Title:
Predicting Concrete’s Strength by Machine Learning: Balance between Accuracy and Complexity of Algorithms
Author(s):
B. Ouyang, Y. Song, Y. Li, F. Wu, H. Yu, Y. Wang, G. Sant, and M. Bauchy
Publication:
Materials Journal
Volume:
117
Issue:
6
Appears on pages(s):
125-133
Keywords:
machine learning; modeling; strength
DOI:
10.14359/51728128
Date:
11/1/2020
Abstract:
The properties of concretes are controlled by the rate of reaction of their precursors, the chemical composition of the binding phase(s), and their structure at different scales. However, the complex and multiscale structure of the cementitious hydrates and the dissimilar rates of numerous chemical reactions make it challenging to elucidate such linkages. In particular, reliable predictions of strength development in concretes remain unavailable. As an alternative route to physics- or chemistry-based models, machine learning (ML) offers a means to develop powerful predictive models for materials using existing data. Here, it is shown that ML models
can be used to accurately predict concrete’s compressive strength at 28 days. This approach relies on the analysis of a large data set (>10,000 observations) of measured compressive strengths for industrially produced concretes, based on knowledge of their mixture proportions. It is demonstrated that these models can readily predict the 28-day compressive strength of any concrete based merely on the knowledge of the mixture proportions with an accuracy of approximately ±4.4 MPa (as captured by the rootmean-
square error). By comparing the performance of select ML algorithms, the balance between accuracy, simplicity, and interpretability in ML approaches is discussed.
Related References:
1. Rodríguez de Sensale, G., “Strength Development of Concrete with Rice-Husk Ash,” Cement and Concrete Composites, V. 28, No. 2, 2006, pp. 158-160. doi: 10.1016/j.cemconcomp.2005.09.005
2. Ashour, S. A., and Wafa, F. F., “Flexural Behavior of High-Strength Fiber Reinforced Concrete Beams,” ACI Structural Journal, V. 90, No. 3, May-June 1993, pp. 279-287.
3. Purnell, P., and Black, L., “Embodied Carbon Dioxide in Concrete: Variation with Common Mix Design Parameters,” Cement and Concrete Research, V. 42, No. 6, 2012, pp. 874-877. doi: 10.1016/j.cemconres.2012.02.005
4. Biernacki, J. J.; Bullard, J. W.; Sant, G.; Brown, K.; Glasser, F. P.; Jones, S.; Ley, T.; Livingston, R.; Nicoleau, L.; Olek, J.; Sanchez, F.; Shahsavari, R.; Stutzman, P. E.; Sobolev, K.; and Prater, T., “Cements in the 21st Century: Challenges, Perspectives, and Opportunities,” Journal of the American Ceramic Society, V. 100, No. 7, 2017, pp. 2746-2773. doi: 10.1111/jace.14948
5. Provis, J. L., “Grand Challenges in Structural Materials,” Frontiers in Materials, V. 2, No. 31, 2015.
6. Wild, S.; Sabir, B. B.; and Khatib, J. M., “Factors Influencing Strength Development of Concrete Containing Silica Fume,” Cement and Concrete Research, V. 25, No. 7, 1995, pp. 1567-1580. doi: 10.1016/0008-8846(95)00150-B
7. Burris, L. E.; Alapati, P.; Moser, R. D.; Ley, T.; Berke, N.; and Kurtis, K. E., “Alternative Cementitious Materials: Challenges and Opportunities,” Durability and Sustainability of Concrete Structures, SP-305, American Concrete Institute, Farmington Hills, MI, 2015, 10 pp.
8. Khoury, G. A.; Majorana, C. E.; Pesavento, F.; and Schrefler, B. A., “Modelling of Heated Concrete,” Magazine of Concrete Research, V. 54, No. 2, 2002, pp. 77-101. doi: 10.1680/macr.2002.54.2.77
9. Breysse, D., and Martínez-Fernández, J. L., “Assessing Concrete Strength with Rebound Hammer: Review of Key Issues and Ideas for More Reliable Conclusions,” Materials and Structures, V. 47, No. 9, 2014, pp. 1589-1604. doi: 10.1617/s11527-013-0139-9
10. Yeh, I.-C., “Modeling of Strength of High-Performance Concrete Using Artificial Neural Networks,” Cement and Concrete Research, V. 28, No. 12, 1998, pp. 1797-1808. doi: 10.1016/S0008-8846(98)00165-3
11. Young, B. A.; Hall, A.; Pilon, L.; Gupta, P.; and Sant, G., “Can the Compressive Strength of Concrete Be Estimated from Knowledge of the Mixture Proportions?: New Insights from Statistical Analysis and Machine Learning Methods,” Cement and Concrete Research, V. 115, 2019, pp. 379-388. doi: 10.1016/j.cemconres.2018.09.006
12. Oey, T.; Jones, S.; Bullard, J. W.; and Sant, G., “Machine Learning Can Predict Setting Behavior and Strength Evolution of Hydrating Cement Systems,” Journal of the American Ceramic Society, V. 103, No. 1, 2020, pp. 480-490. doi: 10.1111/jace.16706
13. Breiman, L., “Random Forests,” Machine Learning, V. 45, No. 1, 2001, pp. 5-32. doi: 10.1023/A:1010933404324
14. Stone, M., “Cross-Validatory Choice and Assessment of Statistical Predictions,” Journal of the Royal Statistical Society. Series B. Methodological, V. 36, No. 2, 1974, pp. 111-133. doi: 10.1111/j.2517-6161.1974.tb00994.x
15. Sinha, P., “Multivariate Polynomial Regression in Data Mining: Methodology, Problems and Solutions,” International Journal of Scientific and Engineering Research, V. 4, No. 12, 2013.
16. Guo, J.; Xu, N.; Qian, K.; Shi, Y.; Xu, K.; Wu, Y.; and Alwan, A., “Deep Neural Network Based i-Vector Mapping for Speaker Verification Using Short Utterances,” Speech Communication, V. 105, 2018, pp. 92-102. doi: 10.1016/j.specom.2018.10.004
17. Wasserman, P. D., Advanced Methods in Neural Computing, first edition, John Wiley & Sons, New York, 1993.
18. Li, J.; Cheng, J.; Shi, J.; and Huang, F., “Brief Introduction of Back Propagation (BP) Neural Network Algorithm and Its Improvement,” Advances in Computer Science and Information Engineering, D. Jin and S. Lin, eds., Springer, Berlin, Germany, 2012, pp. 553-558.
19. Liaw, A., and Wiener, M., “Classification and Regression by randomForest,” R News, V. 2/3, 2002, p. 6
20. Segal, M. R., “Machine Learning Benchmarks and Random Forest Regression,” UCSF: Center for Bioinformatics and Molecular Biostatistics, Apr. 2004.
21. Chen, T., and Guestrin, C., “XGBoost: A Scalable Tree Boosting System,” Proceedings, Twenty Second ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, New York, ACM, 2016, pp. 785-794.
22. Ozturan, M.; Kutlu, B.; and Ozturan, T., “Comparison of Concrete Strength Prediction Techniques with Artificial Neural Network Approach,” Building Research Journal, V. 56, No. 1, 2008, pp. 23-36.
23. Akande, K. O.; Owolabi, T. O.; Twaha, S.; and Olatunji, S. O., “Performance Comparison of SVM and ANN in Predicting Compressive Strength of Concrete,” IOSR Journal of Computer Engineering, V. 16, No. 5, 2014, pp. 88-94. doi: 10.9790/0661-16518894
24. Liu, H.; Fu, Z.; Li, Y.; Sabri, N. F. A.; and Bauchy, M., “Balance between Accuracy and Simplicity in Empirical Forcefields for Glass Modeling: Insights from Machine Learning,” Journal of Non-Crystalline Solids, V. 515, 2019, pp. 133-142. doi: 10.1016/j.jnoncrysol.2019.04.020
25. Liu, H.; Zhang, T.; Anoop Krishnan, N. M.; Smedskjaer, M. M.; Ryan, J. V.; Gin, S.; and Bauchy, M., “Predicting the Dissolution Kinetics of Silicate Glasses by Topology-Informed Machine Learning,” Nature Partner Journals Materials Degradation, V. 3, No. 1, 2019, pp. 1-12. doi: 10.1038/s41529-019-0094-1
26. Yang, K.; Xu, X.; Yang, B.; Cook, B.; Ramos, J.; Anoop Krishnan, N. M.; Smedskjaer, M. M.; Hoover, C.; and Bauchy, M., “Predicting the Young’s Modulus of Silicate Glasses Using High-Throughput Molecular Dynamics Simulations and Machine Learning,” Scientific Reports, V. 9, No. 1, 2019, pp. 1-11. doi: 10.1038/s41598-019-45344-3
27. Bishnoi, S.; Singh, S.; Ravinder, R.; Bauchy, M.; Gosvami, N. N.; Kodamana, H.; and Anoop Krishnan, N. M., “Predicting Young’s Modulus of Oxide Glasses with Sparse Datasets Using Machine Learning,” Journal of Non-Crystalline Solids, V. 524, 2019, p. 119643 doi: 10.1016/j.jnoncrysol.2019.119643
28. ASTM C39/C39M-12a, “Standard Test Method for Compressive Strength of Cylindrical Concrete Specimens,” ASTM International, West Conshohocken, PA, 2012, 7 pp.
29. Fonti, V., and Belitser, E., “Feature Selection Using Lasso,” VU Amsterdam: Research Paper in Business Analytics, Vrije Universiteit, Amsterdam, Netherlands, 2017, pp. 1-25.