Scholarlink

The study of the corrosion impact on metallic materials is critical to industries and the metallurgical market. Over the years, several formulas, known as Dose-Response Functions, have been developed to predict corrosion based on environmental factors. Using data from the MICAT atmospheric corrosion study, this article proposes data-driven prediction models for four materials: Carbon Steel, Aluminum, Copper, and Zinc. The models indicate that the Random Forest algorithm can predict atmospheric corrosion of metallic materials with competitive results compared to standard prediction functions.

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

Atmospheric Corrosion Prediction in Metallic Materials Using Machine Learning

  • 会议论文

  • 发表日期：

    2025年

查看全文
  • Vinícius Michelon Geremias,
  • Thiago Brandenburg,
  • Fabiano Miranda,
  • Gustavo Fischer,
  • José Silva Filho,
  • Rafael Stubs Parpinelli

摘要

The study of the corrosion impact on metallic materials is critical to industries and the metallurgical market. Over the years, several formulas, known as Dose-Response Functions, have been developed to predict corrosion based on environmental factors. Using data from the MICAT atmospheric corrosion study, this article proposes data-driven prediction models for four materials: Carbon Steel, Aluminum, Copper, and Zinc. The models indicate that the Random Forest algorithm can predict atmospheric corrosion of metallic materials with competitive results compared to standard prediction functions.