东北大学学报:自然科学版 ›› 2019, Vol. 40 ›› Issue (5): 635-640.DOI: 10.12068/j.issn.1005-3026.2019.05.006

• 材料与冶金 • 上一篇    下一篇

深度学习在中厚板轧后超快速冷却系统中的研究与应用

张田, 张子豪, 田勇, 王昭东   

  1. (东北大学 轧制技术及连轧自动化国家重点实验室, 辽宁 沈阳110819)
  • 收稿日期:2018-04-02 修回日期:2018-04-02 出版日期:2019-05-15 发布日期:2019-05-17
  • 通讯作者: 张田
  • 作者简介:张田(1989-),男,安徽马鞍山人,东北大学博士后研究人员; 王昭东(1968-),男,安徽安庆人,东北大学教授,博士生导师.
  • 基金资助:
    国家重点基础研究发展计划项目(2017YFB0306404); 中央高校基本科研业务费专项资金资助项目(N170703010).

Research and Application of Deep Learning Method for Plate Ultra Fast Cooling

ZHANG Tian, ZHANG Zi-hao, TIAN Yong, WANG Zhao-dong   

  1. State Key Laboratory of Rolling and Automation, Northeastern University, Shenyang 110819, China.
  • Received:2018-04-02 Revised:2018-04-02 Online:2019-05-15 Published:2019-05-17
  • Contact: ZHANG Zi-hao
  • About author:-
  • Supported by:
    -

摘要: 传热系数是冷却控制模型的核心参数.传统学习模型对传热系数的修正存在不稳定、鲁棒性不强等问题.为解决上述问题,进一步提高控制精度,基于深度学习技术,建立了传热系数自学习的深度神经网络,对神经网络框架的超参数进行了优化和算法选型,增强控冷模型的稳定性.通过在某钢厂3500mm中厚板生产线的应用验证,采用深度学习的控冷模型对终冷温度预报精度有明显提高,鲁棒性较强,满足现场实际生产的需要.

关键词: 深度学习, 中厚板, 超快冷, 传热系数, 命中率

Abstract: The heat transfer coefficient (HTC) is a key parameter to determine control precision in a cooling-controlled model. However, the correction for the HTC isn’t always stable and robustness by a traditional self-learning method. In order to solve such problems,the deep neural networks for the self-learning HTC were built based on the deep learning technology. The optimization of hyper parameter and the selection of algorithm in the network frame are studied. Therefore, the stability of the cooling control model can be greatly enhanced. The application of the 3500mm plate mill plant proves the better accuracy and robustness of the model, which can meet the requirements of actual on-site production.

Key words: deep learning, plate, ultra fast cooling, heat transfer coefficient, hit rate

中图分类号: