Ensemble learning based approach for FRP-concrete bond strength prediction

Abstract Nowadays, externally bonding fiber reinforced polymer (FRP) plates or sheets have become a major maintenance approach for aged reinforced concrete flexure structures. However, the capacity of strengthend structure cannot be precisely estimated as a result of the critical FRP-concrete interfacial (FCI) bond strength unpredictable. In order to solve this issue, many experimental studies have been carried out with corresponding emipirical models proposed. Due to limited experiment samples, these models were found more or less lacking the generalization ability. Under this circumstance, in this study, an ensemble learning algorithm “gradient boosted regression trees” (GBRT) was employed to develop a prediction model for FCI bond strength prediction based on a collected comprehensive database containing 520 tested samples. The model’s performance has been thoroughly compared with the representative empirical models and the common utilized machine learning algorithms. The rationality of this model has also been discussed through feature importance analysis. The results showed that the model in this study exhibits the highest accuracy and is proven to be feasible for predicting FCI bond strength in actual practice.

[1]  Trevor Hastie,et al.  The Elements of Statistical Learning , 2001 .

[2]  D. Mostofinejad,et al.  Effective bond length of FRP-to-concrete adhesively-bonded joints: Experimental evaluation of existing models , 2014 .

[3]  Mohammad Reza Azadi Kakavand,et al.  Data-Driven Approach to Predict the Plastic Hinge Length of Reinforced Concrete Columns and Its Application , 2021 .

[4]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[5]  Jack Chin Pang Cheng,et al.  Identifying the influential features on the regional energy use intensity of residential buildings based on Random Forests , 2016 .

[6]  Thomas G. Dietterich.  Machine-Learning Research , 1997, AI Mag..

[7]  Qingda Yang,et al.  On shear bond strength of FRP-concrete structures , 2010 .

[8]  S. M. Hamze-Ziabari,et al.  Predicting Bond Strength between FRP Plates and Concrete Sub-strate: Applications of GMDH and MNLR Approaches , 2017 .

[9]  Christian Carloni,et al.  Investigation of sub-critical fatigue crack growth in FRP/concrete cohesive interface using digital image analysis , 2013 .

[10]  K. Zilch,et al.  Beiträge im fib-Bulletin 14: Externally bonded FRP Reinforcement for RC Structures , 2001 .

[11]  L. Hollaway.  A review of the present and future utilisation of FRP composites in the civil infrastructure with reference to their important in-service properties , 2010 .

[12]  D. R. Eidgahee,et al.  A new and robust hybrid artificial bee colony algorithm – ANN model for FRP-concrete bond strength evaluation , 2020 .

[13]  Zeyu Wang,et al.  Random Forest based hourly building energy prediction , 2018, Energy and Buildings.

[14]  D. Mostofinejad,et al.  A generic non-linear bond-slip model for CFRP composites bonded to concrete substrate using EBR and EBROG techniques , 2019, Composite Structures.

[15]  Miao Su,et al.  Selected machine learning approaches for predicting the interfacial bond strength between FRPs and concrete , 2020 .

[16]  Deric J. Oehlers,et al.  Generic Debonding Resistance of EB and NSM Plate-to-Concrete Joints , 2007 .

[17]  Gang Hu,et al.  Implementing ensemble learning methods to predict the shear strength of RC deep beams with/without web reinforcements , 2021 .

[18]  Sang-Kyun Woo,et al.  Experimental study on interfacial behavior of CFRP-bonded concrete , 2010 .

[19]  Jian fei Chen,et al.  Experimental study on FRP-to-concrete bonded joints , 2005 .

[20]  Matthew B. Blaschko,et al.  Externally bonded FRP reinforcement for RC structures , 2001 .

[21]  Tamon Ueda,et al.  Development of the Nonlinear Bond Stress-Slip Model of Fiber Reinforced Plastics Sheet-Concrete Interfaces with a Simple Method , 2005 .

[22]  Ali Lahouar,et al.  Hour-ahead wind power forecast based on random forests , 2017 .

[23]  De-Cheng Feng,et al.  A machine learning-based time-dependent shear strength model for corroded reinforced concrete beams , 2021 .

[24]  X. Zhao,et al.  State-of-the-art review on FRP strengthened steel structures , 2007 .

[25]  Claudio Mazzotti,et al.  Experimental determination of FRP–concrete cohesive interface properties under fatigue loading , 2012 .

[26]  Scott T Smith,et al.  Design handbook for RC structures retrofitted with FRP and metal plates: beams and slabs HB 305-2008 , 2008 .

[27]  K. Neale,et al.  Transfer Lengths and Bond Strengths for Composites Bonded to Concrete , 1999 .

[28]  F. Xing,et al.  Mechanism of surface preparation on FRP-Concrete bond performance: A quantitative study , 2019, Composites Part B: Engineering.

[29]  Michel Ghosn,et al.  Experimental Investigation and Fracture Analysis of Debonding between Concrete and FRP Sheets , 2006 .

[30]  Jian fei Chen,et al.  Anchorage strength models for FRP and steel plates bonded to concrete , 2001 .

[31]  C. Leung,et al.  Coupling effect of concrete strength and bonding length on bond behaviors of fiber reinforced polymer–concrete interface , 2015 .

[32]  Wei Dongfang,et al.  Machine learning-based compressive strength prediction for concrete: An adaptive boosting approach , 2020, Construction and Building Materials.

[33]  G. Monti,et al.  FRP ADHESION IN UNCRACKED AND CRACKED CONCRETE ZONES , 2003 .

[34]  De-Cheng Feng,et al.  Failure mode classification and bearing capacity prediction for reinforced concrete columns based on ensemble machine learning algorithm , 2020, Adv. Eng. Informatics.

[35]  Francesco Micelli,et al.  Analytical model based on artificial neural network for masonry shear walls strengthened with FRM systems , 2016 .

[36]  Geoffrey E. Hinton,et al.  Rectified Linear Units Improve Restricted Boltzmann Machines , 2010, ICML.

[37]  U. Neubauer,et al.  DESIGN ASPECTS OF CONCRETE STRUCTURES STRENGTHENED WITH EXTERNALLY BONDED CFRP-PLATES , 1997 .

[38]  Qiang Han,et al.  Data-driven ultimate conditions prediction and stress-strain model for FRP-confined concrete , 2020 .

[39]  D. Mostofinejad,et al.  Effects of coarse aggregate volume on CFRP-concrete bond strength and behavior , 2019, Construction and Building Materials.

[40]  Wensu Chen,et al.  Effect of aggregate size on bond behaviour between basalt fibre reinforced polymer sheets and concrete , 2019, Composites Part B: Engineering.

[41]  Juncheng Gao,et al.  Evaluating the bond strength of FRP in concrete samples using machine learning methods , 2020 .