东北大学学报（自然科学版）

东北大学学报(自然科学版) ›› 2007, Vol. 28 ›› Issue (1): 63-67.DOI: -

• 论著 • 上一篇    下一篇

热轧过程中轧件组织与性能软测量系统的研究

何纯玉;赵宪明;吴迪;许云波;   

  1. 东北大学轧制技术及连轧自动化国家重点实验室;东北大学轧制技术及连轧自动化国家重点实验室;东北大学轧制技术及连轧自动化国家重点实验室;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110004;辽宁沈阳110004;辽宁沈阳110004;辽宁沈阳110004
  • 收稿日期:2013-06-27 修回日期:2013-06-27 出版日期:2007-01-15 发布日期:2013-06-24
  • 通讯作者: He, C.-Y.
  • 作者简介:-
  • 基金资助:
    国家自然科学基金资助项目(50334010)

On the soft-sensing system for workpiece's microstructure and mechanical properties during hot rolling

He, Chun-Yu (1); Zhao, Xian-Ming (1); Wu, Di (1); Xu, Yun-Bo (1)   

  1. (1) State Key Laboratory of Rolling and Automation, Northeastern University, Shenyang 110004, China
  • Received:2013-06-27 Revised:2013-06-27 Online:2007-01-15 Published:2013-06-24
  • Contact: He, C.-Y.
  • About author:-
  • Supported by:
    -

RichHTML

0

PDF (PC)

530

摘要： 介绍了热轧中轧件组织与性能软测量系统的组成和功能,讨论了开发软测量系统所必要的辅助变量选择和数据的预处理方法.通过对热轧过程中的工艺机理分析,并结合生产现场的控制要求,采用机理模型和人工神经网络相结合的方法建立了组织性能软测量系统的架构,并使用机理模型计算得到的微观组织和轧件的化学成分作为人工神经网络的输入变量,规范了人工神经网络的层次结构.在软测量系统的应用过程中,利用校正模型的短期和长期自学习方法,使系统的测量精度满足在线检测要求.

关键词: 软测量, 温度场, 再结晶, 人工神经网络, 在线校正

Abstract: Discusses the architecture and functions required by the soft-sensing system for workpiece's microstructure and mechanical properties during hot rolling, especially the choice of auxiliary variables and the way to preprocess data both are integral to the soft-sensing system. Based on the mechanism model and artificial neural network (ANN), the architecture of the soft-sensing system is proposed via the technological mechanism analysis of hot rolling and system control requirements in site. The ANN input variables consist of the microstructure calculated by mechanism model and chemical composition of workpiece during rolling, thus normalizing the ANN architecture. During the application of the soft-sensing system, the short/long-term self-learning through correction model is used to meet the requirement of measuring accuracy for online detection.

中图分类号: