The early-age hydration of Portland cement paste has an important impact on the formation of microstructure and development of strength. However, manual derivation of analytic kinetic equation for hydration process is very difficult because there are multi-phased, multi-sized and interrelated complex chemical and physical reactions during cement hydration. In this paper, a flexible neural tree structure is built as the right-hand side of kinetics instead of traditional analytic expression. Two evolutionary algorithms gene expression programming and particle swarm optimization are used to evolve tree structure and rules’ parameters, respectively. In order to reduce the computing time, GPUs are used for acceleration in parallel. Studies have shown that according to the established model, simulation curve of early-age hydration is in good accordance with the observed experimental data. Furthermore, this model still has a good generalization ability even changing chemical composition, particle size and curing conditions.
This is a preview of subscription content, access via your institution.
Buy single article
Instant access to the full article PDF.
Tax calculation will be finalised during checkout.
Subscribe to journal
Immediate online access to all issues from 2019. Subscription will auto renew annually.
Tax calculation will be finalised during checkout.
Yuan R (1996) Cementing material science (in Chinese). Wuhan University of Technology Press, Wuhan
Chen W, Brouwers HJH (2008) Mitigating the effects of system resolution on computer simulation of Portland cement hydration. Cem Concr Compos 30:779–787
Tomosawa F (1974) Kinetic hydration model of cement. In: Proceedings of cement and concrete, pp 53–57
Krstulovic R, Dabic P (2000) A conceptual model of the cement hydration process. Cem Concr Res 30:693–698
Pignat C, Navi P, Scrivener K (2005) Simulation of cement paste microstructure hydration, pore space characterization and permeability determination. Mater Struct 38:459–466
Park K-B, Noguchi T, Plawsky J (2005) Modeling of hydration reactions using neural networks to predict the average properties of cement paste. Cem Concr Res 35:1676–1684
Yan P, Zheng F (2006) Kinetics model for the hydration mechanism of cementitious materials (in Chinese). J Chin Ceram Soc 34:555–559
Ozbay E, Gesoglu M, Guneyisi M (2008) Empirical modeling of fresh and hardened properties of self-compacting concretes by genetic programming. Constr Build Mater 22:1831–1840
Koza JR (1992) Genetic programming: on the programming of computers by means of natural selection. MIT Press, Cambridge
Baykasoglu A, Dereli T, Tanis S (2004) Prediction of cement strength using soft computing techniques. Cem Concr Res 34:2083–2090
Subasi A, Yilmaz AS, Binici H (2009) Prediction of early heat of hydration of plain and blended cements using neuro-fuzzy modelling techniques. Expert Syst Appl 36:4940–4950
Trtnik G, Kavcic F, Turk G (2008) The use of artificial neural networks in adiabatic curves modeling. Autom Constr 18:10–15
Chen Y, Yang B, Dong J, Abraham A (2005) Time-series forecasting using flexible neural tree model. Inf Sci 174:219–235
Bahrololum M, Salahi E, Khaleghi M (2009) Machine learning techniques for feature reduction in intrusion detection systems: a comparison. In: Proceedings of the 4th international conference on computer sciences and convergence information technology, pp 1091–1095
Chen Y, Abraham A, Yang B (2007) Hybrid flexible neural tree based intrusion detection systems. Int J Intell Syst 22:337–352
Qi F, Liu X, Ma Y (2009) Housing price index forecasting using neural tree model. In: Proceedings of the 2nd ISECS international colloquium on computing, communication, control and management, pp 467–470
Chen Y, Abraham A, Yang B (2006) Feature selection and classification using flexible neural tree. Neurocomputing 70:305–313
Pan Y, Liu Y, Zheng Y-W (2007) Face recognition using kernel PCA and hybrid flexible neural tree. In: Proceedings of international conference on wavelet analysis and pattern recognition, pp 1361–1366
Ferreira C (2001) Gene expression programming: a new adaptive algorithm for solving problems. Com Syst 13:87–129
Kennedy J, Eberhart RC (1995) A new optimizer using particle swarm theory. In: Proceedings of the 6th international symposium on micro machine and human science, pp 39–43
Wang P, Feng S, Liu X (2005) Research approaches of cement hydration degree and their development (in Chinese). J Bldg Mater 8:646–652
Schindler AK, Folliard KJ (2005) Heat of hydration models for cementitious materials. ACI Mater J 102:24–33
Bogue RH (1955) The chemistry of Portland cement. Reinhold Publishing Corporation, New York
Salustowicz R, Schmidhuber J (1997) Probabilistic incremental program evolution. Evol Comput 5:123–141
Oltean M, Grosan C (2003) Evolving evolutionary algorithms using multi expression programming. In: Proceedings of the 7th European conference on artificial life, pp 651–658
Chen L (2005) Optimal design for machinery: genetic algorithm (in Chinese). Machinery Industry Press, Beijing
NVIDIA (2009) CUDA programming guide version 2.3.1. Online at http://developer.download.nvidia.com/compute/cuda/2_3/toolkit/docs/NVIDIA_CUDA_Programming_Guide_2.3.pdf
This work was supported by National Basic Pre-Research Program of China (973 Program) under Grant No. 2010CB635117. National Natural Science Foundation of China under Grant No. 60873089, No. 60573065, No. 61070130, No. 60903176, No. 60673130, and No. 90818001. Provincial Natural Science Foundation for Outstanding Young Schoolers of Shandong under Grant No. JQ200820. Program for New Century Excellent Talents in University under Grant No. NCET-10-0863.
About this article
Cite this article
Wang, L., Yang, B., Chen, Y. et al. Modeling early-age hydration kinetics of Portland cement using flexible neural tree. Neural Comput & Applic 21, 877–889 (2012). https://doi.org/10.1007/s00521-010-0475-4
- Neural network
- Flexible neural tree
- Portland cement
- Hydration kinetics