基于XGBoost模型的钢筋混凝土梁长期挠度预测研究  

Research on Long-term Deflection Prediction of Reinforced Concrete Beams Based on XGBoost

作　　者：岳鑫鑫 常山 杜玉杰 马露 但文蛟 YUE Xinxin;CHANG Shan;DU Yujie;MA Lu;DAN Wenjiao(College of Architecture,Anhui Science and Technology University,Bengbu 233030,China;College of Mechanical Engineering,Anhui Science and Technology University,Chuzhou 233030,China)

机构地区：[1]安徽科技学院建筑学院,安徽蚌埠233030 [2]安徽科技学院机械学院,安徽滁州233100

出　　处：《安阳工学院学报》2024年第4期98-105,共8页Journal of Anyang Institute of Technology

基　　金：安徽省教育厅重大项目(2023AH040274);安徽省教育厅重点项目(2023AH051841);企业横向课题(881027、881028、881202)。

摘　　要：为准确地对钢筋混凝土(Reinforced Concrete,RC)梁的长期挠度进行预测,首先收集了RC梁的长期挠度试验数据,随后基于极度梯度提升树(eXtreme Gradient Boosting,XGBoost)建立了RC梁长期挠度预测模型,在试验数据集上进行了模型精度的测试,并与基于支持向量回归基(Support vector regression,SVR)和反向传播神经网络(Back Propagation Neural Network,BPNN)建立的预测模型进行比对。结果表明,本研究建立的基于XGBoost模型的RC梁长期挠度预测模型在训练集、测试集上的决定系数分别达到1.0000、0.9818,可用于RC梁的长期变形挠度预测;与基于SVR和BPNN建立的模型相比,XGBoost模型的均方根误差分别降低了98.03%、15.93%和99.47%、85.97%,平均绝对百分比误差分别降低了95.51%、11.81%和96.40%、30.83%,优势明显。最后,基于XGBoost模型对RC梁的长期挠度进行了全局灵敏度分析,对影响参数进行了重要性排序。本研究结果证明了基于XGBoost的预测模型在该领域具有优异的性能。To accurately predict the long-term deflection of reinforced concrete(RC)beams,long-term deflection test data of RC beams were collected,and a prediction model was established based on eXtreme Gradient Boosting(XGBoost).The accuracy of this model was tested and compared with prediction models established using Support Vector Regression(SVR)and Back Propagation Neural Network(BPNN)on the test dataset.The results show that the long-term deflection prediction model for RC beams based on XGBoost model can be effectively used for longterm deflection prediction,achieving coefficients of determination reaching 1.0000 and 0.9818 on the training set and testing set,respectively.Comparing with the models established using SVR and BPNN,the root mean square error of XGBoost model was reduced by 98.03%,15.93%for the training set,and by 99.47%and 85.97%for the testing set.Additionally,the mean absolute percentage error was reduced by 95.51%,11.81%for the training set,and by 96.40%and 30.83%for the testing set.Finally,a global sensitivity analysis of the long-term deflection of RC beams based on XGBoost model was conducted to rank the importance of influential parameters.The results demonstrate that the XGBoost model has the excellent performance.

关 键 词：钢筋混凝土梁 XGBoost 长期挠度预测 机器学习 全局灵敏度分析 

分 类 号：TU59[建筑科学—建筑技术科学]