Abstract

This study aims at utilizing machine learning (ML) in predicting the fire resistance and spalling degree of reinforced concrete (RC) columns with improved accuracy and reliability. A database with 119 test specimens was created for the development of ML-based regression models, and a database with 101 test specimens was created for the development of ML-based classification models. Six ML algorithms—support vector machine (SVM), random forest (RF), multilayer perceptron (MLP), extreme gradient boosting (XGBoost), adaptive boosting (AdaBoost), and light gradient boosting machine (LightGBM). The hyperparameters of the ML-based models were optimized through Bayes optimization search (BayesSearchCV) with ten-fold cross-validation. The results indicated that the AdaBoost not only accurately predicted the spalling degree of RC columns with an accuracy of 87%, but also performed best in predicting the fire resistance of RC columns with R² = 0.96 and RMSE = 16.58. The AdaBoost model achieved high accuracy without significant bias, surpassing existing design equations. SHAP method was utilized to produce global explanations for the predictions. The results revealed that concrete compressive strength, loading ratio, slenderness ratio, and column width were the most critical features for spalling degree identification. Meanwhile, those were slenderness ratio, concrete cover, loading ratio, part of the fired column, and longitudinal reinforcement for fire resistance prediction. The parametric study demonstrated that the fire resistance of RC columns is positively affected by only concrete cover.

中文翻译：

---

使用基于机器学习的方法对烧成的 RC 柱进行混凝土剥落识别和耐火预测

摘要

本研究旨在利用机器学习（ML）来预测钢筋混凝土（RC）柱的耐火性和剥落程度，并提高准确性和可靠性。创建了一个包含 119 个测试样本的数据库，用于开发基于 ML 的回归模型，并创建了一个包含 101 个测试样本的数据库，用于开发基于 ML 的分类模型。六种 ML 算法——支持向量机 (SVM)、随机森林 (RF)、多层感知器 (MLP)、极端梯度增强 (XGBoost)、自适应增强 (AdaBoost) 和光梯度增强机 (LightGBM)。基于 ML 的模型的超参数通过贝叶斯优化搜索 (BayesSearchCV) 和十倍交叉验证进行优化。结果表明，AdaBoost不仅能够准确预测RC柱的剥落程度，准确率达到87%，而且在预测RC柱的耐火性能方面也表现最好，R ²  = 0.96，RMSE = 16.58。AdaBoost 模型实现了高精度，没有明显偏差，超越了现有的设计方程。SHAP 方法用于对预测进行全局解释。结果表明，混凝土抗压强度、荷载比、长细比和柱宽是剥落程度识别的最关键特征。同时，这些是长细比、混凝土保护层、荷载比、火柱部分和用于耐火预测的纵向钢筋。参数研究表明，RC 柱的耐火性仅受混凝土保护层的影响。