Citation :

Karam Ali Hadi, "Enhancing Civil Engineering Material Characterization Using Fuzzy Neural Networks: Applications in Concrete Mix Design and Soil Detection," International Journal of Civil Engineering, vol. 13, no. 5, pp. 75-85, 2026. Crossref, https://doi.org/10.14445/23488352/IJCE-V13I5P106

Abstract

Accurate prediction of soil properties and concrete compressive strength is crucially important in civil engineering in order to ensure safety within the limit states and to economize on materials. Traditional methods, including multiple regression analysis and ANNs, are often not competent to handle data uncertainty and nonlinearity inherent in construction materials. In this paper, a hybrid Fuzzy Neural Network (FNN) framework is introduced as a methodology that allows the strengths of fuzzy logic for uncertain reasoning with the learning capabilities of neural networks. The developed FNN model was applied to two important tasks: (1) the prediction of the 28-day compressive strength of concrete from mix proportions, and (2) the estimation of key soil contamination indicators, Total Soluble Salts, Sulfur Trioxide, and Organic Matter from standard geotechnical parameters. The model has been trained, validated, and tested on real datasets consisting of 941 concrete mixes and 99 soil samples. The results indicate that the FNN performs better than conventional models on both sets of data, with R² values greater than 0.97 for soil properties and 0.94 for concrete strength. In addition, MATLAB-based simulations also showed the robustness of the proposed model against variability of input and measurement noise.

Keywords

Fuzzy Neural Network (FNN), Civil engineering materials, Concrete compressive strength prediction, Soil property prediction, Machine learning, Uncertainty modeling, Material characterization, Hybrid intelligent systems, MATLAB.

References

1. Lofti Zadeh, “Fuzzy Logic,” Computer, vol. 21, no. 4, pp. 83-93, 1988.
   [CrossRef] [Google Scholar] [Publisher Link]
2. Tomohiro Takagi, and Michio Sugeno, “Fuzzy Identification of Systems and its Applications to Modeling and Control,” IEEE Transactions on Systems, Man, and Cybernetics, vol. SMC-15, no. 1, pp. 116-132, 1985.
   [CrossRef] [Google Scholar] [Publisher Link]
3. Kenneth Levenberg, “A Method for the Solution of Certain Non-Linear Problems in Least Squares,” Quarterly of Applied Mathematics, vol. 2, no. 2, pp. 164-168, 1944.
   [CrossRef] [Google Scholar] [Publisher Link]
4. Jyh-Shing Jang, “ANFIS: Adaptive-Network-Based Fuzzy Inference System,” IEEE Transactions on Systems, Man, and Cybernetics, vol. 23, no. 3, pp. 665-685, 1993.
   [CrossRef] [Google Scholar] [Publisher Link]
5. Yann LeCun, Yoshua Bengio, and Geoffrey Hinton, “Deep Learning,” Nature, vol. 521, no. 7553, pp. 436-444, 2015.
   [CrossRef] [Google Scholar] [Publisher Link]
6. Christopher M. Bishop, Pattern Recognition and Machine Learning, New York, NY, USA: Springer, 2006.
   [Google Scholar] [Publisher Link]
7. Ian Goodfellow, Yoshua Bengio and Aaron Courville, Deep Learning, Cambridge, MA, USA: MIT Press, 2016.
   [Google Scholar] [Publisher Link]
8. Jerry M. Mendel, Uncertain Rule-Based Fuzzy Systems, 2^nd ed., Cham, Switzerland: Springer, 2017.
   [CrossRef] [Google Scholar] [Publisher Link]
9. Nikola Kasabov, “Evolving Fuzzy Neural Networks for Supervised/Unsupervised Online Knowledge-based Learning,” IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics), vol. 31, no. 6, pp. 902-918, 2007.
   [CrossRef] [Google Scholar] [Publisher Link]
10. Xiao-Le Han et al., “Deep Learning based Approach for the Instance Segmentation of Clayey Soil Desiccation Cracks,” Computers and Geotechnics, vol. 146, 2022.
    [CrossRef] [Google Scholar] [Publisher Link]
11. Ahmad T. Abdulsadda et al., “Expert Systems for Soil Detection Using Deep Learning Techniques,” ICACS '25: Proceedings of the 9^th International Conference on Algorithms, Computing and Systems, Bangkok, Thailand, 2025.
    [CrossRef] [Google Scholar] [Publisher Link]
12. Karam Ali Hadi, and Aseel Sultan Ridha, “Deep Learning Techniques in Concrete Powder Mix Designing,” Open Engineering, vol. 14, no. 1, 2024.
    [CrossRef] [Google Scholar] [Publisher Link]
13. Bushra S. Albusoda, Dhurgham A. Al-Hamdani, and Mohammed F. Abbas, “Dry Density Prediction from Soil Index Properties using Expert Systems,” Key Engineering Materials, vol. 857, pp. 266-272, 2020.
    [CrossRef] [Google Scholar] [Publisher Link]
14. Jiuxiang Gu et al., “Recent Advances in Convolutional Neural Networks,” Pattern Recognition, vol. 77, pp. 354-377, 2018.
    [CrossRef] [Google Scholar] [Publisher Link]
15. D. Sivabalaselvamani et al., “Soil Classification using Deep Learning Techniques,” 2023 Second International Conference on Augmented Intelligence and Sustainable Systems (ICAISS), Trichy, India, pp. 582-586, 2023.
    [CrossRef] [Google Scholar] [Publisher Link]
16. A. Adoko, Li Wu., “Fuzzy Inference Systems-based Approaches in Geotechnical Engineering-a Review,” Electronic Journal of Geotechnical Engineering (EJGE), vol. 16, pp. 1543-1558, 2011.
    [Google Scholar]
17. Tianlong Li et al., “Predicting High-Strength Concrete’s Compressive Strength: A Comparative Study of Artificial Neural Networks, Adaptive Neuro-Fuzzy Inference System, and Response Surface Methodology,” Materials, vol. 17, no. 18, pp. 1-37, 2024.
    [CrossRef] [Google Scholar] [Publisher Link]
18. Kok-Kwang Phoon et al., “Geotechnical Uncertainty, Modeling, and Decision Making,” Soils and Foundations, vol. 62, no. 5, pp. 1-21, 2022.
    ​​​​​​​[CrossRef] [Google Scholar] [Publisher Link]