金属热处理 ›› 2022, Vol. 47 ›› Issue (3): 227-233.DOI: 10.13251/j.issn.0254-6051.2022.03.042

• 数值模拟 • 上一篇    下一篇

基于ELM的齿轮钢淬透性预测模型

赵艺琪1, 聂小龙1, 赵四新2, 高加强2, 刘新宽1   

  1. 1.上海理工大学 材料与化学学院, 上海 200093;
    2.宝钢研究院, 上海 201900
  • 收稿日期:2021-12-07 修回日期:2022-02-05 出版日期:2022-03-25 发布日期:2022-04-22
  • 通讯作者: 刘新宽,副教授,E-mail:xinkuanliu@163.com
  • 作者简介:赵艺琪(1995—),女,硕士研究生,主要研究方向为齿轮钢淬透性的影响因素,E-mail:18614761965@163.com。

Predicting model of gear steel hardenability based on extreme learning machine

Zhao Yiqi1, Nie Xiaolong1, Zhao Sixin2, Gao Jiaqiang2, Liu Xinkuan1   

  1. 1. School of Materials and Chemistry, University of Shanghai for Science and Technology, Shanghai 200093, China;
    2. Baosteel Central Research Institute, Shanghai 201900, China
  • Received:2021-12-07 Revised:2022-02-05 Online:2022-03-25 Published:2022-04-22

摘要: 利用极限学习机(ELM)研究了20Cr齿轮钢端淬硬度曲线和化学成分的预测,并将其预测结果与传统预测模型进行比较。结果表明,ELM可以根据齿轮钢的化学成分预测其淬透性,计算精度明显优于传统线性拟合及神经网络模型,同时ELM也能通过齿轮钢淬透性硬度曲线反测化学成分,元素含量误差在5%以内。

关键词: ELM, 齿轮钢, 淬透性

Abstract: Prediction of end-quenching hardness curve and chemical composition of 20Cr gear steel was studied by using extreme learning machine(ELM), and the prediction results were compared with the traditional prediction models. The results show that the ELM not only can predict the hardenability of the gear steel according to the chemical composition with calculation accuracy significantly higher than that of the traditional linear fitting and neural network models,but also can be used to backward predict the chemical composition from the hardenability curve with the element content error within 5%.

Key words: extreme learning machine (ELM), gear steel, hardenability

中图分类号: