Scholarlink

<p>Accurate prediction of material properties is essential in steel manufacturing, as it enables optimized production processes. The scarcity of microscopy images in steel microstructure analysis has led to the adoption of pre-trained deep learning models for property prediction on smaller datasets. This study investigates prediction capabilities of a fine-tuned VisionTransformer for five mechanical properties on the microstructures of 47 steel specimen over six magnifications. While the model achieves competitive predictions for upper yield strength, yield strength, ultimate tensile strength and elongation at fracture, while the Charpy V-notch impact energy is predicted less accurate. Lower magnifications tend to improve the prediction of all properties. Our analysis of different popular data splitting strategies indicates that improper splitting of micrographs can lead to data leakage, resulting in an overestimation of model performance by up to threefold. Our findings underscore the need for reliable evaluation procedures and highlight the critical challenges of applying deep learning to steel microstructure analysis.</p>

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

Steel microstructure analysis using transfer learning: a study on data leakage

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年4月4日

查看全文
  • Marcel Wentzien,
  • Jerome Ingber,
  • Jörg Schlötterer,
  • Thomas Friedrich,
  • Henning Kempka,
  • Dirk Schmalzried,
  • Maik Kunert

摘要

Accurate prediction of material properties is essential in steel manufacturing, as it enables optimized production processes. The scarcity of microscopy images in steel microstructure analysis has led to the adoption of pre-trained deep learning models for property prediction on smaller datasets. This study investigates prediction capabilities of a fine-tuned VisionTransformer for five mechanical properties on the microstructures of 47 steel specimen over six magnifications. While the model achieves competitive predictions for upper yield strength, yield strength, ultimate tensile strength and elongation at fracture, while the Charpy V-notch impact energy is predicted less accurate. Lower magnifications tend to improve the prediction of all properties. Our analysis of different popular data splitting strategies indicates that improper splitting of micrographs can lead to data leakage, resulting in an overestimation of model performance by up to threefold. Our findings underscore the need for reliable evaluation procedures and highlight the critical challenges of applying deep learning to steel microstructure analysis.