Prediction of the Residual Compressive Strength of Rice Husk Ash Concrete after Exposure to Elevated Temperatures Using XGBoost Machine Learning Algorithm

Elvis Ang'ang'o; Silvester Abuodha; Siphila   Mumenya

doi:10.25077/aijaset.v4i3.187

Authors

Elvis Ang'ang'o University of Nairobi, Kenya
Silvester Abuodha University of Nairobi, Kenya
Siphila Mumenya University of Nairobi, Kenya

DOI:

https://doi.org/10.25077/aijaset.v4i3.187

Abstract

The study aimed to assess the applicability of XGBoost in determining the residual compressive strength of rice husk ash concrete exposed to elevated temperature, reducing the need for costly, time-consuming laboratory experiments. Data was collected from the available literature, with 75% used for training and 25% for testing. Synthetic data was created using the Wasserstein Generative Adversarial Network with Gradient Penalty (WGAN-GP). The model accuracy was checked using statistical scores: coefficient of determination (R²), root mean squared error (RMSE), and mean absolute error (MAE). SHAP values were used for feature importance analysis. Coding was done in Python using Jupyter Notebook. With the original data, the model produced RMSE, R², and MAE test values of 3.351, 0.939, and 2.994, respectively, indicating excellent performance. The combined original and synthetic dataset gave RMSE, R², and MAE values of 0.071, 0.941, and 0.053, respectively, signifying improved performance. The feature analysis identified higher temperature, unheated compressive strength, and water-cement ratio as the most significant factors in the XGBoost prediction. The exposure duration, alumina content, and iron oxide had minimal influence.

Author Biographies

Elvis Ang'ang'o, University of Nairobi, Kenya

Department of Civil & Construction Engineering, University of Nairobi, Kenya

Silvester Abuodha, University of Nairobi, Kenya

Department of Civil & Construction Engineering, University of Nairobi, Kenya

Siphila Mumenya, University of Nairobi, Kenya

Department of Civil & Construction Engineering, University of Nairobi, Kenya

References

H. M. Owaid, R. B. Hamid, and M. R. Taha, “A Review of Sustainable Supplementary Cementitious Materials as an Alternative to All-Portland Cement Mortar and Concrete,” Australian Journal of Basic and Applied Sciences, vol. 6, no. 9, pp. 287–303, 2012.

A. Hossain, M. H. Rashid, O. U. Laz, and M. Rahman, “Effect of Rice Husk Ash on Concrete,” in WasteSafe 2011, Khulna, Bangladesh, 2011.

S. A. Zareei, F. Ameri, F. Dorostkar, and M. Ahmadi, “Rice husk ash as a partial replacement of cement in high strength concrete containing micro silica: Evaluating durability and mechanical properties,” Case Studies in Construction Materials, vol. 7, no. 7, pp. 73–81, 2017.

M.-H. Zhang and V. M. Malhotra, “High-Performance Concrete Incorporating Rice Husk Ash as a Supplementary Cementing Material,” ACI Materials Journal, vol. 93, no. 6, pp. 629–636, 1996.

A. Ahmad, K. A. Ostrowski, M. Maslak, F. Farooq, I. Mehmood, and A. Nafees, “Comparative Study of Supervised Machine Learning Algorithms for Predicting the Compressive Strength of Concrete at High Temperature,” Materials, vol. 14, no. 4222, Jul. 2021.

M. Ahmad et al., “Supervised Learning Methods for Modeling Concrete Compressive Strength Prediction at High Temperature,” Materials, vol. 14, no. 1983, Apr. 2021.

M. Rahmati and V. Toufigh, “Evaluation of Geopolymer Concrete at High Temperatures: An Experimental Study using Machine Learning,” Journal of Cleaner Production, vol. 372, 2022.

C. Cakiroglu, “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., vol. 13, no. 11991, Nov. 2023.

M. K. H. Al-Majidi, “Effects of Exposure to Elevated Temperatures on Properties of Concrete Containing Rice Husk Ash,” University of Malaysia, 2011.

R. Umasabor and J. O. Okovido, “Fire Resistance Evaluation of Rice Husk Ash Concrete,” Heliyon, vol. 4, no. e01035, Dec. 2018.

W. H. Wang, Y. F. Meng, and D. Z. Wang, “Effect of Rice Husk Ash on High-Temperature Mechanical Properties and Microstructure of Concrete,” Kemija U Industriji, vol. 66, no. 3–4, pp. 157–164, 2017.

H. Nguyen, T. Vu, T. P. Vo, and H.-T. Thai, “Efficient Machine Learning Models for Prediction of Concrete Strengths,” Construction and Building Materials, vol. 266, Oct. 2020.

T. Chen and C. Guestrin, “XGBoost: A Scalable Tree Boosting System,” in Proceedings of the 22nd ACM SIGKDD International Conference, San Francisco, California, USA: ACM, Aug. 2016.

T. Nguyen-Sy, J. Wakim, Q.-D. To, M.-N. Vu, T.-D. Nguyen, and T.-T. Nguyen, “Predicting the Compressive Strength of Concrete from its Compositions and Age using the Extreme Gradient Boosting Method,” Construction and Building Materials, vol. 260, 2020.

S. Watanabe, “Tree-Structured Parzen Estimator: Understanding Its Algorithm Components and Their Roles for Better Empirical Performance,” Germany, Tutorial paper arXiv:2304.11127v3 [cs.LG], May 2023.

N.-H. Nguyen, J. Abellan-Garcia, S. Lee, E. Garcia-Castano, and T. P. Vo, “Efficient Estimating Compressive Strength of Ultra-High-Performance Concrete using XGBoost Model,” Journal of Building Engineering, vol. 52, Mar. 2022.

S. Lundberg and S. Lee, “A Unified Approach to Interpreting Model Predictions,” arXiv:1705.07874v2, vol. [cs.AI], Nov. 2017.

S. Lundberg, G. Erion, and S. Lee, “Consistent Individualized Feature Attribution for Tree Ensembles,” arXiv:1802.03888, vol. [cs.LG], Mar. 2019.

I. J. Goodfellow et al., “Generative Adversarial Nets,” presented at the Advances in Neural Information Processing Systems, Jun. 2014.

M. Arjovsky, S. Chintala, and L. Bottou, “Wasserstein Generative Adversarial Networks,” presented at the International Conference on Machine Learning, Dec. 2017.

I. Gulrajani, F. Ahmed, M. Arjovsky, V. Dumoulin, and A. Courville, “Improved Training of Wasserstein GANs,” arXiv preprint, 2017. [Online]. Available: arXiv preprint arXiv:1704.00028

A. M. Seyam and R. Nemes, “Age influence on compressive strength for concrete made with different types of aggregates after exposure to high temperatures,” Materials Today: Proceedings, 2023.

A. Nazari, S. Riahi, S. Riahi, S. F. Shamekhi, and A. Khademno, “Influence of Al2O3 nanoparticles on the compressive strength and workability of blended concrete,” Journal of American Science, vol. 6, no. 5, pp. 6–9, 2010.