condition of the back-up roll according to the rolling schedule;thus,it can serve as the basis of a more scientific strategy to guide the replacement and maintenance of the back-up roll. KEY WORDS back-up roll;health prognostics;Copula function;data-driven;profile and flatness 收稿日期:2019-08-26 基金项目:国家自然科学基金资助项目(51674028):创新方法专项资助项目(2016M010300)基于 Copula 函数的热轧支持辊健康状态预测模型 李天伦1),何安瑞1),邵    健1) 苣,付文鹏2),强    毅3),谢向群2) 1) 北京科技大学工程技术研究院,北京 100083    2) 上海梅山钢铁股份有限公司热轧厂,南京 210039    3) 机械科学研究总院,北京 100044 苣通信作者,E-mail:jianshao@ustb.edu.cn 摘    要    热轧支持辊的健康状态在带钢板形质量和轧制稳定性控制中起着关键作用,非线性、强耦合、少样本等特点使得热 轧支持辊健康状态的预测复杂,目前各大钢厂仍以定期维护和事后维修为主. 本文提出了一种支持辊虚拟健康指数的构建 方法以及基于 Copula 函数的复杂工况健康状态预测模型. 首先结合支持辊弯窜辊数据表征支持辊健康状态,再使用 K￾means 聚类方法对支持辊工况进行划分,将各工况下过程数据分别构建 Copula 预测模型,最后根据实际轧制计划的排布顺序 融合各工况模型的预测结果. 提出的基于 Copula 函数的预测模型在某钢厂 1780 热连轧产线得到应用,结果表明,该模型能 够准确有效的按照轧制计划实现支持辊的健康状态预测,以更科学的策略指导支持辊更换维护. 关键词    支持辊;健康状态预测;Copula 函数;数据驱动;板形 分类号    TG333.7 Copula-based model for hot-rolling back-up roll health prediction LI Tian-lun1) ,HE An-rui1) ,SHAO Jian1) 苣 ,FU Wen-peng2) ,QIANG Yi3) ,XIE Xiang-qun2) 1) Institute of Engineering Technology, University of Science and Technology Beijing, Beijing 100083, China 2) Hot Rolling Plant, Meishan Iron & Steel Co. Ltd., Nanjing 210039, China 3) China Academy of Machinery Science and Technology, Beijing 100044, China 苣 Corresponding author, E-mail: jianshao@ustb.edu.cn ABSTRACT    The  health  condition  of  hot-rolling  back-up  rolls  plays  a  key  role  in  controlling  the  strip  profile  quality  and  rolling stability. The characteristics of nonlinearity, strong coupling, and the use of limited samples complicate the prediction of the back-up roll health state. The current back-up roll replacement strategy of each steel mill is generally determined according to a certain rolling time or rolling kilometer, and such a maintenance mode is based on experience. In actual experience, due to different strip specifications in each rolling cycle, the degrees of wear on the back-up rolls are different. Regular maintenance methods may easily lead to excessive wear of the back-up rolls and reduce the quality of the strip shape at the end of the unit, or premature roll replacement wastes the back-up roll performance. This paper proposed a construction method for the back-up roll virtual health index and a Copula function–based model for predicting  the  health  condition  of  complex  working  conditions.  The  health  condition  of  a  pair  of  back-up  rolls  was  characterized  by combining roll bending and shifting data, and the back-up roll condition was divided by the K-means clustering method. The Copula prediction  model  was  constructed  using  the  process  data  under  each  working  condition,  and  finally,  according  to  the  actual  rolling schedule, the arrangement order combines the prediction results of the working conditions. The production performance data of a 1780- mm hot rolling line were used to verify the results. The results show that the proposed Copula-based prediction model can accurately and effectively predict the health condition of the back-up roll according to the rolling schedule; thus, it can serve as the basis of a more scientific strategy to guide the replacement and maintenance of the back-up roll. KEY WORDS    back-up roll;health prognostics;Copula function;data-driven;profile and flatness 收稿日期: 2019−08−26 基金项目: 国家自然科学基金资助项目 (51674028);创新方法专项资助项目(2016IM010300) 工程科学学报,第 42 卷,第 6 期:787−795,2020 年 6 月 Chinese Journal of Engineering, Vol. 42, No. 6: 787−795, June 2020 https://doi.org/10.13374/j.issn2095-9389.2019.08.26.001; http://cje.ustb.edu.cn
<<向上翻页向下翻页>>
©2008-现在 cucdc.com 高等教育资讯网 版权所有