Evaluation of bond strength degradation between FRP bars and normal concrete under seawater exposure: An explainable modeling approach

被引:0
作者
Cao, Heng [1 ,2 ,3 ]
Zhao, Xiao-Ling [4 ]
Li, Hui [5 ]
Iqbal, Mudassir [1 ,2 ,3 ,4 ,6 ]
Zhang, Daxu [1 ,2 ,3 ]
Zhang, Pei-Fu [1 ,2 ,3 ]
Tuerxunmaimaiti, Yiliyaer [1 ,2 ,3 ]
Zhao, Xuan [1 ,2 ,3 ]
机构
[1] Shanghai Jiao Tong Univ, State Key Lab Ocean Engn, Shanghai 200240, Peoples R China
[2] Shanghai Jiao Tong Univ, Shanghai Key Lab Digital Maintenance Bldg & Infras, Shanghai 200240, Peoples R China
[3] Shanghai Jiao Tong Univ, Sch Ocean & Civil Engn, Shanghai 200240, Peoples R China
[4] Hong Kong Polytech Univ, Dept Civil & Environm Engn, Hong Kong, Peoples R China
[5] First Co China Eighth Engn Bur Ltd, Jinan 250100, Peoples R China
[6] Univ Engn & Technol Peshawar, Dept Civil Engn, Peshawar 25120, Pakistan
基金
中国国家自然科学基金;
关键词
FRP composites; Concrete; Bond durability; Marine environment; Machine learning; DURABILITY; BASALT; PREDICTION;
D O I
10.1016/j.istruc.2025.109525
中图分类号
TU [建筑科学];
学科分类号
0813 ;
摘要
The harsh conditions in corrosive environments impose critical demands on the durability of concrete structures. The replacement of steel reinforcement with corrosion-resistant fibre-reinforced polymer (FRP) bars offers a viable solution for enhancing structural durability. The bond strength retention (BSR) is a significant factor in evaluating the bond durability between FRP bars and concrete. The traditional methods face significant challenges in accurately assessing bond durability due to the complexity of corrosion mechanisms. To address the challenges, this paper presented a novel approach for predicting the BSR between FRP bars and concrete under seawater immersion using explainable modelling. A dataset of 153 pull-out test data points incorporating 12 parameters was compiled, and a Random Forest (RF) model was developed, achieving an R2 of 0.954 and 0.937 on training and testing sets, respectively. SHAP (SHapley Additive exPlanations) analysis was employed to interpret the prediction results, revealing the significance and influence patterns of the input parameters. The effects of input parameters, including the properties of FRP bars, concrete, environmental effects and bond, were analysed and discussed in detail. Furthermore, an explicit equation for predicting BSR was derived based on SHAP analysis, exhibiting superior accuracy (R2 of 0.836) and applicability compared to existing methods based on Fib Bulletin 40 (R2 of 0.795) and Arrhenius relationship (R2 of 0.186 and -1.830). The proposed approach provides valuable insights for designing durable marine structures and other engineering applications in corrosive environments.
引用
收藏
页数:16
相关论文
共 66 条
[1]   Properties evaluation of fiber reinforced polymers and their constituent materials used in structures - A review [J].
Abbood, Imad Shakir ;
Odaa, Sief Aldeen ;
Hasan, Kamalaldin F. ;
Jasim, Mohammed A. .
MATERIALS TODAY-PROCEEDINGS, 2021, 43 :1003-1008
[2]   A review on durability of fiber reinforced polymer (FRP) bars reinforced seawater sea sand concrete [J].
Ahmed, Azzam ;
Guo, Shuaicheng ;
Zhang, Zuhua ;
Shi, Caijun ;
Zhu, Deju .
CONSTRUCTION AND BUILDING MATERIALS, 2020, 256
[3]   Durability of basalt FRP reinforcing bars in alkaline solution and moist concrete environments [J].
Al Rifai, Mohamed ;
El-Hassan, Hilal ;
El-Maaddawy, Tamer ;
Abed, Farid .
CONSTRUCTION AND BUILDING MATERIALS, 2020, 243
[4]   Bond durability of sand coated and ribbed basalt FRP bars embedded in high-strength concrete [J].
Al-Hamrani, Abathar ;
Alnahhal, Wael .
CONSTRUCTION AND BUILDING MATERIALS, 2023, 406
[5]  
Alkhrdaji T., 2004, Guide Test Methods for Fiber-Reinforced Polymers (FRPs) for Reinforcing or Strengthening Concrete Structures
[6]   Bond degradation of basalt fiber-reinforced polymer (BFRP) bars exposed to accelerated aging conditions [J].
Altalmas, Ahmad ;
El Refai, Ahmed ;
Abed, Farid .
CONSTRUCTION AND BUILDING MATERIALS, 2015, 81 :162-171
[7]  
[Anonymous], 2007, FRP reinforcement in RC structures
[8]  
[Anonymous], 2014, A. D7913/D7913M-14
[9]   Artificial intelligence and smart vision for building and construction 4.0: Machine and deep learning methods and applications [J].
Baduge, Shanaka Kristombu ;
Thilakarathna, Sadeep ;
Perera, Jude Shalitha ;
Arashpour, Mehrdad ;
Sharafi, Pejman ;
Teodosio, Bertrand ;
Shringi, Amkit ;
Mendis, Priyan .
AUTOMATION IN CONSTRUCTION, 2022, 141
[10]   Experimental study of bond behaviour between concrete and FRP bars using a pull-out test [J].
Baena, Marta ;
Torres, Lluis ;
Turon, Albert ;
Barris, Cristina .
COMPOSITES PART B-ENGINEERING, 2009, 40 (08) :784-797