İstatistiksel ve Makine Öğrenmeye Dayalı Yaklaşımlarla Kobalt Katalizör Üzerinden Metan Kuru Reformundan Elde Edilen Sentez Gazının Tahmini Modellemesi

Abstract

Metanın kuru reformlanması, CO₂ emisyonunu azaltmak ve çeşitli Fischer-Tropsch sentezlerinde ve sentez gazlarının üretiminde kullanmak için umut verici bir yöntemdir. İstenen ürünleri verimli bir şekilde elde etmek için, reaktantların ürünler üzerindeki etkisi kesin olarak bilinmelidir. Bu amaçla, yapay-zeka bazlı veri odaklı tahmin modelleri ile metan kuru reformunun modellenmesi için çeşitli çalışmalar yayınlanmıştır. Önerilen metotlar, aşırı uyum probleminin araştırılmamasından, eksik ve/veya yanlı performans değerlendirmelerinden dolayı, sürecin belirli çıktılarını tahmin etmek için yetersiz kalmıştır. Bu çalışmada 57 örnek içeren bir veri seti kullanarak üç regresyon yöntemi kullandık ve tahmin modelleri geliştirdik. Modellerin performans değerlendirmeleri, tarafsız sonuçlar elde etmek için, 10 katlı çapraz doğrulama ile gerçekleştirilmiştir. Önerilen yöntemlerin hem eğitim hem de test performansları ayrı ayrı incelenmiş ve pratikte uygulanabilirliği tartışılmıştır.

Keywords

• metan,kuru reformlama,destek vektör makineleri,yapay sinir ağları,çapraz-doğrulama

Predictive Modeling of the Syngas Production from Methane Dry Reforming over Cobalt Catalyst with Statistical and Machine Learning Based Approaches

Abstract

Dry reforming of methane is a promising method to reduce the emission of CO₂ and to use it in various type of Fischer–Tropsch synthesis and production of syngas. In order to obtain desirable products efficiently, the effect of reactants on the products must be known precisely. For this purpose, several studies have published for modeling the dry reforming of methane process with artificial intelligence-based data-driven prediction models. Due to lack of investigating overfitting problem and deficient and/or biased performance evaluations, actual potential of proposed methods have not been revealed for predicting certain outputs of the process. In this paper, we employed three regression methods and developed prediction models using a dataset with 57 observations. Performance evaluations of the models are performed with 10-fold cross-validation to ensure unbiased results. Proposed methods’ both training and testing performances are separately investigated, further applicability is discussed.

Keywords

• methane,dry reforming,support vector machine,artificial neural networks,cross-validation

References

1. Florides, G. A. and Christodoulides, P., “Global warming and carbon dioxide through sciences,” Environ. Int., vol. 35, no. 2, pp. 390–401, 2009.
2. Ayodele, B. V. and Cheng, C. K., “Modelling and optimization of syngas production from methane dry reforming over ceria-supported cobalt catalyst using artificial neural networks and Box-Behnken design,” J. Ind. Eng. Chem., vol. 32, pp. 246–258, 2015.
3. Yücel, Ö. and Hastaoglu, M. A., “Comprehensive Study of Steam Reforming of Methane in Membrane Reactors,” J. Energy Resour. Technol., vol. 138, no. 5, p. 052204, 2016.
4. Luisetto, I., Tuti, S., and Di Bartolomeo, E., “Co and Ni supported on CeO2 as selective bimetallic catalyst for dry reforming of methane,” Int. J. Hydrogen Energy, vol. 37, no. 21, pp. 15992–15999, 2012.
5. Guo, J., Lou, H., and Zheng, X., “The deposition of coke from methane on a Ni/MgAl2O4 catalyst,” Carbon N. Y., vol. 45, no. 6, pp. 1314–1321, 2007.
6. Maestri, M., Vlachos, D. G., Beretta, A., Groppi, G., and Tronconi, E., “Steam and dry reforming of methane on Rh: Microkinetic analysis and hierarchy of kinetic models,” J. Catal., vol. 259, no. 2, pp. 211–222, 2008.
7. Hossain, M. A., Ayodele, B. V., Cheng, C. K., and Khan, M. R., “Artificial neural network modeling of hydrogen-rich syngas production from methane dry reforming over novel Ni/CaFe2O4 catalysts,” Int. J. Hydrogen Energy, vol. 41, no. 26, pp. 11119–11130, 2016.
8. Saidina Amin, N. A., Mohd. Yusof, K., and Isha, R., “Carbon Dioxide Reforming of Methane to Syngas: Modeling Using Response Surface Methodology and Artificial Neural Network,” J. Teknol., vol. 43, no. 1, 2013.

9. Davidson, J. W., Savic, D. A., and Walters, G. A., “Symbolic and numerical regression: Experiments and applications,” Inf. Sci. (Ny)., vol. 150, no. 1–2, pp. 95–117, 2003.
10. Bottou, L., “Large-scale machine learning with stochastic gradient descent,” in Proceedings of COMPSTAT 2010 - 19th International Conference on Computational Statistics, Keynote, Invited and Contributed Papers, 2010, pp. 177–186.
11. Jain, A. K., Mao, J., and Mohiuddin, K. M., “Artificial neural networks: A tutorial,” Computer (Long. Beach. Calif)., vol. 29, no. 3, pp. 31–44, 1996.
12. Detection, T., “Neural Networks (and more!),” Sci. Eng. Guid. to Digit. Signal Process., vol. 171, no. 1, pp. 13–18, 1994.
13. Hecht-Nielsen, R., “Theory of the backpropagation neural network,” Neural Networks, vol. 1, no. 1, p. 445, 1988.
14. Smola, A. J. and Schölkopf, B., “A tutorial on support vector regression,” Stat. Comput., vol. 14, no. 3, pp. 199–222, 2004.
15. Evgeniou, T., Pontil, M., and Poggio, T., “Regularization Networks and Support Vector Machines,” Adv. Comput. Math., vol. 13, no. 1, pp. 1–50, 2000.
16. Elmaz, F., Yücel, Ö., and Mutlu, A. Y., “Evaluating the Effect of Blending Ratio on the Co-Gasification of High Ash Coal and Biomass in a Fluidized Bed Gasifier Using Machine Learning,” Mugla J. Sci. Technol., vol. 5, no. 1, pp. 1–15, Jun. 2019.
17. Mutlu, A. Y. and Yucel, O., “An artificial intelligence based approach to predicting syngas composition for downdraft biomass gasification,” Energy, vol. 165, pp. 895–901, Dec. 2018.