Scholarlink

<p>Corrosion is a major cause of failure in marine engineering steel, resulting in large economic losses worldwide. This study integrates knowledge of marine corrosion with machine learning techniques to predict corrosion potential. Using experimental data collected from numerous published studies, five machine learning models were built in Python: K-Nearest Neighbors (KNN), Extreme Gradient Boosting (XGBoost), Gradient Boosting Regressor (GBR), Stacked Generalization (Stacking), and a Weighted Average Ensemble. Model prediction accuracy was improved through feature engineering and data augmentation. Feature engineering identified C×Mn, Mn×Cu, and Mn×Mo as interaction terms for model training, while data augmentation added appropriate noise to the training set to expand the dataset to prevent overfitting. The XGBoost model performed best and achieved a coefficient of determination (R²) of 0.80 on the training set and 0.62 on the test set. Its mean absolute error (MAE) was 0.07 V and root mean square error (RMSE) was 0.09 V. The generalization gap was 0.179. Feature importance analysis revealed that Mn, Cr, and the Cr×Mo interaction are key factors influencing corrosion potential. This approach provides an accurate and interpretable technical solution to predict corrosion potential for marine engineering steels.</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

Corrosion potential prediction of marine engineering steel based on machine learning

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年5月16日

查看全文
  • Bin Wu,
  • Yicong Luo,
  • Shiwei Yu,
  • Endian Fan

摘要

Corrosion is a major cause of failure in marine engineering steel, resulting in large economic losses worldwide. This study integrates knowledge of marine corrosion with machine learning techniques to predict corrosion potential. Using experimental data collected from numerous published studies, five machine learning models were built in Python: K-Nearest Neighbors (KNN), Extreme Gradient Boosting (XGBoost), Gradient Boosting Regressor (GBR), Stacked Generalization (Stacking), and a Weighted Average Ensemble. Model prediction accuracy was improved through feature engineering and data augmentation. Feature engineering identified C×Mn, Mn×Cu, and Mn×Mo as interaction terms for model training, while data augmentation added appropriate noise to the training set to expand the dataset to prevent overfitting. The XGBoost model performed best and achieved a coefficient of determination (R²) of 0.80 on the training set and 0.62 on the test set. Its mean absolute error (MAE) was 0.07 V and root mean square error (RMSE) was 0.09 V. The generalization gap was 0.179. Feature importance analysis revealed that Mn, Cr, and the Cr×Mo interaction are key factors influencing corrosion potential. This approach provides an accurate and interpretable technical solution to predict corrosion potential for marine engineering steels.