Prediction of ultimate condition of FRP-confined recycled aggregate concrete using a hybrid boosting model enriched with tabular generative adversarial networks. (January 2023)

• Record Type: Journal Article
• Authors: Zhao, Xin-Yu; Chen, Jin-Xin; Chen, Guang-Ming; Xu, Jin-Jun; Zhang, Li-Wen
• Is Part Of: Thin-walled structures. Volume 182(2023)Part B
• Publication Date: 2023-01
• Subjects: FRP confined concrete -- Recycled aggregate concrete -- Machine learning -- XGBoost -- Beetle antennae search algorithm -- Axial behavior; Thin-walled structures -- Periodicals; 690.1
• DOI: 10.1016/j.tws.2022.110318
• Languages: English
• ISSNs: 0263-8231

Abstract

Abstract: Despite its multiple benefits, recycled aggregate concrete (RAC) usually exhibits inferior properties compared with natural aggregate concrete, which has been deemed as a hurdle to its widespread use. One way to overcome this roadblock is to apply FRP jacketing. However, it appears not easy to quantify the axial performance of FRP-confined recycled aggregate concrete columns (FRACC), due largely to the complex load-resisting mechanisms involved. Also, the weakness of RAC itself further compound the problem. This paper aspires to deliver an alternative means to address this difficulty. A powerful boosting approach, XGBoost, was developed to fulfill the goal, where its hyperparameters was fine-tuned by a beetle antennae search metaheuristic algorithm. Meanwhile, a synthetic data generator, tabular generative adversarial networks, was introduced to supplement the limited training data. The model developed outperformed existing empirical equations and several baseline machine learning models. Teng et al.'s FRP-confined concrete model was also improved for better tracing the axial stress–strain behavior. Besides, interpreting the model allows better understanding of the underlying mechanisms such as the minimum reinforcement ratio of FRP required to mitigate the negative effects of RAC. Finally, two data-driven, explicit design equations are given for practical design of FRACC. Highlights: A novel machine learning model is developed to quantify the axial performance of FRP-confined RAC columns. Beetle antenna search is hybridized with XGBoost to fine-tune hyperparameters. The developed model has good performance surpassing existing empirical equations and baseline ML models. The model is also endowed with explainability that yields useful insights.