Predicting the compressive strength of ultra-high-performance concrete: an ensemble machine learning approach and actual application
Asian Journal of Civil Engineering - Trang 1-15 - 2024
Tóm tắt
The main objective of this research is to propose two ensemble machine learning models, namely random forest (RF) and adaptive gradient boosting (AGB), for predicting the compressive strength of ultra-high-performance concrete (UHPC). These models are developed based on a total of 810 experimental results of the compressive strength of UHPC collected from published articles. The predicted results from the RF and AGB are evaluated and compared through three conventional metrics, including the coefficient of determination (R2), mean absolute error (MAE), and root-mean-square error (RMSE). The obtained results demonstrate that the RF model reached high accuracy and reliability with R2, MAE, and RMSE values of 0.97, 4.30, and 5.92 for training and 0.93, 7.33, and 9.74 for testing, respectively. The RF model outperforms the AGB model in predicting the compressive strength of UHPC. Additionally, the effect of input variables on the anticipated compressive strength of the UHPC is determined using the SHapley additive explanations (SHAP) method. It was found that age, silica fume, and fiber are the most sensitive variables, whereas fly ash is the least sensitive to the compressive strength of the UHPC. Eventually, a user-friendly web application (UWA) tool is designed based on the proposed RF model to help quickly predict the compressive strength of the UHPC in practical implementation.
Tài liệu tham khảo
Abubakar, A. U., & Tabra, M. S. (2019). Prediction of compressive strength in high-performance concrete with hooked-end steel fiber using K-nearest neighbor algorithm. International Journal of Integrated Engineering, 11. https://publisher.uthm.edu.my/ojs/index.php/ijie/article/view/3535.
Akyuncu, V., Uysal, M., Tanyildizi, H., & Sumer, M. (2019). Modeling the weight and length changes of the concrete exposed to sulfate using artificial neural network. Revista De La Construcción, 17, 337–353. https://doi.org/10.7764/RDLC.17.3.337
Ayaz, Y., Kocamaz, A. F., & Karakoç, M. B. (2015). Modeling of compressive strength and UPV of high-volume mineral-admixtured concrete using rule-based M5 rule and tree model M5P classifiers. Construction and Building Materials, 94, 235–240.
Behnood, A., Behnood, V., Modiri Gharehveran, M., & Alyamac, K. E. (2017). Prediction of the compressive strength of normal and high-performance concretes using M5P model tree algorithm. Construction and Building Materials, 142, 199–207.
Breiman, L. (2001). Random forests. Machine Learning, 45(1), 5–32.
Cheng, M.-Y., Firdausi, P. M., & Prayogo, D. (2014). High-performance concrete compressive strength prediction using genetic weighted pyramid operation tree (GWPOT). Engineering Applications of Artificial Intelligence, 29, 104–113.
Chou, J.-S., & Pham, A.-D. (2015). Smart artificial firefly colony algorithm-based support vector regression for enhanced forecasting in civil engineering. Computer-Aided Civil and Infrastructure Engineering, 30(9), 715–732.
Farooq, F., Amin, M. N., Khan, K., Sadiq, M. R., Javed, M. F., Aslam, F., & Alyousef, R. (2020). A comparative study of random forest and genetic engineering programming for the prediction of compressive strength of high strength concrete (HSC). Applied Sciences, 10, 7330.
Feng, D. C., Liu, Z. T., Wang, X. D., Chen, Y., Chang, J. Q., Wei, D. F., & Jiang, Z. M. (2020). Machine learning-based compressive strength prediction for concrete: An adaptive boosting approach. Construction and Building Materials, 230, 117000.
Freund, Y., & Schapire, R. E. (1997). A decision-theoretic generalization of on-line learning and an application to boosting. Journal of Computer and System Sciences, 55(1), 119–139. https://doi.org/10.1006/jcss.1997.1504
Graybeal, B., & Davis, M. (2008). Cylinder or cube: strength testing of 80–200 MPa (11.6–29 ksi) ultra-high-performance-fiber-reinforced concrete. ACI Materials Journal, 105(6), 603–609.
Hastie, T., Tibshirani, R., & Friedman, J. H. (2009). The elements of statistical learning: Data mining, inference, and prediction. Springer.
Javed, M. F., Amin, M. N., Shah, M. I., Khan, K., Iftikhar, B., Farooq, F., Aslam, F., Alyousef, R., & Alabduljabbar, H. (2020). Applications of gene expression programming and regression techniques for estimating compressive strength of bagasse ash based concrete. Crystals, 10, 737.
Karahan, O., Tanyildizi, H., & Atis, C. D. (2008). An artificial neural network approach for prediction of long-term strength properties of steel fiber reinforced concrete containing fly ash. Journal of Zhejiang University Science, 9, 1514–1523. https://doi.org/10.1631/jzus.A0720136
Kaveh, A., Dadras, E. A., Javadi, S. M., & Geran Malek, N. (2021). Machine learning regression approaches for predicting the ultimate buckling load of variable-stiffness composite cylinders. Acta Mechanica, 232, 921–931.
Kaveh, A., Eskandari, A., & Movasat, M. (2023). Buckling resistance prediction of high-strength steel columns using metaheuristic-trained artificial neural networks. Structures, 56(C), 104853.
Kaveh, A., Gholipour, Y., & Rahami, H. (2008). Optimal design of transmission towers using genetic algorithm and neural networks. International Journal of Space Structures, 23(1), 1–19.
Kaveh, A., & Khalegi, A. (1998). Prediction of strength for concrete specimens using artificial neural network. Asian Journal of Civil Engineering, 2(2), 113.
Kaveh, A., & Khavaninzadeh, N. (2023). Efficient training of two ANNs using four meta-heuristic algorithms for predicting the FRP strength. Structures, 52, 256–272. https://doi.org/10.1016/j.istruc.2023.03.178
Kim, D. J., Park, S. H., Ryu, G. S., & Koh, K. T. (2011). Comparative flexural behavior of hybrid ultra high performance fiber reinforced concrete with different macro fibers. Construction and Building Materials, 25, 4144–4155.
Kohavi, R. (1995). A study of cross-validation and bootstrap for accuracy estimation and model selection. In Proceedings of the International Joint Conference on Artificial Intelligence (IJCAI), Vol. 14, Montreal, Canada, pp. 1137–1143.
Lundberg, S. M., & Lee, S. I. (2017). A unified approach to interpreting model predictions. Advances in Neural Information Processing Systems, 30, 4766–4775.
Marani, A., Jamali, A., & Nehdi, M. L. (2020). Predicting ultra-high-performance concrete compressive strength using tabular generative adversarial networks. Materials, 13(21), 4757. https://doi.org/10.3390/ma13214757
Matin, S. S., Farahzadi, L., Makaremi, S., Chelgani, S. C., & Sattari, G. (2017). Variable selection and prediction of uniaxial compressive strength and modulus of elasticity by random forest. Applied Soft Computing, 70, 980–987.
Mohamed, O. A., Ati, M., & Najm, O. F. (2017). Predicting compressive strength of sustainable self-consolidating concrete using random forest. Key Engineering Materials, 744, 141–145.
Nagajothi, S., & Elavenil, S. (2020). Influence of aluminosilicate for the prediction of mechanical properties of geopolymer concrete—artificial neural network. Siliconindia, 12, 1011–1021. https://doi.org/10.1007/s12633-019-00203-8
Nazari, A., & Sanjayan, J. G. (2015). Modelling of compressive strength of geopolymer paste, mortar and concrete by optimized support vector machine. Ceramics International, 41, 12164–12177. https://doi.org/10.1016/j.ceramint.2015.06.037
Park, S. H., Kim, D. J., Ryu, G. S., & Koh, K. T. (2012). Tensile behavior of ultra-high performance hybrid fiber reinforced concrete. Construction and Building Materials, 34(2), 172–184.
Phan, T. D. (2023). Practical machine learning techniques for estimating the splitting-tensile strength of recycled aggregate concrete. Asian Journal of Civil Engineering. https://doi.org/10.1007/s42107-023-00744-9. Advance online publication.
Pishro, A. A., & Feng, X. (2017). Experimental study on bond stress between ultra high performance concrete and steel reinforcement. Civil Engineering Journal, 3(12), 1235–1245.
Rofooei, F. R., Kaveh, A., & Masteri, F. F. (2011). Estimating the vulnerability of concrete moment resisting frame structures using artificial neural networks. International Journal of Operational Research, 1(3), 433–448.
Rossi, P., Antonio, A., Parant, E., & Fakhri, P. (2005). Bending and compressive behaviors of a new cement composite. Cement and Concrete Research, 35(1), 27–33.
Sadowski, Ł, Nikoo, M., & Nikoo, M. (2018). Concrete compressive strength prediction using the imperialist competitive algorithm. Computers and Concrete, 22, 355–363.
Sonebi, M., Cevik, A., Grünewald, S., & Walraven, J. (2016). Modelling the fresh properties of self-compacting concrete using support vector machine approach. Construction and Building Materials, 106, 55–64.
Špak, M., Kozlovská, M., Struková, Z., & Bašková, R. (2016). Comparison of conventional and advanced concrete technologies in terms of construction efficiency. Advanced Materials Science and Engineering, 2016, 6. https://doi.org/10.1155/2016/1903729. Article ID 1903729.
Wille, K., Kim, D. J., & Naaman, A. E. (2011). Strain hardening UHP-FRC with low fiber contents. Materials and Structures, 44, 583–598.
Zhang, J. L. Y., Sun, W., Liu, S., & Jiao, C. (2008). Preparation of C200 green reactive powder concrete and its static-dynamic behaviors. Cement and Concrete Composites, 30, 831–838. https://doi.org/10.1016/j.cemconcomp.2008.06.008
Zheng, Y. W. W., & Luo, B. (2013). Compressive and tensile properties of reactive powder concrete with steel fibres at elevated temperatures. Construction and Building Materials, 41, 844–851. https://doi.org/10.1016/j.conbuildmat.2012.12.066