• 《工程索引》(EI)刊源期刊
  • 综合性科学技术类中文核心期刊
  • 中国科技论文统计源期刊
  • 中国科学引文数据库来源期刊

留言板

尊敬的读者、作者、审稿人, 关于本刊的投稿、审稿、编辑和出版的任何问题, 您可以本页添加留言。我们将尽快给您答复。谢谢您的支持!

姓名
邮箱
手机号码
标题
留言内容
验证码

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 付文鹏 强毅 谢向群

李天伦, 何安瑞, 邵健, 付文鹏, 强毅, 谢向群. 基于Copula函数的热轧支持辊健康状态预测模型[J]. 工程科学学报, 2020, 42(6): 787-795. doi: 10.13374/j.issn2095-9389.2019.08.26.001
引用本文: 李天伦, 何安瑞, 邵健, 付文鹏, 强毅, 谢向群. 基于Copula函数的热轧支持辊健康状态预测模型[J]. 工程科学学报, 2020, 42(6): 787-795. doi: 10.13374/j.issn2095-9389.2019.08.26.001
LI Tian-lun, HE An-rui, SHAO Jian, FU Wen-peng, QIANG Yi, XIE Xiang-qun. Copula-based model for hot-rolling back-up roll health prediction[J]. Chinese Journal of Engineering, 2020, 42(6): 787-795. doi: 10.13374/j.issn2095-9389.2019.08.26.001
Citation: LI Tian-lun, HE An-rui, SHAO Jian, FU Wen-peng, QIANG Yi, XIE Xiang-qun. Copula-based model for hot-rolling back-up roll health prediction[J]. Chinese Journal of Engineering, 2020, 42(6): 787-795. doi: 10.13374/j.issn2095-9389.2019.08.26.001

基于Copula函数的热轧支持辊健康状态预测模型

doi: 10.13374/j.issn2095-9389.2019.08.26.001
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)
详细信息
    通讯作者:

    E-mail:jianshao@ustb.edu.cn

  • 中图分类号: TG333.7

Copula-based model for hot-rolling back-up roll health prediction

More Information
  • 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。
  • 图  1  F7机架VHI数据(1#)表现出随轧制计划推进而上升的趋势

    Figure  1.  Rising trend of F7 stand VHI data (1#) with the rolling schedule

    图  2  K-means聚类结果示意图

    Figure  2.  K-means clustering results

    图  3  原始数据统一聚类后1#数据−工况1效果图

    Figure  3.  Working condition 1 of 1# data after clustering

    图  4  工况1支持辊VHI数据拟合降噪后结果示意图

    Figure  4.  Result of noise reduction after fitting VHI data of working condition 1

    图  5  使用Copula函数预测支持辊健康状态的建模流程图

    Figure  5.  Flow chart for predicting the health of back-up roll using Copula function

    图  6  对单工况训练集数据划分退化等级示意图

    Figure  6.  Data degradation level for single-working-condition training set

    图  7  处于不同退化等级下的分布模型适用于不同类型的Copula函数描述。(a)T12-T50, Gumbel; (b) T26T50, Frank; (c) T46T50, Clayton

    Figure  7.  Distribution models at different degradation levels fit for different types of Copula function descriptions: (a) T12T50, Gumbel; (b) T26T50, Frank; (c) T46T50, Clayton

    图  8  提高模型适应性的平移处理。(a)过早失效时Copula模型无法预测;(b)Copula模型平移

    Figure  8.  Translation processing to improve model adaptability: (a) Copula model is unpredictable at premature failure; (b) translation of copula model

    图  9  单工况VHI预测结果

    Figure  9.  Single-condition VHI prediction result

    图  10  经过VHI变尺度处理的单工况预测结果

    Figure  10.  Single-condition VHI prediction result after scale conversion

    图  11  融合预测结果示意图

    Figure  11.  Fusion prediction result diagram

    表  1  某钢厂1780热连轧产线F7机架支持辊使用情况统计

    Table  1.   Statistics on the use of F7 back-up roll in a 1780 hot rolling line

    Data numberTotal number of rolled stripsTotal rolling weight/tTotal rolling length /km
    1#1501633600012015
    2#1602435600013216
    3#1765438890015015
    4#1416830800012282
    5#1629136230013596
    下载: 导出CSV

    表  2  复杂工况下Copula模型融合预测结果

    Table  2.   Copula model fusion prediction results under complex conditions

    Test set numberActual number of rolled stripsActual VHIPredict VHIModel error/%
    5#162910.7260.7695.85
    4#141680.8310.758−8.74
    3#176540.9090.9767.34
    2#160240.8250.8624.42
    1#150160.8910.815−8.54
    下载: 导出CSV
  • [1] 沈一鸣. 宝钢支撑辊的使用技术. 轧钢, 2004, 21(1):55 doi: 10.3969/j.issn.1003-9996.2004.01.018

    Shen Y M. Introduction of application technology of backup roll in Baosteel. Steel Roll, 2004, 21(1): 55 doi: 10.3969/j.issn.1003-9996.2004.01.018
    [2] 何安瑞, 张清东, 曹建国, 等. 宽带钢热轧支持辊辊形变化对板形的影响. 北京科技大学学报, 1999, 21(6):565 doi: 10.3321/j.issn:1001-053X.1999.06.015

    He A R, Zhang Q D, Cao J G, et al. Effect of back-up roll profile in hot wide strip mill on the strip profile and flatness. J Univ Sci Technol Beijing, 1999, 21(6): 565 doi: 10.3321/j.issn:1001-053X.1999.06.015
    [3] 李子文, 高少华, 韩立伟, 等. 承钢1780节约支撑辊换辊时间//第十届中国钢铁年会暨第六届宝钢学术年会论文集. 上海, 2015: 623

    Li Z W, Gao S H, Han L W, et al. Chenggang Company 1780 save backup roll roll change time // Proceedings of the 10th CSM Steel Congress & the 6th Baosteel Biennial Academic Conference. Shanghai, 2015: 623
    [4] 史志勇, 荆涛, 董宝权, 等. 结合热轧机组特点合理使用支撑辊//第八届中国钢铁年会论文集. 北京, 2011: 2882

    Shi Z Y, Jing T, Dong B Q, et al. Application optimization of BUR according to the mill features // 2011 CSM Annual Meeting Proceedings. Beijing, 2011: 2882
    [5] Alford L D. The problem with aviation COTS. IEEE Aerosp Electron Syst Mag, 2001, 16(2): 33 doi: 10.1109/62.904242
    [6] Gartner D L, Dibbert S E. Application of integrated diagnostic process to non-avionics systems // 2001 IEEE Autotestcon Proceedings. IEEE Systems Readiness Technology Conference. Valley Forge, 2001: 229
    [7] 彭宇, 刘大同, 彭喜元. 故障预测与健康管理技术综述. 电子测量与仪器学报, 2010, 24(1):1 doi: 10.3724/SP.J.1187.2010.00001

    Peng Y, Liu D T, Peng X Y. A review: prognostics and health management. J Electron Meas Instrum, 2010, 24(1): 1 doi: 10.3724/SP.J.1187.2010.00001
    [8] 马飒飒, 许爱华, 张群兴, 等. 无人机安全监控与健康管理系统研究. 航空维修与工程, 2009(4):63 doi: 10.3969/j.issn.1672-0989.2009.04.027

    Ma S S, Xu A H, Zhang Q X, et al. The security monitoring and health management system for UAV. Aviat Mainten Eng, 2009(4): 63 doi: 10.3969/j.issn.1672-0989.2009.04.027
    [9] 杨立峰, 王亮, 冯佳晨. 基于PHM技术的导弹维修保障. 海军航空工程学院学报, 2010, 25(4):447 doi: 10.3969/j.issn.1673-1522.2010.04.020

    Yang L F, Wang L, Feng J C. Maintenance support of missile based on PHM technology. J Naval Aeron Astron Univ, 2010, 25(4): 447 doi: 10.3969/j.issn.1673-1522.2010.04.020
    [10] 张东, 冯志鹏. 基于变分模式分解和微积分增强能量算子的滚动轴承故障诊断. 工程科学学报, 2016, 38(9):1327

    Zhang D, Feng Z P. Fault diagnosis of rolling bearings based on variational mode decomposition and calculus enhanced energy operator. Chin J Eng, 2016, 38(9): 1327
    [11] 刘永兵, 周亚凯, 冯志鹏. 形态分量分析在滚动轴承故障诊断中的应用. 工程科学学报, 2017, 39(6):909

    Liu Y B, Zhou Y K, Feng Z P. Application of morphological component analysis for rolling element bearing fault diagnosis. Chin J Eng, 2017, 39(6): 909
    [12] 张景玲, 杨建华, 唐超权, 等. 基于周期势系统随机共振的轴承故障诊断. 工程科学学报, 2018, 40(8):989

    Zhang J L, Yang J H, Tang C Q, et al. Bearing fault diagnosis by stochastic resonance method in periodical potential system. Chin J Eng, 2018, 40(8): 989
    [13] 赵川, 冯志鹏. 基于多域流形的行星齿轮箱局部故障识别. 工程科学学报, 2017, 39(5):769

    Zhao C, Feng Z P. Localized fault identification of planetary gearboxes based on multiple-domain manifold. Chin J Eng, 2017, 39(5): 769
    [14] 张东, 冯志鹏. 迭代广义短时Fourier变换在行星齿轮箱故障诊断中的应用. 工程科学学报, 2017, 39(4):604

    Zhang D, Feng Z P. Application of iterative generalized short-time Fourier transform to fault diagnosis of planetary gearboxes. Chin J Eng, 2017, 39(4): 604
    [15] Gugulothu N, Tv V, Malhotra P, et al. Predicting remaining useful life using time series embeddings based on recurrent neural networks // ACM SIGKDD Workshop on Machine Learning for Prognostics and Health Management. Halifax, 2017
    [16] Guo L, Li N P, Jia F, et al. A recurrent neural network based health indicator for remaining useful life prediction of bearings. Neurocomputing, 2017, 240: 98 doi: 10.1016/j.neucom.2017.02.045
    [17] Huang H Z, Wang H K, Li Y F, et al. Support vector machine based estimation of remaining useful life: current research status and future trends. J Mech Sci Technol, 2015, 29(1): 151 doi: 10.1007/s12206-014-1222-z
    [18] Liu J, Zio E. SVM hyperparameters tuning for recursive multi-step-ahead prediction. Neural Comput Appl, 2017, 38: 3749
    [19] 高明哲, 许爱强, 许晴. 基于aRVM的电子设备状态在线预测方法. 兵器装备工程学报, 2017, 38(11):108 doi: 10.11809/scbgxb2017.11.024

    Gao M Z, Xu A Q, Xu Q. Online condition prediction of electronic equipment based on relevance vector machine with adaptive Kernel learning. J Ordnance Equip Eng, 2017, 38(11): 108 doi: 10.11809/scbgxb2017.11.024
    [20] Zermani S, Dezan C, Chenini H, et al. FPGA implementation of Bayesian network inference for an embedded diagnosis // 2015 IEEE Conference on Prognostics and Health Management. Austin, 2015: 1
    [21] Zermani S, Dezan C, Euler R, et al. Bayesian network-based framework for the design of reconfigurable health management monitors // 2015 NASA/ESA Conference on Adaptive Hardware and Systems. Montreal, 2015: 1
    [22] Wang T Y, Yu J B, Siegel D, et al. A similarity-based prognostics approach for remaining useful life estimation of engineered systems // International Conference on Prognostics and Health Management. Denver, 2008: 1
    [23] 朱扬普. 无损检测技术在轧辊检测中的推广及应用. 机电工程技术, 2016, 45(5):121 doi: 10.3969/j.issn.1009-9492.2016.05.034

    Zhu Y P. Generalization and application of NDT technology in roller testing. Mech Electr Eng Technol, 2016, 45(5): 121 doi: 10.3969/j.issn.1009-9492.2016.05.034
    [24] 何安瑞, 邵键, 孙文权. 板形控制理论与实践. 北京: 冶金工业出版社, 2016

    He A R, Shao J, Sun W Q. Theory and Practice of Shape Control. Beijing: Metallurgical Industry Press, 2016
    [25] Nelsen R B. An Introduction to Copulas. Technometrics, 2000, 42(3): 317
  • 加载中
图(11) / 表(2)
计量
  • 文章访问数:  749
  • HTML全文浏览量:  603
  • PDF下载量:  55
  • 被引次数: 0
出版历程
  • 收稿日期:  2019-08-26
  • 刊出日期:  2020-06-01

目录

    /

    返回文章
    返回