Critical thermal shock temperature prediction of alumina using improved hybrid models based on artificial neural networks and Shannon entropy

Belgacem Fissah; Hadj   Belghalem; Messaoud  Djeddou; Belgacem  Mamen

doi:10.15282/jmes.16.2.2022.07.0703

Authors

B. Fissah Department of Mechanical Engineering, Laboratoire des Mines, Larbi Tébessi University, 12000, Tébessa, Algeria.
H. Belghalem Department of Mechanical Engineering, Laboratoire des Mines, Larbi Tébessi University, 12000, Tébessa, Algeria.
M. Djeddou Department of Hydraulics, Larbi Ben M'hidi University, 04000, Oum El Bouaghi, Algeria.
B. Mamen Department of Civil Engineering, Abbès Laghrour University, 40000, Khenchela, Algeria.

DOI:

https://doi.org/10.15282/jmes.16.2.2022.07.0703

Keywords:

Alumina, Artificial neural network, Shannon entropy, Thermal shock

Abstract

This study investigates the potential of a simple and Hybrid artificial neural network (ANN) to predict dense alumina's critical thermal shock temperature (ΔT_c). The predictive models have been constructed using two ANNS models (M1, M2). In the first model (M1), elaboration, physical and mechanical parameters have been exploited to build three ANNs, namely generalized linear regression (M1-GLRNN), extreme learning machine (M1-ELM), and radial basis function (M1-RBFNN). The second model (M2) has been built by the three models mentioned above incorporated by the Shannon Entropy (SE) method. To compare the performance of all the developed models, coefficient of correlation (R), root mean square error (RMSE), mean absolute percentage error (MAPE), and Nash-Sutcliffe efficiency coefficient (NSE) have been considered. It is found that M2-RBFNN model with (RMSE = 4.3526, MAPE= 0.3406, NSE = 0.9921, and R= 0.9960) had superiority to the M1-RBFNN model (RMSE = 4.7030, MAPE= 0.3003, NSE = 0.9908, and R = 0.9954). More importantly, the contribution of the present work is that prediction of ΔT_c has been performed through the developed hybrid model (M2-RBFNN), which reduces the number of inputs from six to only four inputs and offers high accuracy for all the studied variables.

References

G.Fantozzi, S. Gallet and J. Niepce, Ceramic Science and Technology, France: EDP Science, 2011.

W. D. Kingery, “Factors affecting thermal stress resistance of ceramic materials,” Journal of the American Ceramic Society, vol. 38, no. 1, pp. 3-15, 1955.

D. P. H. Hasselman, “Unified theory of thermal shock fracture initiation and crack propagation in brittle ceramics," Journal of the American Ceramic Society, vol. 52, no. 11, pp. 600-604, 1969

F. Mignard, C. Olagnon, G. Fantozzi, P. Chantrenne and M. Raynauld, “Thermal shock behaviour of a coarse grain porous alumina,” Journal of Materials Science, vol. 31, no. 8, pp. 2131-2138, 1996.

F. Hugot and J. C. Glandus, “Thermal shock of alumina by compressed air cooling, ” Journal of the European Ceramic Society, vol. 27, no. 4, pp. 1919-1925, 2007.

X. Xu, S. Sheng, W. Yuan , and Z. Lin, “Effect of grain size on thermal shock property of alumina ceramic,” International Journal of Computational Materials Science and Engineering, vol. 5, no. 1, p. 1650004, 2016.

T. Bennouioua, Z. Malou, M. Hamidouche and G. Fantozzi, “Thermal shock behavior of a Soda Lime glass treated by Ion exchange,” Glass Physics and Chemistry, vol. 46, no. 6, pp. 462-473, 2020.

Z. Malou, M. Hamidouche, N. Bouaouadja, J. Chevalier and G. Fantozzi, “Thermal shock resistance of a soda lime glass,” Ceramics–Silikáty, vol. 57, no. 01, pp. 39-44, 2013.

Z. Malou, M. Hamidouche, N. Bouaouadja and G. Fantozzi, “Analysis of a soda lime glass thermal shock resistance,” Ceramics-Silikáty, vol. 55, no. 3, pp. 214-220, 2011.

M. Hamidouche, N. Bouaouadja, C. Olagnon and G. Fantozzi, “Thermal shock behaviour of mullite ceramic,” Ceramics International, vol. 29, no. 6, pp. 599-609, 2003.

R. Koker, N. Altinkok and A. Demir, “Neural network based prediction of mechanical properties of particulate reinforced metal matrix composites using various training algorithms,” Materials & Design, vol. 28, no. 2, pp. 616-627, 2007.

H. S. Majdi, A. N. Saud and S. N. Saud, “Modeling the physical properties of gamma alumina catalyst carrier based on an artificial neural network,” Materials, vol. 12, no. 11, p. 1752, 2019.

A. Shokuhfar, M. N. Samani, N. Naserifar, P. Heidary and G. Naderi, “Prediction of physical properties of Al2TiO5‐based ceramics containing micro and nano size oxide additives by using artificial neural network,” Mat.-wiss. u. Werkstofftech, vol. 40, no. 3, pp. 169-177, 2009.

C. Z. Huang, L. Zhang, L. He, J. Sun, B. Fang, B. Zou and X. Ai, “A study on the prediction of the mechanical properties of a ceramic tool based on an artificial neural network,” Journal of Materials Processing Technology, vol. 129, no. 1-3, pp. 399-402, 2002.

O. M. Elmabrouk and A. Kalkanli, “A neural network system for predicting the effect of Quartz and heat treatment on the corrosion properties of ceramic coating,” Journal of Multidisciplinary Engineering Science and Technology, vol. 2, no. 1, pp. 1-5, 2015.

N. Altinkok, “Use of artificial neural network for prediction of mechanical properties of α-Al2O3 particulate-reinforced Al–Si10Mg alloy composites prepared by using stir casting process,” Journal of Composite Materials, vol. 40, no. 9, pp. 779-796, 2006.

O. T. Adesina, T. Jamiru, I. A. Daniyan, E. R. Sadiku, O. F. Ogunbiyi, O. S. Adesina and L. W. Beneke, “Mechanical property prediction of SPS processed GNP/PLA polymer nanocomposite using artificial neural network,” Cogent Engineering, vol. 7, no. 1, p. 1720894, 2020.

M. Çöl, H. M. Ertunç and M. Yılmaz, “An artificial neural network model for toughness properties in microalloyed steel in consideration of industrial production conditions,” Materials & Design, vol. 28, no. 2, pp. 488-495, 2007.

J. Zhang, M. Yi, C. Xu and Z. Jiang, “Prediction of the mechanical properties of ceramic die material with artificial neural network,” IEEE International Conference on Intelligent Computing and Intelligent Systems, Shanghai, 2009,

H. Belghalem, M. Hamidouche, L. Gremillard, G. Bonnefont and G. Fantozzi, “Thermal shock resistance of two micro-structured alumina obtained by natural sintering and SPS,” Ceramics International, vol. 40, no. 1, pp. 619-627, 2014.

H. Belghalem, M. Hamidouche, L. Gremillard, G. Bonnefond and G. Fantozzi, “Effect of spark plasma sintering of alumina nanopowder on the mechanical properties,” Journal of the Australian Ceramic Society, vol. 53, no. 1, pp. 49-55, 2017.

M. Saadaoui, C. Olagnon and G. Fantozzi, “Evaluation of short crack R-curve behaviour of alumina under thermal shock loading,” Journal of Materials Science Letters, vol. 15, no. 1, pp. 64-66, 1996.

C. E. Shannon, “A mathematical theory of communication,” The Bell System Technical Journal, vol. 27, no. 3, pp. 379-423, 1948.

Y. Song and P. Wang, “A predictive model based on RBF neural network,” in Proc Sixth IASTED int Confon Intelligent Systems and Control, pp. 380–383, 2004.

P. Chaber and M. Ławryńczuk, “RBF neural networks for modelling and predictive control: An application to a neutralisation process,” 20th International Conference on Methods and Models in Automation and Robotics (MMAR), Miedzyzdroje, pp. 776-781, 2015.

W. Kehe, Y. Yue, C. Bohao and W. Jinshui, “Research of wind power prediction model based on RBF neural network.” In 2013 International Conference on Computational and Information Sciences, pp. 237-240, 2013.

H. Haviluddin and I. Tahyudin, “Time series prediction using radial basis function neural network,” International Journal of Electrical and Computer Engineering (IJECE), vol. 5, no. 4, pp. 765-771, 2015.

J. Moody and C. J. Darken, “Fast learning in networks of locally-tuned processing units,” Neural Computation, vol. 1, no. 2, pp. 281-294, 1989.

S. Haykin, Neural networks and learning machines, 3rd ed. Pearson Education India., 2009.

D. F. Specht, “A general regression neural network,” IEEE Transactions on Neural Networks, vol. 2, no. 6, pp. 568-576, 1991.

H. B. Celikoglu and H. K. Cigizoglu, “Public transportation trip flow modeling with generalized regression neural networks,” Advances in Engineering Software, vol. 38, no. 2, pp. 71-79, 2007.

B. Kim, D. W. Lee, K. Y. Park, S. R. Choi and S. Choi “Prediction of plasma etching using a randomized generalized regression neural network,” Vacuum, vol. 76, no. 1, pp. 37-43, 2004.

G. B. Huang, Q. Y. Zhu and C. K. Siew, “Extreme learning machine: Theory and applications,” Neurocomputing, vol. 70, no. 1-3, pp. 489-501, 2006.

G. B. Huang, “Learning capability and storage capacity of two-hidden-layer feedforward networks,” IEEE Transactions on Neural Networks, vol. 14, no. 2, pp. 274-281, 2003.

E. Olyaie, H. Z. Abyaneh and A. D. Mehr, “A comparative analysis among computational intelligence techniques for dissolved oxygen prediction in Delaware River,” Geoscience Frontiers, vol. 8, no. 3, pp. 517-527, 2017.

M. S. Gaya, M. U. Zango, L. A. Yusuf, M. Mustapha, B. Muhammad, A. Sani, A. Tijjani, N. Wahab and M. T. M. Khairi, “Estimation of turbidity in water treatment plant using Hammerstein-Wiener and neural network technique,” Indonesian Journal of Electrical Engineer, vol. 5, no. 3, pp. 666-672, 2017.

Q. Wang, “Kernel principal component analysis and its applications in face recognition and active shape models,” arXiv, 2012.

T. Zhou, F. Wang and Z. Yang, “Comparative analysis of ANN and SVM models combined with wavelet preprocess for groundwater depth prediction,” Water, vol. 9, no. 10, p. 781, 2017.

G. Elkiran, V. Nourani and S. I. Abba, “Multi-step ahead modelling of river water quality parameters using ensemble artificial intelligence-based approach,” Journal of Hydrology, vol. 577, p. 123962, 2019.