东北大学学报:自然科学版 ›› 2016, Vol. 37 ›› Issue (12): 1710-1715.DOI: 10.12068/j.issn.1005-3026.2016.12.009

• 材料与冶金 • 上一篇    下一篇

基于大数据的C-Mn钢数据预处理及神经网络模型

吴思炜, 曹光明, 周晓光, 刘振宇   

  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:2015-07-28 修回日期:2015-07-28 出版日期:2016-12-15 发布日期:2016-12-23
  • 通讯作者: 吴思炜
  • 作者简介:吴思炜(1989-),男,辽宁阜新人,东北大学博士研究生; 刘振宇(1967-),男,内蒙古赤峰人,东北大学教授,博士生导师.
  • 基金资助:
    钢铁联合基金重点项目(U1460204); 辽宁省自然科学基金资助项目(2015020180); 中央高校基本科研业务费专项资金资助项目(N140704002).

Data Preprocessing and Neural Network Model of C-Mn Steel Based on Big Data

WU Si-wei, CAO Guang-ming, ZHOU Xiao-guang, LIU Zhen-yu   

  1. State Key Laboratory of Rolling and Automation, Northeastern University, Shenyang 110819, China.
  • Received:2015-07-28 Revised:2015-07-28 Online:2016-12-15 Published:2016-12-23
  • Contact: LIU Zhen-yu
  • About author:-
  • Supported by:
    -

摘要: 在神经网络建模时,如果原始数据不加处理或经过简单剔除异常值后用于建模,则可能建立出错误的模型,即其规律并不符合物理冶金原理.因此建模前需要对原始数据进行处理,使其呈现出显著的规律性.针对钢铁生产采集的大量C-Mn钢数据进行了钢种归并,提出了数据预处理的一套方法,并采用LM-BP神经网络建立了满足一定精度(94.21%)的多牌号C-Mn钢屈服强度预测模型.通过平均影响值(mean impact value,MIV)分析了成分及工艺参数对屈服强度的影响规律.结果表明,随着碳含量的增加,屈服强度增大;随着终轧厚度和卷取温度的降低,屈服强度增大.

关键词: 大数据, 建模, 预处理, 平均影响值, C-Mn钢

Abstract: In neural network modeling, it may build a wrong model using original data without any treatment or only eliminating the abnormal value, for it could contain the law not to follow the physical metallurgy principle. To make the regularity significant, the original data need to be processed before modeling. In this work, based on the data of the C-Mn steel derived from a large number of data collected from different steel grades, a set of method for data preprocessing was proposed and a model for predicting yield strength of the C-Mn steel was established using LM-BP neural network, which could make the prediction accuracy meet the requirement (94.21%). The effects of the elements content and processing parameters on the yield strength were analyzed by the mean impact value (MIV). The results showed that the yield strength increased with the increase of carbon content and increased with the decrease of final rolling thickness and coiling temperature.

Key words: big data, modeling, data preprocessing, mean impact value (MIV), C-Mn steel

中图分类号: