Analyzing the Impact of Sustained Loading and Corrosion on the Structural Integrity of Reinforced Concrete Beams: a Hybrid Neural Network Approach
Keywords:
Flexural behaviour, Corroded concrete, Beams, Crack, Neural network, ANN-SVMAbstract
Deicing chemicals are used in different climates to keep the corrosion process going, and this global examination of the number of defective bridges makes it necessary to develop better analytical techniques for Reinforced Concrete (RC) components that have been corrupted. This research aims to explore the combined effects of prolonged loads and corrosion on the structural function of RC beams. This experimental study examined eight RC beams, including corroded and uncorroded ones, accelerated using impressed current technology. Four-point sustained bending loads applied to all the beams were equal to 16, 32, or 50% of the designed ultimate load, respectively. The degree of corrosion, fracture diameter and patterns, and mid-span beam deflection were measured throughout the test. The experimental tests are analyzed using Finite Element Analysis (FEA), but these studies are expensive, time-consuming, and require a high input error percentage. To estimate these inputs, a new Neural Network (NN) model as a hybrid of an Artificial Neural Network (ANN) and a Support Vector Machine (SVM) has been constructed in this study based on data from the literature. In addition to the hybrid's superior performance, it was discovered that the corrosion level influenced the beams to corrode more. In contrast, the beams' stiffness of corrosion via the accelerated process declined more rapidly with the same rebar mass loss rate. The main reasons the beams could not hold as much weight were the loss of cross-sectional area and the deterioration of the corroded rebar's mechanical features. Bond loss was mostly to blame for the drop in stiffness.
References
[1] Zhang, W., Shang, D., & Gu, X. (2006). Stress-strain relationship of corroded steel bars. Tongji daxue xuebao/journal of tongji university, 34(5), 586–592.
[2] Zhang, W., Zhang, H., Gu, X., & Liu, W. (2018). Structural behavior of corroded reinforced concrete beams under sustained loading. Construction and building materials, 174, 675–683.
[3] Mehta, P. K. (1994). Concrete technology at the crossroads--problems and opportunities. Special publication, 144, 1–30.
[4] Ballim, Y., & Reid, J. C. (2003). Reinforcement corrosion and the deflection of RC beams----an experimental critique of current test methods. Cement and concrete composites, 25(6), 625–632.
[5] Alonso, C., Andrade, C., Rodriguez, J., & Diez, J. M. (1998). Factors controlling cracking of concrete affected by reinforcement corrosion. Materials and structures, 31(7), 435–441.
[6] Andrade, C., & Alonso, C. (2001). On-site measurements of corrosion rate of reinforcements. Construction and building materials, 15(2–3), 141–145.
[7] Branson, D. E. (1976). Deformation of concrete structures. McGraw-Hill Companies.
[8] Kemp, E. L., & Wilhelm, W. J. (1979). Investigation of the parameters influencing bond cracking. Journal proceedings, 76(1), 47–72.
[9] Saifullah, M., & Clark, L. A. (1994). Effect of corrosion rate on the bond strength of corroded reinforcement. Corrosion and corrosion protection of steel in concrete, 1, 591–602.
[10] Rodriguez, J., Ortega, L. M., & Casal, J. (1994). Corrosion of reinforcing bars and service life of reinforced concrete structures: corrosion and bond deterioration. International conference on concrete across borders (Vol. 2, pp. 315–326). Odense, Denmark: Taylor & Francis, Abingdon, UK.
[11] Walraven, J. C., & Bigaj-van Vliet, A. J. (2008). A new future-oriented model code for concrete structures. Proceedings of the international fib symposium 2008 - tailor made concrete structures: new solutions for our society (p. 140). London: Taylor & Francis Group. DOI: 10.1201/9781439828410.ch101
[12] Collins, M. P., & Mitchell, D. (1987). Prestressed concrete basics. Canadian prestressed concrete institute.
[13] Association, C. S., & of Canada, S. C. (1994). A23.3-94 Design of concrete structures: structures (design). The Association.
[14] Zou, Z., Yang, G., & Su, T. (2020). Analytical model to predict residual flexural capacity of recycled aggregate concrete beams with corroded longitudinal rebars. Advances in materials science and engineering, 2020. DOI:10.1155/2020/3079892
[15] Jensen, C. A., Reed, R. D., Marks, R. J., El-Sharkawi, M. A., Jung, J.-B., Miyamoto, R. T., … ., & Eggen, C. J. (1999). Inversion of feedforward neural networks: algorithms and applications. Proceedings of the IEEE, 87(9), 1536–1549.
[16] Horak, J., Vrbka, J., & Suler, P. (2020). Support vector machine methods and artificial neural networks used for the development of bankruptcy prediction models and their comparison. Journal of risk and financial management, 13(3), 1-15.
[17] Horak, J., Vrbka, J., & Suler, P. (2020). Zieli, T. G. (1992). Introduction to the finite element method. Journal of risk and financial management, 13(3), 1–15. https://www.mdpi.com/1911-8074/13/3/60/pdf
[18] Zieli, T. G. (1992). Introduction to the finite element method. http://bluebox.ippt.pan.pl/~tzielins/doc/ICMM_TGZielinski_IntroFEM.Slides.pdf
Metrics
