首页|多元算法融合模型的CFRP约束型钢混凝土柱承载力预测

多元算法融合模型的CFRP约束型钢混凝土柱承载力预测

Prediction of Bearing Capacity of CFRP-constrained Steel and Concrete Columns Based on Multivariate Algorithm Fusion Model

扫码查看
原文链接
  • NETL
  • NSTL
  • 万方数据
为准确预测多影响因素下碳纤维增强复合材料(CFRP)约束型钢混凝土柱(SRCC)的轴压承载力,提出了一种基于随机森林(RF)、分类提升(Catboost)、极端梯度提升(XGBoost)、梯度提升回归树(GBRT)的多元算法融合预测模型.首先采用合成少数类过采样技术(SMOTE)算法对原始数据集进行扩充,开展了10 种传统机器学习和集成学习模型试验,筛选出决定系数R2 均大于0.92 的RF、Catboost、XGBoost、GBRT的 4 种集成学习模型,用随机搜索优化其超参数,然后融合形成了RF-Catboost-XGBoost-GBRT预测模型,对CFRP 约束SRCC的承载力进行预测.结果表明,两种数据集下RF-Catboost-XGBoost-GBRT模型的预测性能最好,原始数据集经SMOTE算法处理后,5 种预测模型 R2 平均提高 20.43%,其中 RF-Catboost-XGBoost-GBRT 模型的 R2 达到了0.942,预测值误差均在±10%以内.
In order to accurately predict the axial compression bearing capacity of steel reinforced con-crete columns(SRCC)confined by carbon fiber reinforced polymer(CFRP)under multiple influencing factors.A multivariate algorithm fusion prediction model based on Random Forest(RF),categorical boosting(Catboost),eXtreme Gradient Boosting(XGBoost)and gradient boosting regression tree(GBRT)is proposed.Firstly,the synthetic minority oversampling technique(SMOTE)algorithm is used to expand the original data set,and 10 kinds of traditional machine learning and ensemble learning model tests are carried out.Four ensemble learning models of RF,Catboost,XGBoost and GBRT with determination coefficients(R2)greater than 0.92 are selected.The hyperparameters are optimized by random search,and then the RF-Catboost-XGBoost-GBRT prediction model is formed by fusion.The bearing capacity of CFRP confined steel reinforced concrete rectangular columns is predicted.The re-sults show that the RF-Catboost-XGBoost-GBRT model shows the best prediction performance under the two datasets,and after the original dataset is processed by SMOTE,the R2 of the five prediction models is increased by an average of 20.43%,among which the R2 of the RF-Catboost-XGBoost-GBRT model reaches 0.942,and the prediction error is within±10%.

combined structuressteel and concrete columnsintegrated learningfusion modelsfi-ber composite reinforced material

王奕斌、王向英、张纪刚、杨光超、王胜、陈德刚

展开 >

青岛理工大学 土木工程学院,山东 青岛 266033

青岛青建理工建筑工业化研究院有限公司,山东 青岛 266033

组合结构 型钢混凝土柱 集成学习 融合模型 纤维复合增强材料

国家重点研发计划国家自然科学基金-山东联合基金重点支持项目国家自然科学基金青年基金山东省自然科学基金

2017YFC0703600U210622252108282ZR2021QE053

2024

10.3969/j.issn.1673-9469.2024.03.002

河北工程大学学报(自然科学版)
河北工程大学

河北工程大学学报(自然科学版)

CSTPCD
影响因子：0.543
ISSN：1673-9469
年,卷(期)：2024.41(3)
  • 5