Title: Artificial Intelligence Model for Fire Resistance of FRP-Strengthened Beams
Authors: Nima Khodadadi, M.Z Naser, Francisco De Caso, Antonio Nanni
DOI: 10.33599/nasampe/c.24.0257
Abstract: Fiber-reinforced polymers (FRP) have become increasingly popular as both primary and secondary reinforcement materials in concrete structures due to their significant advantages over traditional steel reinforcement. However, the fire resistance of concrete structures reinforced with Fiber-Reinforced Polymers (FRP) remains a significant concern, exacerbated by the lack of reliable fire test data and specific testing protocols. This issue is further complicated by the substantial time and cost required to conduct these tests. Additionally, no AI-based model currently utilizes this data to predict outcomes, which could save significant time and costs in assessing fire resistance of FRP-incorporated structures. Addressing this gap, this study develops the AI model for a comprehensive database of over 21,000 numerical data points on the fire performance of FRP-strengthened reinforced concrete beams. This database includes a wide range of parameters such as geometric dimensions, FRP-strengthening levels, steel reinforcement ratios, insulation configurations, material properties, and load levels, aiming to facilitate applying machine learning (ML) techniques in predicting total load applied on beams. Specifically, the study explores the enhancement of Artificial Neural Networks (ANNs) by integrating metaheuristic algorithm for optimizing network structures. The proposed approach in this paper optimizes parameters across a feed-forward backpropagation network, employing the Mountain Gazelle Optimization algorithm in tandem with ANN. The experimental results are subsequently evaluated using R-squared, MSE, RMSE, and MAPE metrics. The refined MGO-ANN approach boasts an impressive R-squared value of 0.8175. To make the findings accessible to practitioners, a graphical user interface (GUI) was developed, enabling users to input features and obtain predictions on the total load applied on beams in a user-friendly manner. This research not only fills a significant knowledge gap regarding the fire resistance of FRP-strengthened beams but also advances the use of ML in structural engineering by providing a reliable method for performance prediction.
References: [1] J. G. Teng et al., “Performance of insulated FRP-strengthened concrete flexural members under fire conditions,” Eng. Struct., vol. 105, no. 1, pp. 2201–2211, 2011. [2] H. A. Rasheed, Strengthening design of reinforced concrete with FRP. CRC Press, 2014. [3] A. Ahmed and V. Kodur, “The experimental behavior of FRP-strengthened RC beams subjected to design fire exposure,” Eng. Struct., vol. 33, no. 7, pp. 2201–2211, 2011. [4] P. P. Bhatt, V. K. R. Kodur, A. M. Shakya, and T. Alkhrdaji, “Performance of insulated FRP-strengthened concrete flexural members under fire conditions,” Front. Struct. Civ. Eng., vol. 15, pp. 177–193, 2021. [5] B. Williams, V. Kodur, M. F. Green, and L. Bisby, “Fire endurance of fiber-reinforced polymer strengthened concrete T-beams,” ACI Struct. J., vol. 105, no. 1, p. 60, 2008. [6] B. Williams, L. Bisby, V. Kodur, M. Green, and E. Chowdhury, “Fire insulation schemes for FRP-strengthened concrete slabs,” Compos. Part A Appl. Sci. Manuf., vol. 37, no. 8, pp. 1151–1160, 2006. [7] R. A. Hawileh, M. Naser, W. Zaidan, and H. A. Rasheed, “Modeling of insulated CFRP-strengthened reinforced concrete T-beam exposed to fire,” Eng. Struct., vol. 31, no. 12, pp. 3072–3079, 2009. [8] P. P. Bhatt, V. K. R. Kodur, and M. Z. Naser, “Dataset on fire resistance analysis of FRP-strengthened concrete beams,” Data Br., vol. 52, p. 110031, 2024. [9] V. K. R. Kodur and A. Ahmed, “Numerical model for tracing the response of FRP-strengthened RC beams exposed to fire,” J. Compos. Constr., vol. 14, no. 6, pp. 730–742, 2010. [10] V. K. R. Kodur and P. P. Bhatt, “A numerical approach for modeling response of fiber reinforced polymer strengthened concrete slabs exposed to fire,” Compos. Struct., vol. 187, pp. 226–240, 2018. [11] E. Golafshani, N. Khodadadi, T. Ngo, A. Nanni, and A. Behnood, “Modelling the compressive strength of geopolymer recycled aggregate concrete using ensemble machine learning,” Adv. Eng. Softw., vol. 191, p. 103611, 2024. [12] B. Yegnanarayana, Artificial neural networks. PHI Learning Pvt. Ltd., 2009. [13] B. Abdollahzadeh, F. S. Gharehchopogh, N. Khodadadi, and S. Mirjalili, “Mountain Gazelle Optimizer: A new Nature-inspired Metaheuristic Algorithm for Global Optimization Problems,” Adv. Eng. Softw., vol. 174, p. 103282, 2022. [14] N. Khodadadi, E.-S. M. El-Kenawy, F. De Caso, A. H. Alharbi, D. S. Khafaga, and A. Nanni, “The Mountain Gazelle Optimizer for truss structures optimization,” Appl. Comput. Intell., vol. 3, no. 2, pp. 116–144, 2023. [15] N. Khodadadi, H. Roghani, F. De Caso, E.-S. M. El-kenawy, Y. Yesha, and A. Nanni, “Data-Driven PSO-CatBoost Machine Learning Model to Predict the Compressive Strength of CFRP-Confined Circular Concrete Specimens,” Thin-Walled Struct., p. 111763, 2024.
Conference: CAMX 2024 | San Diego CA
Publication Date: 2024/9/9
SKU: TP24-0000000257
Pages: 15
Price: $30.00
Get This Paper