基于Stacking集成模型融合的钢筋混凝土锈胀开裂预测方法  

Prediction Method for Reinforced Concrete Corrosion-induced Crack Based on Stacking Integrated Model Fusion

作　　者：梁梓豪 应宗权[1,2,3] 刘梅梅 杨帅[1,2,3] LIANG Zihao;YING Zongquan;LIU Meimei;YANG Shuai(CCCC Fourth Harbor Engineering Institute Co.,Ltd.,Guangzhou 510230,China;Key Laboratory of Construction Materials,CCCC,Guangzhou 510230,China;Key Laboratory of Harbor&Marine Structure Durability Technology,Ministry of Transport,Guangzhou 510230,China)

机构地区：[1]中交四航工程研究院有限公司,广州510230 [2]中交集团建筑材料重点实验室,广州510230 [3]水工构造物耐久性技术交通运输行业重点实验室,广州510230

出　　处：《中国腐蚀与防护学报》2024年第6期1601-1609,共9页Journal of Chinese Society For Corrosion and Protection

基　　金：国家重点研发计划(2022YFB2603000)。

摘　　要：为了解决传统经验公式模型对钢筋混凝土锈胀开裂预测方法存在的公式不统一、精度有限等问题的局限性,本文提出一种基于Stacking集成模型融合的钢筋混凝土锈胀开裂预测方法。首先,通过文献收集的223组钢筋混凝土锈胀开裂试验数据进行数据预处理;其次,基于支持向量回归(SVR)、随机森林(RF)和极端梯度提升树(XGBoost)算法分别进行贝叶斯优化超参数、模型训练及评估,采用决定系数R^(2)、平均绝对误差(MAE)和均方根误差(RMSE)对比分析3种机器学习模型的预测性能,并在此基础上搭建基于Stacking融合多种算法的预测模型;最后,对所提出的机器学习模型和传统经验公式模型进行泛化性能验证,并探讨基于XGBoost模型的可解释性分析。结果表明:与其他机器学习模型相比,基于Stacking集成模型的预测精度和泛化性能较好,且可解释性分析结果说明模型预测逻辑与实际工程经验较为吻合。研究结果有助于提高钢筋混凝土锈胀开裂预测精度,可为决策者在实际工程提供科学的理论指导。In predicting corrosion-induced cracking of reinforced concrete,traditional empirical formulas used are varied with limited precision of prediction.To address these limitations,this paper presents a method based on the stacking of models to predict the cracking of reinforced concrete due to corrosion induced expansion.Firstly,223 sets of test data on the cracking of reinforced concrete due to corrosion induced expansion were collected from published articles and processed in advance.Next,Bayesian optimization of hyperparameters,model training,and evaluation were conducted separately based on Support Vector Regression(SVR),Random Forest(RF),and Extreme Gradient Boosting(XGBoost)algorithms.Determination coefficient(R^(2)),mean absolute error(MAE),and root mean square error(RMSE)were utilized for a comparative analysis of the prediction performances of three machine learning models.On this basis,a prediction model integrating multiple algorithms with the Stacking method was proposed.Finally,the generalization performances of the proposed prediction model and traditional empirical formula models were verified,and the XGBoost model was employed to analyze the interpretability of the proposed model.As revealed in the results,the proposed model has better prediction accuracy and generalization performance than other machine learning models.The interpretability analysis result demonstrates that the prediction of the proposed model logic matches the practical engineering experience.This finding is conducive to improve the prediction accuracy of thecorrosion-induced cracking of reinforced concrete,and can provide scientific theoretical guidance for decision-makers in practical engineering.

关 键 词：钢筋混凝土 锈胀开裂 机器学习 Stacking算法 XGBoost算法 可解释性分析 

分 类 号：TU375[建筑科学—结构工程]