Scholarlink

<p>This work presents the development of an artificial neural network (ANN) designed to predict the microhardness of an experimental medium-carbon, low-alloy Cr–Mo steel. For this purpose, several tempering processes were carried out at different temperatures (between 500 and 600&#xa0;°C) and times (between 0 and 600&#xa0;min) on previously quenched specimens. Under these conditions, resistance to softening was observed, which is a phenomenon associated with secondary hardening. The ANN was trained and tested with these experimental data, considering the tempering temperature and tempering time as input neurons, and the microhardness as the output neuron. A good correlation was observed between the experimental and estimated data, demonstrating that the ANN was adequately trained and tested. Finally, the ANN was used to predict microhardness under tempering conditions different from those used during the training and testing stages.</p> Graphical abstract <p></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

Development of an artificial neural network for the prediction of secondary hardening on an experimental medium-carbon, low-alloy Cr–Mo steel

  • 期刊论文

  • 发表日期：

    2025年12月24日

查看全文
  • Perla G. Díaz-Villaseñor,
  • Edgar López-Martínez,
  • Octavio Vázquez-Gómez,
  • Pedro Garnica-González,
  • Héctor J. Vergara-Hernández

摘要

This work presents the development of an artificial neural network (ANN) designed to predict the microhardness of an experimental medium-carbon, low-alloy Cr–Mo steel. For this purpose, several tempering processes were carried out at different temperatures (between 500 and 600 °C) and times (between 0 and 600 min) on previously quenched specimens. Under these conditions, resistance to softening was observed, which is a phenomenon associated with secondary hardening. The ANN was trained and tested with these experimental data, considering the tempering temperature and tempering time as input neurons, and the microhardness as the output neuron. A good correlation was observed between the experimental and estimated data, demonstrating that the ANN was adequately trained and tested. Finally, the ANN was used to predict microhardness under tempering conditions different from those used during the training and testing stages.

Graphical abstract