Confinement strength prediction of corroded rectangular concrete columns using BP neural networks and support vector regression

被引:3
|
作者
Zheng, Nai-Hao [1 ,2 ]
Zhang, Wei-Ping [1 ,2 ]
Zhou, Yong [2 ]
Liu, Yang [1 ,2 ]
机构
[1] Tongji Univ, Sch Civil Engn, Key Lab Performance Evolut & Control Engn Struct, Minist Educ, Shanghai 200092, Peoples R China
[2] Tongji Univ, Coll Civil Engn, Dept Struct Engn, 1239 Siping Rd, Shanghai 200092, Peoples R China
关键词
BPNN; SVR; SHAP interpretation; Corroded RC columns; Prediction stability; STRESS-STRAIN MODEL; MECHANICAL-PROPERTIES; CORROSION; BEHAVIOR;
D O I
10.1016/j.istruc.2024.107021
中图分类号
TU [建筑科学];
学科分类号
0813 ;
摘要
The application of machine learning in predicting the mechanical performance of reinforced concrete columns subjected to reinforcement corrosion was investigated in this study. Traditional models, often relying on empirical formulas or simplified assumptions, are known to struggle in capturing all variables and relationships in complex problems, leading to inadequate prediction accuracy. Through theoretical analysis, the confinement effect of stirrups on core concrete and its performance deterioration caused by reinforcement corrosion were determined. To improve the prediction accuracy and generalization ability, the error Back Propagation Neural Network (BPNN) and Support Vector Regression (SVR) models were employed. Parameter effects in the BPNN model were interpreted using the SHapley Additive exPlanations (SHAP) and compared with traditional parameter sensitivity analyses. The investigation indicates that the machine learning models have a high degree of fit and low error levels, particularly within the training set. After analyzing using the SHAP approach, it is found that the corrosion ratio of the stirrup and longitudinal reinforcement have a significant effect on the confinement strength of the concrete, whereas the effects of the stirrup configuration and size effect are negligible, which is different from conventional parametric sensitivity analysis. As to the stability analysis of model predictions, the SVR model shows lower volatility and higher prediction stability compared with the BPNN model, despite the latter occasionally providing superior generalization ability. This research underscores the significant advantages offered by machine learning models in addressing longstanding challenges associated with strength prediction, and thus presents new perspectives for future study.
引用
收藏
页数:12
相关论文
共 50 条
  • [31] Predicting ultimate bond strength of corroded reinforcement and surrounding concrete using a metaheuristic optimized least squares support vector regression model
    Nhat-Duc Hoang
    Xuan-Linh Tran
    Hieu Nguyen
    NEURAL COMPUTING & APPLICATIONS, 2020, 32 (11): : 7289 - 7309
  • [32] Ozone prediction on the basis of neural networks, support vector regression and methods with uncertainty
    Hajek, Petr
    Olej, Vladimir
    ECOLOGICAL INFORMATICS, 2012, 12 : 31 - 42
  • [33] Prediction of concrete strength based on BP neural network
    Jiang Jianping
    MATERIAL AND MANUFACTURING TECHNOLOGY II, PTS 1 AND 2, 2012, 341-342 : 58 - 62
  • [34] Prediction of critical stress intensity factor for high strength and ultra high strength concrete beams using support vector regression
    Yuvaraj, P. (yuvarajprakash@gmail.com), 1600, Structural Engineering Research Centre (40):
  • [35] Prediction of strength for concrete specimens using Artificial Neural Networks
    Kaveh, A
    Khalegi, A
    ADVANCES IN ENGINEERING COMPUTATIONAL TECHNOLOGY, 1998, : 165 - 171
  • [36] Prediction of compressive strength and porosity of vegetated concrete based on hybrid BP neural networks
    Li, Qiong
    Su, Rui
    Qiao, Hongxia
    Su, Li
    Wang, Penghui
    Gong, Linhan
    MATERIALS TODAY COMMUNICATIONS, 2025, 44
  • [37] A prediction model for flexural strength of corroded prestressed concrete beam using artificial neural network
    Bhagwat, Yamuna
    Nayak, Gopinatha
    Bhat, Radhakrishna
    Kamath, Muralidhar
    COGENT ENGINEERING, 2023, 10 (01):
  • [38] Unconfined compressive strength prediction of soils stabilized using artificial neural networks and support vector machines
    Alireza TABARSA
    Nima LATIFI
    Abdolreza OSOULI
    Younes BAGHERI
    Frontiers of Structural and Civil Engineering, 2021, (02) : 520 - 536
  • [39] Unconfined compressive strength prediction of soils stabilized using artificial neural networks and support vector machines
    Tabarsa, Alireza
    Latifi, Nima
    Osouli, Abdolreza
    Bagheri, Younes
    FRONTIERS OF STRUCTURAL AND CIVIL ENGINEERING, 2021, 15 (02) : 520 - 536
  • [40] Unconfined compressive strength prediction of soils stabilized using artificial neural networks and support vector machines
    Alireza Tabarsa
    Nima Latifi
    Abdolreza Osouli
    Younes Bagheri
    Frontiers of Structural and Civil Engineering, 2021, 15 : 520 - 536