Computers and Concrete

Techno-Press (테크노프레스)
권호 표지
DOI QR코드

DOI QR Code

Application of ML algorithms to predict the effective fracture toughness of several types of concret

  • Ibrahim Albaijan (Mechanical Engineering Department, College of Engineering at Al-Kharj, Prince Sattam Bin Abdulaziz University) ;
  • Hanan Samadi (IRO, Civil Engineering Department, University of Halabja) ;
  • Arsalan Mahmoodzadeh (IRO, Civil Engineering Department, University of Halabja) ;
  • Hawkar Hashim Ibrahim (Department of Civil Engineering, College of Engineering, Salahaddin University-Erbil) ;
  • Nejib Ghazouani (College of Engineering, Northern Border University)
  • Received : 2023.10.01
  • Accepted : 2024.01.31
  • Published : 2024.08.25
⟨ Previous Next ⟩

Abstract

Measuring the fracture toughness of concrete in laboratory settings is challenging due to various factors, such as complex sample preparation procedures, the requirement for precise instruments, potential sample failure, and the brittleness of the samples. Therefore, there is an urgent need to develop innovative and more effective tools to overcome these limitations. Supervised learning methods offer promising solutions. This study introduces seven machine learning algorithms for predicting concrete's effective fracture toughness (K-eff). The models were trained using 560 datasets obtained from the central straight notched Brazilian disc (CSNBD) test. The concrete samples used in the experiments contained micro silica and powdered stone, which are commonly used additives in the construction industry. The study considered six input parameters that affect concrete's K-eff, including concrete type, sample diameter, sample thickness, crack length, force, and angle of initial crack. All the algorithms demonstrated high accuracy on both the training and testing datasets, with R2 values ranging from 0.9456 to 0.9999 and root mean squared error (RMSE) values ranging from 0.000004 to 0.009287. After evaluating their performance, the gated recurrent unit (GRU) algorithm showed the highest predictive accuracy. The ranking of the applied models, from highest to lowest performance in predicting the K-eff of concrete, was as follows: GRU, LSTM, RNN, SFL, ELM, LSSVM, and GEP. In conclusion, it is recommended to use supervised learning models, specifically GRU, for precise estimation of concrete's K-eff. This approach allows engineers to save significant time and costs associated with the CSNBD test. This research contributes to the field by introducing a reliable tool for accurately predicting the K-eff of concrete, enabling efficient decision-making in various engineering applications.

Keywords

Acknowledgement

The authors extend their appreciation to the Deanship of Scientific Research at Northern Border University, Arar, KSA for funding this research work through the project number "NBU-FFR-2024-2105-01".

References

  1. Bayer, J., Wierstra, D., Togelius, J. and Schmidhuber, J. (2009), "Evolving memory cell structures for sequence learning", Artificial Neural Networks-ICANN 2009: 19th International Conference, Limassol, Cyprus, September.
  2. Cho, K., Van Merrienboer, B., Bahdanau, D. and Bengio, Y. (2014), "On the properties of neural machine translation: Encoder-decoder approaches", 8th Workshop on Syntax, Semantics and Structure in Statistical Translation, SSST 2014, Doha, Qatar, October.
  3. Dehestani, A., Kazemi, F., Abdi, R. and Nitka, M. (2022), "Prediction of fracture toughness in fiber-reinforced concrete, mortar, and rocks using various ML techniques", Eng. Fract. Mech., 276, 108914. https://doi.org/10.1016/j.engfracmech.2022.108914.
  4. Dikshit, V., Bhudolia, S.K. and Joshi, S.C. (2017), "Multiscale polymer composites: A review of the interlaminar fracture toughness improvement", Fib., 5(4), 38. https://doi.org/10.3390/fib5040038
  5. Ferreira, C. (2001), "Gene expression programming: A new adaptive algorithm for solving problems", Compl. Syst., 13(2), 87-129.
  6. Guan, J., Yuan, P., Hu, X., Qing, L. and Yao, X. (2019), "Statistical analysis of concrete fracture using normal distribution pertinent to maximum aggregate size", Theoret. Appl. Fract. Mech., 101, 236-253. https://doi.org/10.1016/j.tafmec.2019.03.004.
  7. Hamdia, K.M., Lahmer, T., Nguyen-Thoi, T. and Rabczuk, T. (2015), "Predicting the fracture toughness of PNCs: A stochastic approach based on ANN and ANFIS", Comput. Mater. Sci., 102, 304-313. https://doi.org/10.1016/j.commatsci.2015.02.045.
  8. Hochreiter, S. and Schmidhuber, J. (1997), "Long short-term memory", Neural Comput., 9(8), 1735-1780. https://doi.org/10.1162/neco.1997.9.8.1735.
  9. Li, Z. and Yan, G. (2022), "ML for structural stability: Predicting dynamics responses using physics-informed neural networks", Comput. Concrete, 29(6), 419-432. https://doi.org/10.12989/cac.2022.29.6.419.
  10. Liu, G., Jia, L., Kong, B., Guan, K. and Zhang, H. (2017), "Artificial neural network application to study quantitative relationship between silicide and fracture toughness of Nb-Si alloys", Mater. Des., 129, 210-218. https://doi.org/10.1016/j.matdes.2017.05.027.
  11. Mahmoodzadeh, A., Fakhri, D., Mohammed, A.H., Mohammed, A.S., Ibrahim, H.H. and Rashidi, S. (2023), "Estimating the K-eff of a variety of materials using several ML models", Eng. Fract. Mech., 286, 109321. https://doi.org/10.1016/j.engfracmech.2023.109321.
  12. Mahmoodzadeh, A., Nejati, H.R., Mohammadi, M., Ibrahim, H.H., Khishe, M., Rashidi, S. and Ali, H.F.H. (2022), "Prediction of Mode-I rock fracture toughness using support vector regression with metaheuristic optimization algorithms", Eng. Fract. Mech., 264, 108334. https://doi.org/10.1016/j.engfracmech.2022.108334.
  13. Sharma, A., Anand Kumar, S. and Kushvaha, V. (2020), "Effect of aspect ratio on dynamic fracture toughness of particulate polymer composite using artificial neural network", Eng. Fract. Mech., 228, 106907. https://doi.org/10.1016/j.engfracmech.2020.106907.
  14. Suykens, J.A. and Vandewalle, J. (1999), "Multiclass least squares support vector machines", IJCNN'99. International Joint Conference on Neural Networks. Proceedings, Washington, D.C., USA, July.
  15. Wang, Y., Hu, X., Liang, L. and Zhu, W. (2016), "Determination of tensile strength and fracture toughness of concrete using notched 3-pb specimens", Eng. Fract. Mech., 160, 67-77. https://doi.org/10.1016/j.engfracmech.2016.03.036.
  16. Wu, Z., Tang, Y., Hong, B., Liang, B. and Liu, Y. (2023), "Enhanced precision in dam crack width measurement: Leveraging advanced lightweight network identification for pixel-level accuracy", Int. J. Intell. Syst., 2023, 1-16. https://doi.org/10.1155/2023/9940881.
  17. Yazici, S., Inan, G. and Tabak, V. (2007), "Effect of aspect ratio and volume fraction of steel fiber on the mechanical properties of SFRC", Constr. Build. Mater., 21(6), 1250-1253. https://doi.org/10.1016/j.conbuildmat.2006.05.025.