Utilization of Prior Information in Neural Network Training for Improving 28-Day Concrete Strength Prediction
Publication: Journal of Construction Engineering and Management
Volume 147, Issue 5
Abstract
A concrete mix design aims to obtain the optimal proportions of concrete ingredients, including cement, water, sand, coarse aggregates, and admixtures. Neural networks (NNs) have been widely applied in research to predict concrete strength, and the concrete ingredients and concrete strength metrics have been used as the input and output parameters, respectively. The objective of this study is to use the 3-day concrete strength as the prior information in the NN training to reduce overfitting and improve the 28-day concrete strength prediction capability. This study is unique because the 3-day concrete strength was not used as another input parameter in the NN training; instead, it was used as data for the initial weights and biases of the connection node in the hidden layer during the NN training. Accordingly, a prior information-based NN model (PI-NNM) was developed to obtain a 28-day concrete strength prediction model. According to the tests with data subsets, the PI-NNM showed a better prediction capability than the conventional NN model, which uses only input parameters for the concrete prediction. Moreover, an adjusted PI-NNM was applied to the actual concrete production; the results showed a high prediction capability for the 28-day concrete strength.
Get full access to this article
View all available purchase options and get full access to this article.
Data Availability Statement
Data generated or analyzed during the study are available from the corresponding author by request.
Acknowledgments
This work was supported by a National Research Foundation of Korea (NRF) grant funded by the Korean Government (No. NRF-2019R1A2C201120212).
References
Aghdam, H. H., and E. J. Heravi. 2017. “Pattern classification.” In Guide to convolutional neural networks: A practical application to traffic-sign detection and classification. Cham, Switzerland: Springer.
Alilou, V. K., and M. Teshnehlab. 2010. “Prediction of 28-day compressive strength of concrete on the third day using artificial neural networks.” Int. J. Eng. 3 (6): 565–576.
ASTM. 2001. Standard specification for chemical admixtures for concrete. C 494/C 494M. West Conshohocken, PA: ASTM.
ASTM. 2018. Standard specification for concrete aggregates. C33/C33M-18. West Conshohocken, PA: ASTM.
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: 54–64. https://doi.org/10.1016/j.jclepro.2018.08.065.
Bonaccorso, G. 2018. “Optimizing neural networks.” In Mastering machine learning algorithms. Birmingham, UK: Packt Publishing Limited.
Bui, D. K., T. Nguyen, J. S. Chou, H. Nguyen–Xuan, and T. D. Ngo. 2018. “A modified firefly algorithm-artificial neural network expert system for predicting compressive and tensile strength of high-performance concrete.” Constr. Build. Mater. 180: 320–333. https://doi.org/10.1016/j.conbuildmat.2018.05.201.
Cascardi, A., F. Micelli, and M. A. Aiello. 2017. “An artificial neural networks model for the prediction of the compressive strength of FRP-confined concrete circular columns.” Eng. Struct. 140: 199–208. https://doi.org/10.1016/j.engstruct.2017.02.047.
Chopra, P., R. K. Sharma, and M. Kumar. 2016. “Prediction of compressive strength of concrete using artificial neural network and genetic programming.” Adv. Mater. Sci. Eng. 1–10. https://doi.org/10.1155/2016/7648467.
Dhir, R. K., G. S. Ghataora, and C. J. Lynn. 2017. Sustainable construction materials: Sewage sludge ash, 1st ed., 117–118. Birmingham, UK: Woodhead Publishing.
Diab, A. M., H. E. Elyamany, A. E. M. Abd Elmoaty, and A. H. Shalan. 2014. “Prediction of concrete compressive strength due to long term sulfate attack using neural network.” Alexandria Eng. J. 53 (3): 627–642. https://doi.org/10.1016/j.aej.2014.04.002.
Faraway, J. J., and N. H. Augustin. 2018. “When small data beats big data.” Stat. Probab. Lett. 136: 142–145.
Forrester, A. I. J., A. Sobester, and A. J. Keane. 2008. Engineering design via surrogate modelling: A practical guide. West Sussex, UK: Wiley.
Golnaraghi, S., Z. Zangenehmadar, O. Moselhi, and S. Alkass. 2019. “Application of artificial neural network(s) in predicting formwork labour productivity.” Adv. Civ. Eng. 1–11. https://doi.org/10.1155/2019/5972620.
Gülçehre, C., and Y. Bengio. 2016. “Knowledge matters: Importance of prior information for optimization.” J. Mach. Learn. Res. 17 (8): 1–32.
Gupta, S. 2013. “Concrete mix design using artificial neural network.” J. Today’s Ideas 1 (1): 29–43. https://doi.org/10.15415/jotitt.2013.11003.
Hagan, M. T., H. B. Demuth, and M. H. Beale. 1996. “Neuron model and network architectures.” In Neural network design, 2–12. Boston: PWS Publishing.
Hasan, M., and A. Kabir. 2012. “Early age tests to predict 28 days compressive strength of concrete.” In Proc., AWAM Int. Conf. on Civil Engineering, 376–383. Penang, Malaysia: Universiti Sains Malaysia.
Hasan, M., A. Kabir, and M. K. Miah. 2012. “Predicting 28 days compressive strength of concrete from 7 days test result.” In Proc., Int. Conf. on Advances in Design and Construction of Structures, 18–22. Thiruvananthapuram, India: Institute of Doctors Engineers and Scientists.
Horr, A. M., S. R. Asadsajadi, and M. Safi. 2004. “Design of concrete cooling tower structures with imperfection using ANN-based simulator.” In Proc., 5th Int. Symp. on Natural Draught Cooling Towers, 163–174. Boca Raton, FL: CRC Press.
Hosny, O. A., M. G. Elbarkouky, and A. Elhakeem. 2015. “Construction claims prediction and decision awareness framework using artificial neural networks and backward optimization.” J. Construct. Eng. Proj. Manage. 5 (1): 11–19. https://doi.org/10.6106/JCEPM.2015.5.1.011.
Ismaeel, A. G., and D. Y. Mikhail. 2016. “Effective data mining technique for classification cancers via mutations in gene using neural network.” Int. J. Adv. Comput. Sci. Appl. 7 (7): 69–76.
Juszczyk, M., and A. Leśniak. 2019. “Modelling construction site cost index based on neural network ensembles.” Symmetry 11 (14): 3828. https://doi.org/10.3390/sym11030411.
Khademi, F., M. Akbari, S. M. Jamal, and M. Nikoo. 2017. “Multiple linear regression, artificial neural network, and fuzzy logic prediction of 28-days compressive strength of concrete.” Front. Struct. Civ. Eng. 11 (1): 90–99. https://doi.org/10.1007/s11709-016-0363-9.
Kim, J. I, D. K. Kim, M. Q. Feng, and F. Yazdani. 2004. “Application of neural networks for estimation of concrete strength.” J. Mater. Civ. Eng. 16 (3): 257–264. https://doi.org/10.1061/(ASCE)0899-1561(2004)16:3(257).
Kobayashi, M., U. H. Issa, and A. Ahmed. 2015. “On the compressive strength and geo-environmental properties of MC-clay soil treated with recycled bassanite.” Int. J. Civ. Eng. 13 (1): 54–61.
Kosmatka, S. H., and M. L. Wilson. 2011. “Designing and proportioning concrete mixtures.” In Design and control of concrete mixtures, 15th ed., Skokie, IL: Portland Cement Association.
KSA (Korean Standard Association). 2007. Aggregate for concrete. KS F 2526. Seoul, Korea: Korean Industrial Standards.
KSA (Korean Standard Association). 2016. Ready-mixed concrete. KS F 4009. Seoul, Korea: Korean Industrial Standards.
Lü, B., J. Murata, and K. Hirasawa. 2004. “A new learning method using prior information of neural networks.” Sci. China (Ser. E) 34 (4): 374–390.
MathWorks. 2020. MATLAB documentation. Natick, MA: MathWorks.
Neukart, F. 2017. “An outline of artificial neural networks.” In Reverse engineering the mind: Consciously acting machines and accelerated evolution, 1st ed., Berlin: Springer.
Ni, H.-G., and J. Z. Wang. 2000. “Prediction of compressive strength of concrete by neural networks.” Cem. Concr. Res. 30 (8): 1245–1250. https://doi.org/10.1016/S0008-8846(00)00345-8.
Nikoo, M., F. T. Moghadam, and L. Sadowski. 2015. “Prediction of concrete compressive strength by evolutionary artificial neural networks.” Adv. Mater. Sci. Eng. 2015 (Jan): 8. https://doi.org/10.1155/2015/849126.
Patel, D. A., and K. N. Jha. 2015. “Neural network model for the prediction of safe work behavior in construction projects.” J. Constr. Eng. Manage. 141 (1): 04014066. https://doi.org/10.1061/(ASCE)CO.1943-7862.0000922.
Pavelka, A., and A. Proch. 2004. “Algorithms for initialization of neural network weights random numbers in MATLAB.” In Proc., Control Engineering, 453–459. New York: IEEE.
Punmia, B. C., A. K. Jain, and A. K. Jain. 2004. “Cement concrete.” In Basic civil engineering. 1st ed. New Delhi, India: Laxmi Publications.
Shah, S. A. R., T. Brijs, N. Ahmad, A. Pirdavani, Y. Shen, and M. A. Basheer. 2017. “Road safety risk evaluation using GIS-based data envelopment analysis—Artificial neural networks approach.” Appl. Sci. 7 (9): 886. https://doi.org/10.3390/app7090886.
Shapiro, A. M. 2004. “How including prior knowledge as a subject variable may change outcomes of learning research.” Am. Educ. Res. J. 41 (1): 159–189. https://doi.org/10.3102/00028312041001159.
Sivanandam, S. N., S. Sumathi, and S. N. Deepa. 2006. “Feed forward networks.” In Introduction to neural networks using MATLAB 6.0, 1st ed., New York: McGraw-Hill.
Tadeusiewicz, R., R. Chaki, and N. Chaki. 2005. “Neural net structure.” In Exploring neural networks with C#, 1st ed., Boca Raton, FL: CRC Press.
Viviani, M., B. Glisic, K. L. Scrivener, and I. F. C. Smith. 2008. “Equivalency points: Predicting concrete compressive strength evolution in three days.” Cem. Concr. Res. 38 (8–9): 1070–1078. https://doi.org/10.1016/j.cemconres.2008.03.006.
Wang, H., C. Wang, J. Xu, and X. Wang. 2019. “Concrete compression test data estimation based on a wavelet neural network model.” Math. Probl. Eng. 2019 (Jan): 4952036. https://doi.org/10.1155/2019/4952036.
Woodson, R. D. 2012. Concrete portable handbook, 1st ed., Waltham, MA: Elsevier.
Information & Authors
Information
Published In
Journal of Construction Engineering and Management
Volume 147 • Issue 5 • May 2021
Copyright
© 2021 American Society of Civil Engineers.
History
Received: Jul 13, 2020
Accepted: Dec 8, 2020
Published online: Feb 23, 2021
Published in print: May 1, 2021
Discussion open until: Jul 23, 2021
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.