Bidirectional Estimation of Self-Compacting Concrete Parameters Using Simplified Neuro-Fuzzy Networks
Downloads
The objective of this paper is to propose a novel bidirectional modeling framework using simplified neuro-fuzzy networks to approximate the complex dependencies between the workability parameters of self-compacting concrete (SCC) and the quantities of its five principal ingredients, namely cement, fly ash, water, additives, and admixtures. The forward model predicts seven key workability parameters based on the input ingredients and is essential for assessing the quality and performance of fresh SCC before production begins. In contrast, the backward model is trained to recommend the specific quantities of input ingredients required to achieve the expected SCC parameters. A comprehensive dataset consisting of 480 field-tested SCC mixtures was developed and used to train simplified Takagi–Sugeno–Kang (sTSK) networks. The numerical experiments demonstrated high accuracy, with the forward model achieving average relative errors of less than 2.46% and the backward model achieving an average relative error of 1.62%. These findings highlight the effectiveness of the proposed solutions in developing highly accurate approximation models. This study introduces a robust backward estimation approach, addressing a gap left by conventional forward-only models. Moreover, by incorporating Mahalanobis distance into the sTSK architecture, the proposed models use three times fewer nonlinear parameters than classical versions. This reduction enables their potential practical application in real-field concrete mixing and production systems for on-site quality control in production environments.
Downloads
[1] Okamura, H., & Ouchi, M. (2003). Self-Compacting Concrete. Journal of Advanced Concrete Technology, 1(1), 5–15. doi:10.3151/jact.1.5.
[2] Brouwers, H. J. H., & Radix, H. J. (2005). Self-compacting concrete: Theoretical and experimental study. Cement and Concrete Research, 35(11), 2116–2136. doi:10.1016/j.cemconres.2005.06.002.
[3] Tattersall, G. H. (1991). Workability and Quality Control of Concrete. CRC Press, London, United Kingdom.doi:10.1201/9781482267006.
[4] Rizal, N. S., Arifi, E., & Mufarida, N. A. (2025). High Initial Concrete Compressive Strength with Variations of Superplasticizer and Silica Fume Additions. Civil Engineering Journal (Iran), 11(1), 107–119. doi:10.28991/CEJ-2025-011-01-07.
[5] Irshidat, M. R., & Kailani, H. Y. (2025). Sustainable Utilization of Recycled Concrete Powder as Sand Replacement in Cement Mortar Production: Impact of Sand-Cement Ratio. Civil Engineering Journal (Iran), 11(8), 3375–3394. doi:10.28991/CEJ-2025-011-08-016.
[6] Hamdouni, S., Benaicha, M., Alaoui, A. H., & Burtschell, Y. (2025). Optimizing self-compacting concrete: A comprehensive analysis of weighting methods and multi-response optimization. Results in Engineering, 26. doi:10.1016/j.rineng.2025.105138.
[7] Cui, T., Kulasegaram, S., & Li, H. (2024). Design automation of sustainable self-compacting concrete containing fly ash via data driven performance prediction. Journal of Building Engineering, 87, 108960. doi:10.1016/j.jobe.2024.108960.
[8] Yeh, I. C., & Chen, J. W. (2005). Modeling workability of concrete using design of experiments and artificial neural networks. Journal of Technology, 20(2), 153-162.
[9] Hu, X., Li, B., Mo, Y., & Alselwi, O. (2021). Progress in artificial intelligence-based prediction of concrete performance. Journal of Advanced Concrete Technology, 19(8), 924–936. doi:10.3151/jact.19.924.
[10] Gou, J., Zaman, A., & Farooq, F. (2025). Machine learning-based prediction of compressive strength in sustainable self-compacting concrete. Engineering Applications of Artificial Intelligence, 161(B). doi:10.1016/j.engappai.2025.112190.
[11] Sobhani, J., Najimi, M., Pourkhorshidi, A. R., & Parhizkar, T. (2010). Prediction of the compressive strength of no-slump concrete: A comparative study of regression, neural network and ANFIS models. Construction and Building Materials, 24(5), 709–718. doi:10.1016/j.conbuildmat.2009.10.037.
[12] Zhang, Y., Yuan, X., Zhang, X., Wang, H., He, P., Luo, L., & Xu, C. (2025). Prediction of high-performance concrete compressive strength using Decision Tree-Guided Artificial Neural Network Pretraining approach. Engineering Applications of Artificial Intelligence, 156(A), 110828. doi:10.1016/j.engappai.2025.110828.
[13] Singh, T., Singh, R. B., Kapoor, K., & Singh, S. P. (2025). Calculating plastic viscosity of self-compacting concrete using V-funnel time: a novel mathematical approach with calibration using coefficient of viscosity. Discover Civil Engineering, 2(1), 201. doi:10.1007/s44290-025-00354-1.
[14] Nguyen, D. B., Wu, C. J., & Liao, W. C. (2023). Experimental Study and Development of Prediction Model of Self-Compacting Concrete Incorporating Fly Ash on Compressive Creep Behaviour. Journal of Advanced Concrete Technology, 21(8), 596–610. doi:10.3151/jact.21.596.
[15] Karthikeyan, J., Upadhyay, A., & Bhandari, N. M. (2008). Artificial neural network for predicting creep and shrinkage of high performance concrete. Journal of Advanced Concrete Technology, 6(1), 135–142. doi:10.3151/jact.6.135.
[16] Naadia, T., Ghernouti, Y., & Gueciouer, D. (2020). Development of a measuring procedure of rheological behavior for self compacting concrete. Journal of Advanced Concrete Technology, 18(7), 328–338. doi:10.3151/jact.18.328.
[17] TCVN 12209:2018. (2018). Self-compacting Concrete – Specification And Test Method. National Standards of Vietnam, Hanoi, Vietnam. (In Vietnamese).
[18] Nguyen, C. H., & Tran, L. H. (2023). Applications of Neural Network and Neuro-Fuzzy Network To Estimate the Parameters of Self-Compacting Concrete. International Journal of GEOMATE, 24(106), 120–129. doi:10.21660/2023.106.3656.
[19] Abood, E. A., Thoeny, Z. A., Azize, N. M., Imran, H., Kamchoom, V., Onyelowe, K. C., & Arunachalam, K. P. (2025). Self compacting concrete with recycled aggregate compressive strength prediction based on gradient boosting regression tree with Bayesian optimization hybrid model. Scientific Reports, 15(1), 28175. doi:10.1038/s41598-025-11161-0.
[20] Shukla, N. K., Garg, A., Bhutto, J., Aggarwal, M., Abbas, M., Hussein, H. S., Verma, R., & Khan, T. M. Y. (2023). Predicting the compressive strength of SCC containing nano silica using surrogate machine learning algorithms. Computers and Concrete, 32(4), 373–381. doi:10.12989/cac.2023.32.4.373.
[21] Golafshani, E. M., & Pazouki, G. (2018). Predicting the compressive strength of self-compacting concrete containing fly ash using a hybrid artificial intelligence method. Computers and Concrete, 22(4), 419–437. doi:10.12989/cac.2018.22.4.419.
[22] Le Nguyen, K., Shakouri, M., & Ho, L. S. (2025). Investigating the effectiveness of hybrid gradient boosting models and optimization algorithms for concrete strength prediction. Engineering Applications of Artificial Intelligence, 149, 110568. doi:10.1016/j.engappai.2025.110568.
[23] Serraye, M., Kenai, S., & Boukhatem, B. (2021). Prediction of compressive strength of self-compacting concrete (SCC) with silica fume using neural networks models. Civil Engineering Journal (Iran), 7(1), 118–139. doi:10.28991/cej-2021-03091642.
[24] el Asri, Y., Benaicha, M., Zaher, M., & Hafidi Alaoui, A. (2022). Prediction of the compressive strength of self-compacting concrete using artificial neural networks based on rheological parameters. Structural Concrete, 23(6), 3864–3876. doi:10.1002/suco.202100796.
[25] Padavala, S. S. A. B., Avudaiappan, S., Paluri, Y., Bharath, C. N., Prathipati, S. R. R. T., & Kumara, A. M. (2025). Self-compacting concrete with fly ash and silica fume: experimental evaluation, microstructural analysis, and machine learning modeling. Scientific Reports, 15(1), 45146. doi:10.1038/s41598-025-33180-7.
[26] De Smedt, J., & De Weerdt, J. (2024). Predictive process model monitoring using long short-term memory networks. Engineering Applications of Artificial Intelligence, 133(D), 108295. doi:10.1016/j.engappai.2024.108295.
[27] Yang, L., & An, X. (2020). Estimating the workability of self-compacting concrete in different mixing conditions based on deep learning. Computers and Concrete, 25(5), 433–445. doi:10.12989/cac.2020.25.5.433.
[28] Saha, P., Prasad, M. L. V., & RathishKumar, P. (2017). Predicting strength of SCC using artificial neural network and multivariable regression analysis. Computers and Concrete, 20(1), 31–38. doi:10.12989/cac.2017.20.1.031.
[29] Seshaiah, B., Rao, P. S., & Rao, P. S. (2021). Effect of mineral admixtures on the properties of steel fibre reinforced SCC proportioned using plastic viscosity and development of regression & ANN model. Computers and Concrete, 27(6), 523–535. doi:10.12989/cac.2021.27.6.523.
[30] Haykin, S. (2009). Neural networks and learning machines (3rd Ed.). Pearson Education India, Chennai, India.
[31] Tran, H. L. (2002). The modification of TSK network in neuro-fuzzy systems, Proceeding of International Conference on Fundamentals of Electrotechnics and Circuit Theory (IC-SPETO), Poland.
[32] Sankhya, A. (2018). Reprint of: Mahalanobis, P.C. (1936). On the Generalised Distance in Statistic, 80(1), 1–7. doi:10.1007/s13171-019-00164-5.
- Authors retain all copyrights. It is noticeable that authors will not be forced to sign any copyright transfer agreements.
- This work (including HTML and PDF Files) is licensed under a Creative Commons Attribution 4.0 International License.
