Scholarlink

In this paper, the neural network digital simulation technology is combined with the study of IF steel yield strength. The grain size of ferrite, grain shape factor of ferrite, size and average spacing of second-phase particles on the yield strength of IF steel were investigated by establishing BP neural network and GRNN neural network models. The establishment of the yield strength prediction model of IF steel was realized by MATLAB software and the yield strength of IF steel was predicted. The results show that the yield strength shows the law of weakening and then strengthening with the increase of the sample parameters, and the optimal ferrite grain structure parameters are the 25th group of sample data, with the grain size of 19.5 μm, the shape factor of 44.7, the particle size of 0.031 μm, and the average spacing of 1.9 μm, at which time the yield strength reaches the highest value.

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Strength Prediction of iF Steel Based on Machine Learning Approach

  • 会议论文

  • 发表日期：

    2025年

查看全文
  • Jiayin Song,
  • Yonghao Zeng,
  • Jingwen Wang,
  • Ming Wang

摘要

In this paper, the neural network digital simulation technology is combined with the study of IF steel yield strength. The grain size of ferrite, grain shape factor of ferrite, size and average spacing of second-phase particles on the yield strength of IF steel were investigated by establishing BP neural network and GRNN neural network models. The establishment of the yield strength prediction model of IF steel was realized by MATLAB software and the yield strength of IF steel was predicted. The results show that the yield strength shows the law of weakening and then strengthening with the increase of the sample parameters, and the optimal ferrite grain structure parameters are the 25th group of sample data, with the grain size of 19.5 μm, the shape factor of 44.7, the particle size of 0.031 μm, and the average spacing of 1.9 μm, at which time the yield strength reaches the highest value.