Use of Different Hyperparameter Optimization Algorithms in ANN for Predicting the Compressive Strength of Concrete Containing Calcined Clay
Publication: Practice Periodical on Structural Design and Construction
Volume 27, Issue 2
Abstract
Calcined clays as supplementary cementitious materials (SCMs) have the potential to answer the need for SCMs because they have many resources in comparison with other SCMs. Moreover, calcined clays can be combined with limestone, which makes limestone calcined clay cement (LC3). LC3 can reduce the clinker of cement, which leads to the reduction of carbon dioxide pollution. The application of calcined clays as SCMs can make concrete with lower cost and the same compressive strength in comparison with other SCMs such as fly ash. Therefore, in this research, a predictive model has been built by the application of an artificial neural network (ANN), which can encourage the industry to increase the clay application in concrete. On the other hand, for improving the performance of the ANN model, four different optimization algorithms, such as genetic algorithm (GA), Bayesian optimization with a Gaussian process (BO-GP), Bayesian optimization with tree parzen estimator (BO-TPE), and hyperband algorithm, have been applied to optimize the number of neurons, number of hidden layers, activation function, number of batches, and epochs to predict the compressive strength of concrete. The results performance of models showed the superiority of the hyperband algorithm in running time and accuracy.
Get full access to this article
View all available purchase options and get full access to this article.
Data Availability Statement
Some or all data, models, or code that support the findings of this study are available from the corresponding author upon reasonable request:
•
The data that have been collected and used in this study are available in Excel format upon reasonable request.
References
Alshihri, M. M., A. M. Azmy, and M. S. El-Bisy. 2009. “Neural networks for predicting compressive strength of structural light weight concrete.” Constr. Build. Mater. 23 (6): 2214–2219. https://doi.org/10.1016/j.conbuildmat.2008.12.003.
Atici, U. 2011. “Prediction of the strength of mineral admixture concrete using multivariable regression analysis and an artificial neural network.” Expert Syst. Appl. 38 (8): 9609–9618. https://doi.org/10.1016/j.eswa.2011.01.156.
Behnood, A., V. Behnood, M. Modiri Gharehveran, and K. E. Alyamac. 2017. “Prediction of the compressive strength of normal and high-performance concretes using M5P model tree algorithm.” Constr. Build. Mater. 142 (Jul): 199–207. https://doi.org/10.1016/j.conbuildmat.2017.03.061.
Behnood, A., and E. M. Golafshani. 2018. “Predicting the compressive strength of silica fume concrete using hybrid artificial neural network with multi-objective grey wolves.” J. Cleaner Prod. 202 (Nov): 54–64. https://doi.org/10.1016/j.jclepro.2018.08.065.
Bergstra, J. 2011. “Algorithms for hyper-parameter optimization.” In Proc., 25th Annual Conf. on Neural Information Processing Systems (NIPS 2011), 1–9. San Diego: Neural Information Processing Systems.
Bergstra, J., R. Bardenet, Y. Bengio, and B. Kégl. 2011. “Algorithms for hyper-parameter optimization.” In Proc., 24th Int. Conf. on Neural Information Processing Systems, 2546–2554. New York: Curran Associates.
Bilim, C., C. D. Atiş, H. Tanyildizi, and O. Karahan. 2009. “Predicting the compressive strength of ground granulated blast furnace slag concrete using artificial neural network.” Adv. Eng. Software 40 (5): 334–340. https://doi.org/10.1016/j.advengsoft.2008.05.005.
Bishnoi, S., S. Maity, A. Mallik, S. Joseph, and S. Krishnan. 2014. “Pilot scale manufacture of limestone calcined clay cement: The Indian experience.” Indian Concr. J. 88 (7): 22–28.
Bottou, L. 2010. “Large-scale machine learning with stochastic gradient descent.” In Proc., COMPSTAT’2010, 177–186. Berlin: Physica-Verlag HD.
Chanakya, P., and D. Behera. 2016. “Experimental study on compressive strength of concrete by partial replacement of cement with metakaolin.” Int. J. Sci. Eng. Technol. Res. 5 (26): 5354–5358. https://doi.org/10.1063/1.4990212.
Chandwani, V., V. Agrawal, and R. Nagar. 2015. “Modeling slump of ready mix concrete using genetic algorithms assisted training of artificial neural networks.” Expert Syst. Appl. 42 (2): 885–893. https://doi.org/10.1016/j.eswa.2014.08.048.
Cheng, M.-Y., D. Prayogo, and Y.-W. Wu. 2014. “Novel genetic algorithm-based evolutionary support vector machine for optimizing high-performance concrete mixture.” J. Comput. Civ. Eng. 28 (4): 06014003. https://doi.org/10.1061/(ASCE)CP.1943-5487.0000347.
Cihan, M. T. 2019. “Prediction of concrete compressive strength and slump by machine learning methods.” Adv. Civ. Eng. 2019 (Nov): 1. https://doi.org/10.1155/2019/3069046.
Dantas, A. T. A., M. Batista Leite, and K. de Jesus Nagahama. 2013. “Prediction of compressive strength of concrete containing construction and demolition waste using artificial neural networks.” Constr. Build. Mater. 38 (Jan): 717–722. https://doi.org/10.1016/j.conbuildmat.2012.09.026.
Deepa, C., K. SathiyaKumari, and V. P. Sudha. 2010. “Prediction of the compressive strength of high performance concrete mix using tree based modeling.” Int. J. Comput. Appl. 6 (5): 18–24. https://doi.org/10.5120/1076-1406.
Delgado, J. M. P. Q., F. A. N. Silva, A. C. Azevedo, D. F. Silva, R. L. B. Campello, and R. L. Santos. 2020. “Artificial neural networks to assess the useful life of reinforced concrete elements deteriorated by accelerated chloride tests.” J. Build. Eng. 31 (Sep): 101445. https://doi.org/10.1016/j.jobe.2020.101445.
Deng, F., Y. He, S. Zhou, Y. Yu, H. Cheng, and X. Wu. 2018. “Compressive strength prediction of recycled concrete based on deep learning.” Constr. Build. Mater. 175 (Jun): 562–569. https://doi.org/10.1016/j.conbuildmat.2018.04.169.
Dewancker, I., M. McCourt, and S. Clark. 2016. Bayesian optimization for machine learning : A practical guidebook. Ithaca, NY: Cornell Univ.
Dutta, S., P. Samui, and D. Kim. 2018. “Comparison of machine learning techniques to predict compressive strength of concrete.” Comput. Concr. 21 (4): 463–470. https://doi.org/10.12989/cac.2018.21.4.463.
Eggensperger, K., M. Feurer, F. Hutter, J. Bergstra, J. Snoek, H. H. Hoos, and K. Leyton-brown. 2013. “Towards an empirical foundation for assessing Bayesian optimization of hyperparameters.” In NeurIPS workshop on Bayesian optimization in theory and practice (BayesOpt’13). Ithaca, NY: Cornell Univ.
Elshawi, R., M. Maher, and S. Sakr. 2019. Automated machine learning: State-of-the-art and open challenges. Ithaca, NY: Cornell Univ.
Emmanuel, A. C., P. Haldar, S. Maity, and S. Bishnoi. 2016. “Second pilot production of limestone calcined clay cement in India: The experience.” Indian Concr. 90 (5): 57–63.
Farooq, F., M. Nasir Amin, K. Khan, M. Rehan Sadiq, M. F. Faisal Javed, F. Aslam, and R. Alyousef. 2020. “A comparative study of random forest and genetic engineering programming for the prediction of compressive strength of high strength concrete (HSC).” Appl. Sci. 10 (20): 7330. https://doi.org/10.3390/app10207330.
Fazel Zarandi, M. H., I. B. Türksen, J. Sobhani, and A. A. Ramezanianpour. 2008. “Fuzzy polynomial neural networks for approximation of the compressive strength of concrete.” Appl. Soft Comput. 8 (1): 488–498. https://doi.org/10.1016/j.asoc.2007.02.010.
Feng, D.-C., Z.-T. Liu, X.-D. Wang, Y. Chen, J.-Q. Chang, D.-F. Wei, and Z.-M. Jiang. 2020. “Machine learning-based compressive strength prediction for concrete: An adaptive boosting approach.” Constr. Build. Mater. 230 (Jul): 117000. https://doi.org/10.1016/j.conbuildmat.2019.117000.
Fernandez, R., F. Martirena, and K. L. Scrivener. 2011. “The origin of the pozzolanic activity of calcined clay minerals: A comparison between kaolinite, illite and montmorillonite.” Cem. Concr. Res. 41 (1): 113–122. https://doi.org/10.1016/j.cemconres.2010.09.013.
Ferreira, R. M., J. P. Castro-Gomes, P. Costa, and R. Malheiro. 2016. “Effect of metakaolin on the chloride ingress properties of concrete.” KSCE J. Civ. Eng. 20 (4): 1375–1384. https://doi.org/10.1007/s12205-015-0131-8.
Getahun, M. A., S. M. Shitote, and Z. C. Abiero Gariy. 2018. “Artificial neural network based modelling approach for strength prediction of concrete incorporating agricultural and construction wastes.” Constr. Build. Mater. 190 (Nov): 517–525. https://doi.org/10.1016/j.conbuildmat.2018.09.097.
Golafshani, E. M., and A. Ashour. 2016. “Prediction of self-compacting concrete elastic modulus using two symbolic regression techniques.” Autom. Constr. 64 (Apr): 7–19. https://doi.org/10.1016/j.autcon.2015.12.026.
Golafshani, E. M., A. Behnood, and M. Arashpour. 2020. “Predicting the compressive strength of normal and high-performance concretes using ANN and ANFIS hybridized with Grey Wolf optimizer.” Constr. Build. Mater. 232 (Jan): 117266. https://doi.org/10.1016/j.conbuildmat.2019.117266.
Hutter, F., H. H. Hoos, and K. Leyton-Brown. 2011. “Sequential model-based optimization for general algorithm configuration.” In Vol. 6683 of Learning and intelligent optimization, edited by C. A. C. Coello, 507–523. Berlin: Springer. https://doi.org/10.1007/978-3-642-25566-3_40.
Hutter, F., L. Kotthoff, and J. Vanschoren. 2019. The Springer series on challenges in machine learning. New York: Springer.
Injadat, M., F. Salo, A. B. Nassif, A. Essex, and A. Shami. 2018. “Bayesian optimization with machine learning algorithms towards anomaly detection.” In Proc., 2018 IEEE Global Communications Conf. (GLOBECOM), 1–6. New York: IEEE.
Jamieson, K., and A. Talwalkar. 2016. “Non-stochastic best arm identification and hyperparameter optimization.” In Proc., 19th Int. Conf. on Artificial Intelligence and Statistics, 240–248. New York: Proceedings of Machine Learning Research.
Kandasamy, K., W. Neiswanger, J. Schneider, B. Poczos, and E. Xing. 2018. “Neural architecture search with Bayesian optimisation and optimal transport.” In Proc., 32nd Conf. on Neural Information Processing Systems, 31. Red Hook, NY: Curran Associates.
Kandiri, A., E. Mohammadi Golafshani, and A. Behnood. 2020. “Estimation of the compressive strength of concretes containing ground granulated blast furnace slag using hybridized multi-objective ANN and salp swarm algorithm.” Constr. Build. Mater. 248 (Jul): 118676. https://doi.org/10.1016/j.conbuildmat.2020.118676.
Kandiri, A., F. Sartipi, and M. Kioumarsi. 2021. “Predicting compressive strength of concrete containing recycled aggregate using modified ANN with different optimization algorithms.” Appl. Sci. 11 (2): 1–19. https://doi.org/10.3390/app11020485.
Kohavi, R., and S. Edu. 1993. “A study of cross-validation and bootstrap for accuracy estimation and model selection.” In Proc., 14th Int. Joint Conf. on Artificial Intelligence, 1137–1143. San Francisco: Morgan Kaufmann Publishers.
Li, L., K. Jamieson, G. DeSalvo, A. Rostamizadeh, and A. Talwalkar. 2016. “Hyperband: A novel bandit-based approach to hyperparameter optimization.” J. Mach. Learn. Res. 18 (1): 1–52.
Liu, G., and J. Zheng. 2019. “Prediction model of compressive strength development in concrete containing four kinds of gelled materials with the artificial intelligence method.” Appl. Sci. 9 (6): 1039. https://doi.org/10.3390/app9061039.
Martirena, F., A. Favier, and K. Scrivener. 2018. RILEM bookseries. Berlin: Springer.
Mermerdaş, K., M. Gesoǧlu, E. Güneyisi, and T. Özturan. 2012. “Strength development of concretes incorporated with metakaolin and different types of calcined kaolins.” Constr. Build. Mater. 37 (Oct):766–774. https://doi.org/10.1016/j.conbuildmat.2012.07.077.
Naderpour, H., A. H. Rafiean, and P. Fakharian. 2018. “Compressive strength prediction of environmentally friendly concrete using artificial neural networks.” J. Build. Eng. 16 (Mar): 213–219. https://doi.org/10.1016/j.jobe.2018.01.007.
Narmatha, M., and D. T. Felixkala. 2016. “Meta kaolin—The best material for replacement of cement in concrete.” J. Mech. Civ. Eng. 13 (4): 66–71. https://doi.org/10.9790/1684-1304016671.
Nuruddin, M. F., S. U. Khan, and N. Shafiq. 2014. “Effect of calcined kaolin on the mechanical properties of high-strength concrete as cement replacing material.” Appl. Mech. Mater. 567 (Feb): 375–380. https://doi.org/10.4028/www.scientific.net/AMM.567.375.
Opoku Amankwah, E. 2014. “Influence of calcined clay pozzolana on strength characteristics of Portland cement concrete.” Int. J. Mater. Sci. Appl. 3 (6): 410. https://doi.org/10.11648/j.ijmsa.20140306.30.
Özcan, F., C. D. Atiş, O. Karahan, E. Uncuoğlu, and H. Tanyildizi. 2009. “Comparison of artificial neural network and fuzzy logic models for prediction of long-term compressive strength of silica fume concrete.” Adv. Eng. Software 40 (9): 856–863. https://doi.org/10.1016/j.advengsoft.2009.01.005.
Pazouki, G., and E. Golafshani. 2018. “Predicting the compressive strength of self-compacting concrete containing fly ash using a hybrid artificial intelligence method.” Comput. Concr. 22 (4): 419–437. https://doi.org/10.12989/cac.2018.22.4.419.
Pham, A.-D., N.-D. Hoang, and Q.-T. Nguyen. 2016. “Predicting compressive strength of high-performance concrete using metaheuristic-optimized least squares support vector regression.” J. Comput. Civ. Eng. 30 (3): 06015002. https://doi.org/10.1061/(ASCE)CP.1943-5487.0000506.
Raj, R. R., and E. B. P. Pillai. 2008. “Shear strength of high performance concrete containing high reactivity metakaolin under direct shearing.” Int. J. Environ. Sci. Technol. 2008 (1): 2. https://doi.org/10.21307/acee-2017-025.
Saand, A., M. A. Keerio, and D. K. Bangwar. 2017. “Effect of metakaolin developed from local natural material soorh on workability, compressive strength, ultrasonic pulse velocity and drying shrinkage of concrete.” Archit. Civ. Eng. Environ. 10 (2): 115–122. https://doi.org/10.21307/acee-2017-025.
Sadowski, Ł., M. Piechówka-Mielnik, T. Widziszowski, A. Gardynik, and S. Mackiewicz. 2019. “Hybrid ultrasonic-neural prediction of the compressive strength of environmentally friendly concrete screeds with high volume of waste quartz mineral dust.” J. Cleaner Prod. 212 (Mar): 727–740. https://doi.org/10.1016/j.jclepro.2018.12.059.
Salman, S., and X. Liu. 2019. Overfitting mechanism and avoidance in deep neural networks. Ithaca, NY: Cornell Univ.
Sarıdemir, M., İ. B. Topçu, F. Özcan, and M. H. Severcan. 2009. “Prediction of long-term effects of GGBFS on compressive strength of concrete by artificial neural networks and fuzzy logic.” Constr. Build. Mater. 23 (3): 1279–1286. https://doi.org/10.1016/j.conbuildmat.2008.07.021.
Scrivener, A. K., A. Dekeukelaere, and L. G. F. Avet. 2019. Financial attractiveness of LC3. Palaiseau, France: École Polytech.
Scrivener, K., and A. Favier. 2015. RILEM bookseries. Berlin: Springer.
Scrivener, K., F. Martirena, S. Bishnoi, and S. Maity. 2018. “Calcined clay limestone cements (LC3).” In Cement and concrete research, 49–56. Amsterdam, Netherlands: Elsevier.
Seeger, M. 2004. “Gaussian processes for machine learning.” Int. J. Neural Syst. 14 (2): 69–106. https://doi.org/10.1142/S0129065704001899.
Shrestha, A., and A. Mahmood. 2019. “Review of deep learning algorithms and architectures.” In IEEE access, 53040–53065. New York: IEEE.
Siddique, R., and J. Klaus. 2009. “Influence of metakaolin on the properties of mortar and concrete: A review.” Appl. Clay Sci. 43 (3–4): 392–400. https://doi.org/10.1016/j.clay.2008.11.007.
Snellings, R. 2016. “Assessing, understanding and unlocking supplementary cementitious materials.” RILEM Tech. Lett. 1 (212): 50–55. https://doi.org/10.21809/rilemtechlett.2016.12.
Sobhani, J., M. Najimi, A. R. Pourkhorshidi, and T. Parhizkar. 2010. “Prediction of the compressive strength of no-slump concrete: A comparative study of regression, neural network and ANFIS models.” Constr. Build. Mater. 24 (5): 709–718. https://doi.org/10.1016/j.conbuildmat.2009.10.037.
Srivastava, N., G. Hinton, A. Krizhevsky, I. Sutskever, and R. Salakhutdinov. 2014. “Dropout: A simple way to prevent neural networks from overfitting.” J. Mach. Learn. Res. 15 (1): 1929–1958.
Swersky, K., D. Duvenaud, J. Snoek, F. Hutter, and M. A. Osborne. 2014. “Raiders of the lost architecture: Kernels for Bayesian optimization in conditional parameter spacesy.” In Proc., NIPS Workshop on Bayesian Optimization in Theory and Practice (BayesOpt '13). Ithaca, NY: Cornell Univ.
Tenza-Abril, A. J., Y. Villacampa, A. M. Solak, and F. Baeza-Brotons. 2018. “Prediction and sensitivity analysis of compressive strength in segregated lightweight concrete based on artificial neural network using ultrasonic pulse velocity.” Constr. Build. Mater. 189 (Nov): 1173–1183. https://doi.org/10.1016/j.conbuildmat.2018.09.096.
Topçu, İ. B., and M. Sarıdemir. 2008. “Prediction of compressive strength of concrete containing fly ash using artificial neural networks and fuzzy logic.” Comput. Mater. Sci. 41 (3): 305–311. https://doi.org/10.1016/j.commatsci.2007.04.009.
Uysal, M., and H. Tanyildizi. 2011. “Predicting the core compressive strength of self-compacting concrete (SCC) mixtures with mineral additives using artificial neural network.” Constr. Build. Mater. 25 (11): 4105–4111. https://doi.org/10.1016/j.conbuildmat.2010.11.108.
Uysal, M., and H. Tanyildizi. 2012. “Estimation of compressive strength of self compacting concrete containing polypropylene fiber and mineral additives exposed to high temperature using artificial neural network.” Constr. Build. Mater. 27 (1): 404–414. https://doi.org/10.1016/j.conbuildmat.2011.07.028.
Vizcaíno-Andrés, L. M., S. Sánchez-Berriel, S. Damas-Carrera, A. Pérez-Hernández, K. L. Scrivener, and J. F. Martirena-Hernández. 2015. “Industrial trial to produce a low clinker, low carbon cement.” Materiales de Construcción 65 (317): e045. https://doi.org/10.3989/mc.2015.00614.
Vu, D., P. Stroeven, and V. Bui. 2001. “Strength and durability aspects of calcined kaolin-blended Portland cement mortar and concrete.” Cem. Concr. Compos. 23 (6): 471–478. https://doi.org/10.1016/S0958-9465(00)00091-3.
Wong, H. S., and H. Abdul Razak. 2005. “Efficiency of calcined kaolin and silica fume as cement replacement material for strength performance.” Cem. Concr. Res. 35 (4): 696–702. https://doi.org/10.1016/j.cemconres.2004.05.051.
Xu, J., Y. Chen, T. Xie, X. Zhao, B. Xiong, and Z. Chen. 2019. “Prediction of triaxial behavior of recycled aggregate concrete using multivariable regression and artificial neural network techniques.” Constr. Build. Mater. 226 (Nov): 534–554. https://doi.org/10.1016/j.conbuildmat.2019.07.155.
Yang, L., and A. Shami. 2020. “On hyperparameter optimization of machine learning algorithms: Theory and practice.” Neurocomputing 415 (Nov): 295–316. https://doi.org/10.1016/j.neucom.2020.07.061.
Yeh, I.-C. C. 1998. “Modeling of strength of high-performance concrete using artificial neural networks.” Cem. Concr. Res. 28 (12): 1797–1808. https://doi.org/10.1016/S0008-8846(98)00165-3.
Yuan, Z., L.-N. Wang, and X. Ji. 2014. “Prediction of concrete compressive strength: Research on hybrid models genetic based algorithms and ANFIS.” Adv. Eng. Software 67 (Jan): 156–163. https://doi.org/10.1016/j.advengsoft.2013.09.004.
Zhang, S., J. Xu, E. Huang, and C.-H. Chen. 2016. “A new optimal sampling rule for multi-fidelity optimization via ordinal transformation.” In Proc., 2016 IEEE Int. Conf. on Automation Science and Engineering (CASE), 670–674. New York: IEEE.
Zhang, S., C. Zhang, and Q. Yang. 2003. “Data preparation for data mining.” Appl. Artif. Intell. 17 (5–6): 375–381. https://doi.org/10.1080/713827180.
Zhou, D. 2016. “Developing supplementary cementitious materials from waste London clay.” Imp. Coll. 2016 (1): 236. https://doi.org/10.25560/44528.
Zhou, D., R. Wang, M. Tyrer, H. Wong, and C. Cheeseman. 2017. “Sustainable infrastructure development through use of calcined excavated waste clay as a supplementary cementitious material.” J. Cleaner Prod. 168 (Dec): 1180–1192. https://doi.org/10.1016/j.jclepro.2017.09.098.
Zöller, M.-A., and M. F. Huber. 2021. “Benchmark and survey of automated machine learning frameworks.” J. Artif. Intell. Res. 70 (Jan): 409–472. https://doi.org/10.1613/jair.1.11854.
Information & Authors
Information
Published In
Practice Periodical on Structural Design and Construction
Volume 27 • Issue 2 • May 2022
Copyright
© 2022 American Society of Civil Engineers.
History
Received: Aug 6, 2021
Accepted: Dec 3, 2021
Published online: Jan 27, 2022
Published in print: May 1, 2022
Discussion open until: Jun 27, 2022
Authors
Metrics & Citations
Metrics
Citations
Download citation
If you have the appropriate software installed, you can download article citation data to the citation manager of your choice. Simply select your manager software from the list below and click Download.
Cited by
- Jaeho Son, Sungchul Yang, A New Approach to Machine Learning Model Development for Prediction of Concrete Fatigue Life under Uniaxial Compression, Applied Sciences, 10.3390/app12199766, 12, 19, (9766), (2022).