Explainable Data-Driven Ensemble Learning Models for the Mechanical Properties Prediction of Concrete Confined by Aramid Fiber-Reinforced Polymer Wraps Using Generative Adversarial Networks
Abstract
:1. Introduction
2. Predictive Equations and Machine Learning Models
2.1. Predictive Equations for the Compressive Strength and Ultimate Strain
2.2. Training of the Machine Learning Models
2.3. Machine Learning Methodologies
2.3.1. Gradient Boosting Methods
2.3.2. Tabular Generative Adversarial Networks (TGAN)
2.3.3. SHapley Additive exPlanations (SHAP)
3. Results
3.1. Performances of the Predictive Equations
3.2. Performances of the ML Models
3.3. SHAP Interpretation of the ML Models
3.4. Individual Conditional Expectation (ICE) Interpretation of the ML Models
4. Discussion
5. Conclusions
- To predict the ultimate strength and strain of AFRP-wrapped concrete columns, seven different predictive models were developed on datasets of 225 and 159 data points, respectively. The sizes of these datasets have been further increased using data points synthetically generated by generative adversarial networks.
- The machine learning techniques performed significantly better than the predictive equations adopted from the literature. Particularly, the extra trees, XGBoost, and KNN models were the best performing models in the prediction of the ultimate strength and ultimate strain.
- The unconfined ultimate strength of concrete and the elasticity modulus of AFRP were found to have the greatest and least impact on the predicted values, respectively. Plots of individual conditional expectations (ICE) and feature dependency were used to illustrate the increasing impact of unconfined ultimate strength on confined ultimate strength. In certain ranges the unconfined ultimate strength was shown to have a decreasing effect on the ultimate strain of the specimens.
- The ultimate tensile strength of AFRP and the column diameter were found to have the greatest and least impact on the predicted values, respectively.
- The variations of the predicted ultimate strength and ultimate strain values, with respect to the most impactful input features, were visualized using ICE plots.
- It was shown that the equations in the literature can significantly overestimate the compressive strength and ultimate strain of confined concrete.
Supplementary Materials
Funding
Data Availability Statement
Conflicts of Interest
References
- Green, M.F.; Bisby, L.A.; Fam, A.Z.; Kodur, V.K. FRP confined concrete columns: Behaviour under extreme conditions. Cem. Concr. Compos. 2006, 28, 928–937. [Google Scholar] [CrossRef]
- Parvin, A.; Brighton, D. FRP Composites Strengthening of Concrete Columns under Various Loading Conditions. Polymers 2014, 6, 1040–1056. [Google Scholar] [CrossRef]
- Arabshahi, A.; Gharaei-Moghaddam, N.; Tavakkolizadeh, M. Development of applicable design models for concrete columns confined with aramid fiber reinforced polymer using Multi-Expression Programming. Structures 2020, 23, 225–244. [Google Scholar] [CrossRef]
- Shih, C.-H.; You, J.-L.; Lee, Y.-L.; Cheng, A.-Y.; Chang, C.-P.; Liu, Y.-M.; Ger, M.-D. Design and Ballistic Performance of Hybrid Plates Manufactured from Aramid Composites for Developing Multilayered Armor Systems. Polymers 2022, 14, 5026. [Google Scholar] [CrossRef] [PubMed]
- Alkhatib, F.; Mahdi, E.; Dean, A. Design and Evaluation of Hybrid Composite Plates for Ballistic Protection: Experimental and Numerical Investigations. Polymers 2021, 13, 1450. [Google Scholar] [CrossRef]
- Lee, Y.S.; Wetzel, E.D.; Wagner, N.J. The ballistic impact characteristics of Kevlar® woven fabrics impregnated with a colloidal shear thickening fluid. J. Mater. Sci. 2003, 38, 2825–2833. [Google Scholar] [CrossRef]
- Wang, X.; Zhang, J.; Bao, L.; Yang, W.; Zhou, F.; Liu, W. Enhancement of the ballistic performance of aramid fabric with polyurethane and shear thickening fluid. Mater. Des. 2020, 196, 109015. [Google Scholar] [CrossRef]
- Meliande, N.M.; Oliveira, M.S.; Silveira, P.H.P.M.d.; Dias, R.R.; Marçal, R.L.S.B.; Monteiro, S.N.; Nascimento, L.F.C. Curaua–Aramid Hybrid Laminated Composites for Impact Applications: Flexural, Charpy Impact and Elastic Properties. Polymers 2022, 14, 3749. [Google Scholar] [CrossRef]
- Khedmatgozar Dolati, S.S.; Mehrabi, A. FRP sheet/jacket system as an alternative method for splicing prestressed-precast concrete piles. Case Stud. Constr. Mater. 2022, 16, e00912. [Google Scholar] [CrossRef]
- Khedmatgozar Dolati, S.S.; Mehrabi, A. NSM FRP pile-splice system for prestressed precast concrete piles. Pract. Period. Struct. Des. Constr. 2022, 27, 04022046. [Google Scholar] [CrossRef]
- Tin, H.-X.; Thuy, N.-T.; Seo, S.-Y. Structural Behavior of RC Column Confined by FRP Sheet under Uniaxial and Biaxial Load. Polymers 2022, 14, 75. [Google Scholar] [CrossRef] [PubMed]
- Choi, E.; Jeon, J.S.; Cho, B.S.; Park, K. External jacket of FRP wire for confining concrete and its advantages. Eng. Struct. 2013, 56, 555–566. [Google Scholar] [CrossRef]
- Iacobucci, R.D.; Sheikh, S.A.; Bayrak, O. Retrofit of square concrete columns with carbon fiber-reinforced polymer for seismic resistance. Struct. J. 2003, 100, 785–794. [Google Scholar]
- Yang, H.; Song, H.; Zhang, S. Experimental investigation of the behavior of aramid fiber reinforced polymer confined concrete subjected to high strain-rate compression. Constr. Build. Mater. 2015, 95, 143–151. [Google Scholar] [CrossRef]
- Xie, D.; Hu, Z.; Wang, B.; Zhao, K.; Shi, Y. Axial behavior of basalt FRP-confined reinforced concrete columns with square sections of different corner radii. Eng. Struct. 2023, 274, 115153. [Google Scholar] [CrossRef]
- Sharma, S.S.; Dave, U.V.; Solanki, H. FRP Wrapping for RC Columns with Varying Corner Radii. Procedia Eng. 2013, 51, 220–229. [Google Scholar] [CrossRef]
- Pour, A.F.; Ozbakkaloglu, T.; Vincent, T. Simplified design-oriented axial stress-strain model for FRP-confined normal-and high-strength concrete. Eng. Struct. 2018, 175, 501–516. [Google Scholar] [CrossRef]
- Pham, T.M.; Hadi, M.N. Confinement model for FRP confined normal-and high-strength concrete circular columns. Constr. Build. Mater. 2014, 69, 83–90. [Google Scholar] [CrossRef]
- Lam, L.; Teng, J.G. Design-oriented stress–strain model for FRP-confined concrete. Constr. Build. Mater. 2003, 17, 471–489. [Google Scholar] [CrossRef]
- Wei, Y.Y.; Wu, Y.F. Unified stress–strain model of concrete for FRP-confined columns. Constr. Build. Mater. 2012, 26, 381–392. [Google Scholar] [CrossRef]
- Wu, H.L.; Wang, Y.F.; Yu, L.; Li, X.R. Experimental and computational studies on high-strength concrete circular columns confined by aramid fiber-reinforced polymer sheets. J. Compos. Constr. 2009, 13, 125–134. [Google Scholar] [CrossRef]
- Wang, Y.F.; Wu, H.L. Size effect of concrete short columns confined with aramid FRP jackets. J. Compos. Constr. 2010, 15, 535–544. [Google Scholar] [CrossRef]
- Djafar-Henni, I.; Kassoul, A. Stress–strain model of confined concrete with Aramid FRP wraps. Constr. Build. Mater. 2018, 186, 1016–1030. [Google Scholar] [CrossRef]
- Lobo, P.S.; Faustino, P.; Jesus, M.; Marreiros, R. Design model of concrete for circular columns confined with AFRP. Compos. Struct. 2018, 200, 69–78. [Google Scholar] [CrossRef]
- Song, H.; Ahmad, A.; Farooq, F.; Ostrowski, K.A.; Maślak, M.; Czarnecki, S.; Aslam, F. Predicting the compressive strength of concrete with fly ash admixture using machine learning algorithms. Constr. Build. Mater. 2021, 308, 125021. [Google Scholar] [CrossRef]
- Song, H.; Ahmad, A.; Ostrowski, K.A.; Dudek, M. Analyzing the Compressive Strength of Ceramic Waste-Based Concrete Using Experiment and Artificial Neural Network (ANN) Approach. Materials 2021, 14, 4518. [Google Scholar] [CrossRef]
- Anjum, M.; Khan, K.; Ahmad, W.; Ahmad, A.; Amin, M.N.; Nafees, A. Application of Ensemble Machine Learning Methods to Estimate the Compressive Strength of Fiber-Reinforced Nano-Silica Modified Concrete. Polymers 2022, 14, 3906. [Google Scholar] [CrossRef]
- Ahmad, A.; Ahmad, W.; Aslam, F.; Joyklad, P. Compressive strength prediction of fly ash-based geopolymer concrete via advanced machine learning techniques. Case Stud. Constr. Mater. 2022, 16, e00840. [Google Scholar] [CrossRef]
- Shang, M.; Li, H.; Ahmad, A.; Ahmad, W.; Ostrowski, K.A.; Aslam, F.; Joyklad, P.; Majka, T.M. Predicting the Mechanical Properties of RCA-Based Concrete Using Supervised Machine Learning Algorithms. Materials 2022, 15, 647. [Google Scholar] [CrossRef]
- Ahmad, A.; Chaiyasarn, K.; Farooq, F.; Ahmad, W.; Suparp, S.; Aslam, F. Compressive Strength Prediction via Gene Expression Programming (GEP) and Artificial Neural Network (ANN) for Concrete Containing RCA. Buildings 2021, 11, 324. [Google Scholar] [CrossRef]
- Farooq, F.; Nasir Amin, M.; Khan, K.; Rehan Sadiq, M.; Faisal Javed, M.; Aslam, F.; Alyousef, R. A Comparative Study of Random Forest and Genetic Engineering Programming for the Prediction of Compressive Strength of High Strength Concrete (HSC). Appl. Sci. 2020, 10, 7330. [Google Scholar] [CrossRef]
- Amin, M.N.; Ahmad, A.; Khan, K.; Ahmad, W.; Nazar, S.; Faraz, M.I.; Alabdullah, A.A. Split Tensile Strength Prediction of Recycled Aggregate-Based Sustainable Concrete Using Artificial Intelligence Methods. Materials 2022, 15, 4296. [Google Scholar] [CrossRef] [PubMed]
- Nanni, A.; Bradford, N.M. FRP jacketed concrete under uniaxial compression. Constr. Build. Mater. 1995, 9, 115–124. [Google Scholar] [CrossRef]
- Watanabe, K.; Nakamura, H.; Honda, Y.; Toyoshima, M. Confinement Effect of FRP Sheet on Strength and Ductility of Concrete Cylinders under Uniaxial Compression. In Non-Metallic (FRP) Reinforcement for Concrete Structures; Japan Concrete Institute: Tokyo, Japan, 1997; Volume 1, pp. 233–240. [Google Scholar]
- Rochette, P.; Labossiere, P. Axial testing of rectangular column models confined with composites. J. Compos. Constr. 2000, 4, 129–136. [Google Scholar] [CrossRef]
- Suter, R.; Pinzelli, R. Confinement of Concrete columns with FRP sheets. In Proceedings of the Fifth International Conference on Fiber Reinforced Plastics for Reinforced Concrete Structures, Cambridge, UK, 16–18 July 2001. [Google Scholar]
- Toutanji, H.; Deng, Y. Strength and durability performance of concrete axially loaded members confined with AFRP composite sheets. Compos. Part B Eng. 2002, 33, 255–261. [Google Scholar] [CrossRef]
- Miller, C.; Rohrlach, D.; Staak, A.; Verma, K. Behaviour of Fibre Reinforced Polymer Confined High Strength Concrete under Axial Cyclic Compression. Ph.D. Thesis, The School of Civil, Environmental and Mining Engineering, The University of Adelaide, Adelaide, Australia, 2007. [Google Scholar]
- Wu, G.; Wu, Z.S.; Lu, Z.T.; Ando, Y.B. Structural Performance of Concrete Confined with Hybrid FRP Composites. J. Reinf. Plast. Compos. 2008, 27, 1323–1348. [Google Scholar] [CrossRef]
- Wang, G. Compressive Behaviour of Concrete Confined by Aramid FRP Tubes. Master’s Thesis, The School of Civil, Environmental and Mining Engineering, The University of Adelaide, Adelaide, Australia, 2008. [Google Scholar]
- Wang, Y.; Zhang, D. Creep-effect on mechanical behavior of concrete confined by FRP under axial compression. J. Eng. Mech. 2009, 135, 1315–1322. [Google Scholar] [CrossRef]
- Ozbakkaloglu, T.; Akin, E. Behavior of FRP-confined normal-and high-strength concrete under cyclic axial compression. J. Compos. Constr. 2012, 16, 451–463. [Google Scholar] [CrossRef]
- Dai, J.G.; Bai, Y.L.; Teng, J.G. Behavior and modeling of concrete confined with FRP composites of large deformability. J. Compos. Constr. 2011, 15, 963–973. [Google Scholar] [CrossRef]
- Cheek, J.; Formichella, N.; Graetz, D.; Varasteh, S. The Behavior of Ultra-High Strength Concrete in FRP Confined Concrete Systems under Axial Compression. Bachelor’s Thesis, The School of Civil, Environmental and Mining Engineering, The University of Adelaide, Adelaide, Australia, 2011. [Google Scholar]
- Vincent, T.; Ozbakkaloglu, T. Influence of fiber orientation and specimen end condition on axial compressive behavior of FRP-confined concrete. Constr. Build. Mater. 2013, 47, 814–826. [Google Scholar] [CrossRef]
- Ozbakkaloglu, T.; Vincent, T. Axial compressive behavior of circular high-strength concrete-filled FRP tubes. J. Compos. Constr. 2014, 18, 04013037. [Google Scholar] [CrossRef]
- Ozbakkaloglu, T. Compressive behavior of concrete-filled FRP tube columns: Assessment of critical column parameters. Eng. Struct. 2013, 51, 188–199. [Google Scholar] [CrossRef]
- Vincent, T.; Ozbakkaloglu, T. Influence of slenderness on stress-strain behavior of concrete-filled FRP tubes: Experimental study. J. Compos. Constr. 2015, 19, 04014029. [Google Scholar] [CrossRef]
- Lim, J.C.; Ozbakkaloglu, T. Hoop strains in FRP-confined concrete columns: Experimental observations. Mater Struct 2015, 48, 2839–2854. [Google Scholar] [CrossRef]
- Fekri, M.N.; Ghosh, A.M.; Grolinger, K. Generating Energy Data for Machine Learning with Recurrent Generative Adversarial Networks. Energies 2020, 13, 130. [Google Scholar] [CrossRef]
- Marani, A.; Nehdi, M.L. Predicting shear strength of FRP-reinforced concrete beams using novel synthetic data driven deep learning. Eng. Struct. 2022, 257, 114083. [Google Scholar] [CrossRef]
- Goodfellow, I.; Pouget-Abadie, J.; Mirza, M.; Xu, B.; Warde-Farley, D.; Ozair, S.; Courville, A.; Bengio, Y. Generative Adversarial Nets. In Proceedings of the Advances in Neural Information Processing Systems 27 (NIPS 2014), Montreal, QC, Canada, 8–13 December 2014. [Google Scholar]
- Xu, L.; Skoularidou, M.; Cuesta-Infante, A.; Veeramachaneni, K. Modeling Tabular data using Conditional GAN. In Proceedings of the Advances in Neural Information Processing Systems 32 (NeurIPS 2019), Vancouver, ON, Canada, 8–14 December 2019. [Google Scholar]
- Cakiroglu, C.; Shahjalal, M.; Islam, K.; Mahmood, S.F.; Billah, A.M.; Nehdi, M.L. Explainable ensemble learning data-driven modeling of mechanical properties of fiber-reinforced rubberized recycled aggregate concrete. J. Build. Eng. 2023, 76, 107279. [Google Scholar] [CrossRef]
- Mangalathu, S.; Karthikeyan, K.; Feng, D.C.; Jeon, J.S. Machine-learning interpretability techniques for seismic performance assessment of infrastructure systems. Eng. Struct. 2022, 250, 112883. [Google Scholar] [CrossRef]
- Somala, S.N.; Chanda, S.; Karthikeyan, K.; Mangalathu, S. Explainable Machine learning on New Zealand strong motion for PGV and PGA. Structures 2021, 34, 4977–4985. [Google Scholar] [CrossRef]
- Mangalathu, S.; Hwang, S.H.; Jeon, J.S. Failure mode and effects analysis of RC members based on machine-learning-based SHapley Additive exPlanations (SHAP) approach. Eng. Struct. 2020, 219, 110927. [Google Scholar] [CrossRef]
- Feng, D.C.; Wang, W.J.; Mangalathu, S.; Taciroglu, E. Interpretable XGBoost-SHAP machine-learning model for shear strength prediction of squat RC walls. J. Struct. Eng. 2021, 147, 04021173. [Google Scholar] [CrossRef]
- Wakjira, T.G.; Rahmzadeh, A.; Alam, M.S.; Tremblay, R. Explainable machine learning based efficient prediction tool for lateral cyclic response of post-tensioned base rocking steel bridge piers. Structures 2022, 44, 947–964. [Google Scholar] [CrossRef]
- Lundberg, S.M.; Lee, S.-I. A unified approach to interpreting model predictions. In Proceedings of the 31st Conference on 577 Neural Information Processing Systems (NIPS 2017), Long Beach, CA, USA, 4–9 December 2017. [Google Scholar]
Variable | Min. | Max. | Mean | Standard Dev. | Skewness | Kurtosis |
---|---|---|---|---|---|---|
[MPa] | 18.9 | 119.3 | 67.55 | 29.24 | 0.191 | −1.344 |
d [mm] | 70 | 200 | 130.9 | 40.07 | 0.118 | −1.062 |
L [mm] | 152 | 762 | 368.3 | 190.3 | 1.124 | −0.055 |
[MPa] | 230 | 3732 | 2318 | 859.8 | −0.934 | 0.513 |
[GPa] | 13.6 | 128.5 | 101.5 | 32.35 | −1.575 | 1.222 |
[mm] | 0.057 | 5.21 | 0.919 | 1.115 | 2.252 | 4.613 |
[MPa] | 35.16 | 244.6 | 114.3 | 49.20 | 0.601 | −0.373 |
[%] | 0.24 | 4.78 | 1.924 | 1.016 | 0.328 | −0.645 |
Equation | MAE [MPa] | RMSE [MPa] | |
---|---|---|---|
Wu et al. [21] | 0.7610 | 31.34 | 43.17 |
Wang and Wu [22] | 0.6592 | 72.44 | 104.8 |
Djafar-Henni and Kassoul [23] | 0.6527 | 41.79 | 51.48 |
Lobo et al. [24] | 0.7647 | 29.56 | 41.05 |
Algorithm | R2 | MAE [MPa] | RMSE [MPa] | Duration [s] | |||
---|---|---|---|---|---|---|---|
Train | Test | Train | Test | Train | Test | ||
XGBoost | 0.9792 | 0.9371 | 2.530 | 6.135 | 7.080 | 12.16 | 5.24 |
CatBoost | 0.9232 | 0.9064 | 9.965 | 10.01 | 13.61 | 14.84 | 12.62 |
Random Forest | 0.8729 | 0.9228 | 13.17 | 8.343 | 17.52 | 13.47 | 6.47 |
LightGBM | 0.7894 | 0.8837 | 17.10 | 11.65 | 22.55 | 16.54 | 9.59 |
Extra trees | 0.9799 | 0.9383 | 1.812 | 5.438 | 6.958 | 12.05 | 7.26 |
KNN | 0.9510 | 0.9090 | 3.091 | 6.182 | 10.35 | 14.63 | 4.70 |
SVR | 0.2849 | 0.3063 | 30.74 | 34.70 | 40.29 | 43.16 | 0.01 |
Algorithm | R2 | MAE [%] | RMSE [%] | Duration [s] | |||
---|---|---|---|---|---|---|---|
Train | Test | Train | Test | Train | Test | ||
XGBoost | 0.9966 | 0.9879 | 0.0303 | 0.0708 | 0.0579 | 0.1076 | 5.64 |
CatBoost | 0.9508 | 0.9385 | 0.1677 | 0.1857 | 0.2169 | 0.2471 | 15.37 |
Random Forest | 0.9694 | 0.8863 | 0.1306 | 0.2606 | 0.1711 | 0.3362 | 7.93 |
LightGBM | 0.9242 | 0.8155 | 0.2228 | 0.3378 | 0.2693 | 0.4278 | 11.59 |
Extra trees | 0.9962 | 0.9899 | 0.0117 | 0.0485 | 0.0480 | 0.0979 | 5.16 |
KNN | 0.9968 | 0.9862 | 0.0129 | 0.0537 | 0.0564 | 0.1148 | 4.28 |
SVR | 0.8547 | 0.7084 | 0.2628 | 0.4445 | 0.3640 | 0.5665 | 3.17 |
Disclaimer/Publisher’s Note: The statements, opinions and data contained in all publications are solely those of the individual author(s) and contributor(s) and not of MDPI and/or the editor(s). MDPI and/or the editor(s) disclaim responsibility for any injury to people or property resulting from any ideas, methods, instructions or products referred to in the content. |
© 2023 by the author. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
Share and Cite
Cakiroglu, C. Explainable Data-Driven Ensemble Learning Models for the Mechanical Properties Prediction of Concrete Confined by Aramid Fiber-Reinforced Polymer Wraps Using Generative Adversarial Networks. Appl. Sci. 2023, 13, 11991. https://doi.org/10.3390/app132111991
Cakiroglu C. Explainable Data-Driven Ensemble Learning Models for the Mechanical Properties Prediction of Concrete Confined by Aramid Fiber-Reinforced Polymer Wraps Using Generative Adversarial Networks. Applied Sciences. 2023; 13(21):11991. https://doi.org/10.3390/app132111991
Chicago/Turabian StyleCakiroglu, Celal. 2023. "Explainable Data-Driven Ensemble Learning Models for the Mechanical Properties Prediction of Concrete Confined by Aramid Fiber-Reinforced Polymer Wraps Using Generative Adversarial Networks" Applied Sciences 13, no. 21: 11991. https://doi.org/10.3390/app132111991