An experimental investigation and machine learning-based prediction for seismic performance of steel tubular column filled with recycled aggregate concrete

Tang, Yunchao; Wang, Yufei; Wu, Dongxiao; Zhang, Hexin; Zhu, Ming; Chen, Zheng; Sun, Junbo; Wang, Xiangyu

Abstract

This paper presents the design and application of a low-cycle reciprocating loading test on 23 recycled aggregate concrete-filled steel tube columns (RACSTC) and 3 ordinary concrete-filled steel tube columns (OCSTC). Additionally, a systematic study on the influence of parameters (e.g., slenderness ratio, axial compression ratio, etc.) was conducted on the seismic performance of the specimens. The results show that all the specimens have good hysteresis performance and a similar development trend of skeleton curve. The influence of slenderness ratio on the seismic index of the specimens is more significant than that of the axial compression ratio and the steel pipe wall thickness. Furthermore, artificial intelligence was applied to estimate the influence of parameter variation on the seismic performance of concrete columns. Specifically, Random Forest (RF) with hyperparameters tuned by Firefly Algorithm (FA) was chosen. The prediction results showed acceptable accuracy from the high correlation coefficients (R) and low Root Mean Square Error (RMSE) values. In addition, sensitivity analysis was applied to rank the influence of the aforementioned input variables on the seismic performance of the specimens. The research results can provide experimental reference for the application of steel tube recycled concrete in earthquake areas.

• Journal Article Type: Article
• Acceptance Date: Oct 19, 2022
• Online Publication Date: Dec 22, 2022
• Publication Date: 2022
• Deposit Date: Oct 19, 2022
• Publicly Available Date: Oct 20, 2022
• Journal: Reviews on advanced Materials Science
• Publisher: De Gruyter
• Peer Reviewed: Peer Reviewed
• Volume: 61
• Issue: 1
• Pages: 849-872
• DOI: https://doi.org/10.1515/rams-2022-0274
• Keywords: Low-cycle reciprocating loading test; Recycled concrete-filled steel tube columns; Slenderness ratio; Machine learning; Seismic performance prediction
• Public URL: http://researchrepository.napier.ac.uk/Output/2936512