Modelling a Cement Precalciner by Machine Learning Methods


  • Amila Chandra Kahawalage
  • Wathsala Jinadasa



precalciner, cement manufacturing process, machine learning, degree of calcination


This work is a feasibility study of modelling the calcination process in a cement precalciner by employing machine learning algorithms. Calcination plays a significant role in characterising the clinker quality, energy demand and CO2 emissions in a cement production facility. Due to the complex nature of the calcination process, it has always been a challenge to reasonably model the precalciner system. This study is an attempt of finding a feasible alternative to answering this challenge. In this study, six machine learning algorithms were tested to analyse three output variables, which are, 1). the apparent degree of calcination, 2). CO2 molar fraction (dry basis) and 3).water molar fraction in the precalciner outlet stream. Fifteen input variables were used to train the algorithms, of which the values were obtained through a large number of simulated datasets by applying mass and energy balance to the precalciner system. A number of machine learning algorithms showed better predictability and Artificial neural network (ANN) showed the best performance for all three output variables.


O. I. Abiodun, A. Jantan, A. E. Omolara, K. V. Dada, N. A. Mohamed, and H. Arshad. State-of-the-art in artificial neural network applications: A survey. Heliyon, 4(11), e00938-e00938, 2018. doi:10.1016/j.heliyon.2018.e00938

G. Bonaccorso. Machine Learning Algorithms: Packt Publishing Ltd., 2017. IKN GmbH. CO2 capture from cement production; D 8.1 Status Report on Calciner Technology Revision 2, 2016.

Y. Z. Gang, and L. Hui. Soft sensor for apparent degree of calcination in NSP cement production line. Paper presented at the 2nd International Conference on Computer and Automation Engineering (ICCAE), 2010

M. K. Griparis, F. N. Koumboulis, N. S. Machos, and I. Marinos. Precalcination in cement plants (system description and control trends). IFAC Proceedings Volumes, 33(20), 273-278. 2000. doi:10.1016/S1474-6670(17)38062-X

IEA. CO2 capture in the cement industry; Technical Study Report number 2008/3. 2018.

J. D. Irwin The Industrial Electronics Handbook (The Electrical Engineering Handbook Series)| CRC Press, 1997.

Mathworks. Regression Learner. Retrieved from, 2021.

H. Mikulčić, E. von Berg, M. Vujanović, P. Priesching, L. Perković, R. Tatschl, and N. Duić. Numerical modelling of calcination reaction mechanism for cement production. Chemical Engineering Science, 69(1), 607-615. 2012. doi:10.1016/j.ces.2011.11.024

N. Mohammadhadi. Multi-phase flow and fuel conversion in cement calciner. PhD thesis. Kgs. Lyngby: Technical University of Denmark (DTU), 2018.

J. Osmic, E. Omerdic, E. Imsirovic, T. Smajlovic, and E. Omerdic. Identification and Control of Precalciner in the Cement Plant. In: J.A.Gonçalves, M.Braz-César, and

J.P.Coelho (eds) CONTROLO 2020. Lecture Notes in Electrical Engineering, vol 695. 2020. Springer, Cham. doi: 10.1007/978-3-030-58653-9_12

S. S.-Shwartz and S. B.-David. Understanding Machine Learning: From Theory To Algorithms: Cambridge University Press. 2014.

L.-A. Tokheim. The impact of staged combustion on the operation of a precalciner cement kiln. PhD thesis. NTNU, 1999.

WWFI. A blueprint for a climate friendly cement industry; How to Turn Around the Trend of Cement Related Emissions in the Developing World. 2008.

B. Yang, H. Lu, and L. Chen. BPNN and RBFNN based modeling analysis and comparison for cement calcination process. Paper presented at the Third International Workshop on Advanced Computational Intelligence, 2010.