Predicting the Compressive Strength of PVC-Confined Concrete via Machine Learning

Abstract

Polyvinyl Chloride (PVC) is a promising sustainable alternative to traditional materials for confining concrete in structural applications due to its corrosion resistance, durability, and cost-effectiveness. The present research is focused on the axial compressive strength of PVC-confined concrete short columns with machine learning models for superior predictive accuracy. A database gathered from FEA simulations was utilized to train the Artificial Neural Network (ANN) and Support Vector Machine (SVM) models, in which the performance of each model was compared with an available empirical formula. The ANN and SVM models could achieve a high predictive accuracy with R² values close to 1.0 and smaller RMSE values than those by traditional empirical approaches. Results have shown that machine-learning models succeed in capturing complex interactions among the parameters, including PVC thickness, column diameter, and concrete compressive strength, providing a versatile and powerful method for strength prediction. These models offer construction engineers a rapid, cost-effective tool for predicting PVC-confined concrete column strengths without extensive physical testing, potentially accelerating the adoption of sustainable materials in structural design. By reducing experimental costs and design time, the approach demonstrates significant practical value for innovative construction technologies.

Keywords

• Confined concrete
• Compressive strength
• PVC
• Machine learning
• Finite element analysis

PVC İle Sargılanmış Betonun Eksenel Basınç Dayanımının Makine Öğrenmesi İle Tahmini

Abstract

Polivinil Klorür (PVC), korozyon direnci, dayanıklılığı ve maliyet etkinliği sayesinde betonun yapı uygulamalarında sargılanması için geleneksel malzemelere bir alternatif olma potansiyeline sahip sürdürülebilir bir seçenektir. Bu araştırma, PVC ile sargılanmış beton kısa kolonların eksenel basınç dayanımı üzerine yoğunlaşmakta ve yüksek tahmin kapasiteli makine öğrenimi modelleri kullanılmaktadır. Sonlu Elemanlar Analizi (FEA) simülasyonlarından elde edilen bir veri tabanı kullanılarak, Yapay Sinir Ağı (YSA) ve Destek Vektör Makinesi (DVM) modelleri eğitilmiştir ve her modelin performansı mevcut bir ampirik modelle karşılaştırılmıştır. YSA ve DVM modelleri, 1.0’a yakın R² değerleri ve geleneksel ampirik yaklaşımlara kıyasla daha düşük RMSE değerleri ile yüksek tahmin doğruluğu elde edebilmiştir. Sonuçlar, makine öğrenimi modellerinin, PVC kalınlığı, kolon çapı ve beton basınç dayanımı gibi parametreler arasındaki karmaşık etkileşimleri başarılı bir şekilde yakalayarak dayanım tahmini için esnek ve güçlü bir yöntem sağladığını göstermiştir. Bu modeller, inşaat mühendislerine kapsamlı fiziksel testlere gerek kalmadan PVC ile sargılanmış beton kolon mukavemetlerini tahmin etmek için hızlı ve uygun maliyetli bir araç sunarak yapısal tasarımda sürdürülebilir malzemelerin benimsenmesini potansiyel olarak hızlandırmaktadır. Bu yaklaşım, deneysel maliyetleri ve tasarım süresini azaltarak yenilikçi inşaat teknolojileri için önemli bir pratik değer ortaya koymaktadır.

Keywords

• Sargılanmış beton
• Basınç dayanımı
• PVC
• Makine öğrenmesi
• Sonlu Elemanlar Analizi

References

1. Abbas, J. L. (2023). Structural behavior of concrete-filled double-skin PVC tubular columns confined by plain PVC sockets. Open Engineering, 13(1), 20220404.
2. Abdulla, N. A. (2017). Concrete filled PVC tube: A review. Construction and Building Materials, 156, 321–329.
3. Abdulla, N. A. (2021a). Concrete with an outer plastic protective shell: Axial and flexural performance. Structures, 29, 235–245.
4. Abdulla, N. A. (2021b). Simple equations for predicting the strength of slender plain and composite columns. Journal of Brilliant Engineering, 3, 4593.
5. Abdulla, N. A. (2021c). Strength models for uPVC-confined concrete. Construction and Building Materials, 310, 125070.
6. Abdulla, N. A. (2022a). Axial strength of short concrete-filled plastic tubes. Structures, 38, 102150.
7. Abdulla, N. A. (2022b). Recent developments in polyvinyl-chloride tube filled with concrete. Journal of Cement Based Composites, 3, 5555.
8. Abdulla, N. A. (2023). A state-of-art review of materials, methods, and applications of PVC-FRP-confined concrete. Construction and Building Materials, 363, 129719.

9. Alinejad, P., Khaloo, A., & Tale Masoule, M. S. (2021). Investigating the behavior of circular concrete-filled plastic tube columns under axial compression. Engineering Structures, 244, 112778.
10. Alves, L. M., & Martins, P. A. F. (2009). Cold expansion and reduction of thin-walled PVC tubes using a die. Journal of Materials Processing Technology, 209(9), 4229–4236.
11. Askari, S. M., Khaloo, A., Borhani, M. H., & Tale Masoule, M. S. (2020). Performance of polypropylene fiber reinforced concrete-filled UPVC tube columns under axial compression. Construction and Building Materials, 231, 117049.
12. Bazli, M., Ashrafi, H., & Oskouei, A. V. (2016). Effect of harsh environments on mechanical properties of GFRP pultruded profiles. Composites Part B: Engineering, 99, 203–215.
13. Bazli, M., Jafari, A., Ashrafi, H., Zhao, X. L., Bai, Y., & Raman, R. S. (2020). Effects of UV radiation, moisture, and elevated temperature on mechanical properties of GFRP pultruded profiles. Construction and Building Materials, 231, 117137.
14. Bishop, C. M. (2006). Pattern Recognition and Machine Learning. Springer.
15. Boser, B. E., Guyon, I. M., & Vapnik, V. N. (1992). A training algorithm for optimal margin classifiers. In Proceedings of the fifth annual workshop on Computational learning theory.
16. Červenka Consulting. (2021). ATENA Program Documentation Part 1 Theory. Prague, Czech Republic.
17. Çevik, A., Kurtoğlu, A. E., Bilgehan, M., Gülşan, M. E., & Albegmprli, H. M. (2015). Support vector machines in structural engineering: A review. Journal of Civil Engineering and Management, 21(3), 261–281.
18. Fakharifar, M., & Chen, G. (2016). Compressive behavior of FRP-confined concrete-filled PVC tubular columns. Composite Structures, 141, 91–109.
19. Fakharifar, M., & Chen, G. (2017). FRP-confined concrete-filled PVC tubes: A new design concept for ductile column construction in seismic regions. Construction and Building Materials, 130, 1–10.
20. Fang, Y., Yu, F., Guan, Y., Wang, Z., Feng, C., & Li, D. (2020). A model for predicting the stress-strain relation of PVC-CFRP confined concrete stub columns under axial compression. Structures, 25, 259–270.
21. Feng, Y., Li, Z., Fang, Y., Zhu, D., & Kong, Z. (2020). Mechanical behaviour of PVC-CFRP confined concrete column with RC beam joint subjected to axial load. Građevinar, 72(2), 89–99.
22. Goodfellow, I., Bengio, Y., & Courville, A. (2016). Deep Learning. MIT Press.
23. Gupta, A. (2013). Confinement of concrete columns with unplasticized polyvinyl chloride tubes. International Journal of Advanced Structural Engineering, 5(1), 19.
24. Haykin, S. (2009). Neural Networks and Learning Machines (3rd ed.). Pearson.
25. Isleem, H. F., Jagadesh, P., Qaidi, S., Althoey, F., Rahmawati, C., & Najm, H. M. S. (2022). Finite element and theoretical investigations on PVC–CFRP confined concrete columns under axial compression. Frontiers in Materials, 9, 1055397.
26. Isleem, H. F., Yusuf, B. O., Xingchong, W., Qiong, T., & Jagadesh, P. (2024). Analytical and numerical investigation of polyvinyl chloride (PVC) confined concrete columns under different loading conditions. Australian Journal of Structural Engineering, 25(1), 69–97.
27. Kumutha, R., & Vijai, K. (2016). External confinement of plain and reinforced concrete columns using PVC pipes. In Proceedings of 2nd International Conference on Structural Architecture and Civil Engineering. Dubai, UAE, 72–78.
28. LeCun, Y., Bengio, Y., & Hinton, G. (2015). Deep learning. Nature, 521(7553), 436–444.
29. Lu, Y., Li, N., Li, S., & Liang, H. (2015). Behavior of steel fiber reinforced concrete-filled steel tube columns under axial compression. Construction and Building Materials, 95, 74–85.
30. Mammen, A. M., & Antony, M. (2017). Experimental study on FRP-PVC confined circular columns. International Research Journal of Engineering and Technology, 4(5).
31. Masajedian, S. S. (2011). Experimental investigation of the behavior of the steel reinforced high-density polyethylene and corrugated metal pipe (Master's Thesis). University of Texas at Arlington.
32. Morozov, Y. K., Ashraf, E. V., & Shankar, K. (2014). Buckling behavior of reinforced thermoplastic pipes under combined external pressure and bending. In Proceedings of the 8th Australian Congress on Applied Mechanics (ACAM8). Melbourne, Australia.
33. Ozbakkaloglu, T., & Lim, J. C. (2013). Axial compressive behavior of FRP-confined concrete: Experimental test database and a new design-oriented model. Composites Part B: Engineering, 55, 607–634.
34. Raheemah, M. A., & Resan, S. F. (2019). Experimental investigation of concrete columns enhanced by PVC tubes. IOP Conference Series: Materials Science and Engineering, 584(1), 012047.
35. Raheemah, M. A., & Resan, S. F. (2020). Structural performance of concrete columns reinforced with PVC tubes and glass fiber reinforced polymer jackets. Journal of Physics: Conference Series, 1279(1), 012051.
36. Topal O. Modeling the behavior of concrete-filled PVC composite columns under axial compression (Master's Thesis). Iğdır University, Turkey; 2022.
37. Wang, Z., & Wang, X. (2014). Properties of PVC confined concrete stub columns. Građevinar, 66(6), 509–519.