Learning from a carbon dioxide capture system dataset: Application of the piecewise neural network algorithm

Abstract

This paper presents the application of a neural network rule extraction algorithm, called the piece-wise linear artificial neural network or PWL-ANN algorithm, on a carbon capture process system dataset. The objective of the application is to enhance understanding of the intricate relationships among the key process parameters. The algorithm extracts rules in the form of multiple linear regression equations by approximating the sigmoid activation functions of the hidden neurons in an artificial neural network (ANN). The PWL-ANN algorithm overcomes the weaknesses of the statistical regression approach, in which accuracies of the generated predictive models are often not satisfactory, and the opaqueness of the ANN models. The results show that the generated PWL-ANN models have accuracies that are as high as the originally trained ANN models of the four datasets of the carbon capture process system. An analysis of the extracted rules and the magnitude of the coefficients in the equations revealed that the three most significant parameters of the CO₂ production rate are the steam flow rate through reboiler, reboiler pressure, and the CO₂ concentration in the flue gas.

Keywords

Carbon dioxide capture process system / Artificial neural network / Rule extractions / Non-linear modeling / Linear regression

Acknowledgements

The first Author is grateful for the scholarships and generous support from the Faculty of Graduate Studies and Research, University of Regina and from the Canada Research Chair Program. The Authors also wish to acknowledge the contributions of Dr. Raphael Idem and Dr. Paitoon Tontiwachwuthikul in allowing us to use the datasets on the carbon dioxide capture plant of the Clean Energy Technology Research Institute.

References

[1] H.F. Svendsen, E.T. Hessen, T. Mejdell, Carbon dioxide capture by absorption, challenges and possibilities, Chem. Eng. J. 171 (3) (2011) 718-724.

[2] T.C. Merkel, H. Lin, X. Wei, R. Baker, Power plant post-combustion carbon dioxide capture : an opportunity for membranes, J. Membr. Sci. 1 (359) (2010) 126-139.

[3] Q. Zhou, C.W. Chan, P. Tontiwachwuthikul, R.O. Idem, D. Gelowitz, Part 4b: application of data modeling and analysis techniques to the CO₂ capture process system, J. Carbon Manag. 3 (1) (2012) 81-94.

[4] Q. Zhou, C.W. Chan, P. Tontiwachwuthikul, R.O. Idem, D. Gelowitz, A statistical analysis of the carbon dioxide capture process, Greenh. Gas. Control 3 (2009) 535-544.

[5] Q. Zhou, C.W. Chan, P. Tontiwachwuthikul,Application of three data analysis techniques for modeling the carbon dioxide capture process, in:Proceedings of 23rd Canadian Conference on Electrical and Computing Engineering, vol. 23, 2010, pp. 1-4.

[6] Q. Zhou, C.W. Chan, P. Tontiwachwuthikul, R.O. Idem, D. Gelowitz, Application of neuro-fuzzy modeling technique for operational problem solving in a CO₂ capture process system, Int. J. Greenh. Gas Control 15 (2013) 32-41.

[7] A.B. Rao, E.S. Rubin, A technical, economic and environmental assessment of amine-based CO₂ capture technology for power plant greenhouse gas control, Env. Sci. Technol. 36 (2002) 4467-4475.

[8] A.B. Rao, E. Rubin, D. Keith, M. Morgan, Evaluation of potential cost reductions from improved amine-based CO₂ capture system, Energy Policy 34 (2006) (2006) 3765-3772.

[9] R. Idem, M. Wilson, P. Tontiwachwuthikul, et al., Pilot plant studies of the CO₂ capture performance of aqueous MEA and mixed MEA/MDEA solvents at the University of Regina CO₂ capture technology development plant and the boundary dam CO₂ capture demonstration plant, Ind. Eng. Chem. Res. 45 (2006) 2414-2420.

[10] T. Yokoyama, Japanese R&D on large-scale CO₂ capture, Presented at: 2004 ECI Conference on Separations Technology VI: New Perspectives on Very Large-Scale Operations, Fraser Island, Queensland, Australia, 3-8 October 2004.

[11] R. Sakwattanapong, A. Aroonwilas, A. Veawab, Behavior of reboiler heat duty for CO₂ capture plants using regenerable single and blended alkanolamines, Ind. Eng. Chem. Res. 44 (12) (2005) 4465-4473.

[12] A. Aroonwilas, A. Veawab, Characterization and comparison of the CO₂ absorption performance into single and blended alkanolamines in a packed column, Ind. Eng. Chem. Res. 43 (2004) 2228-2237.

[13] A. Aroonwilas, A. Veawab, Integration of CO₂ capture unit using single-and blended-amines into supercritical coal-fired power plants: implications for emission and energy management, Ind. Eng. Chem. Res. 1 (2007) 143-150.

[14] M.R.G. Meireles, P.E.M. Almeida, M.G. Sim-oes, A comprehensive review for industrial applicability of artificial neural networks, IEEE Trans. Ind. Electron. 50 (3) (2003) 585-601.

[15] R. Andrews, J. Diederich, A.B. Tickle, Survey and critique of techniques for extracting rules from trained artificial neural networks, Knowledge-Based Syst. 8 (6) (1995) 373-389.

[16] G.G. Towell, J.W. Shavlik, Extracting refined rules from knowledge-based neural networks, Mach. Learn. 13 (1) (1993) 71-101.

[17] R. Setiono, H. Liu,Understanding neural netowrks via rule extraction, in:Proceeding of 14th International Joint Conference on Artificial Intelligence, 1995, pp. 480-485.

[18] R. Setiono, H. Liu, Neurolinear: from neural networks to oblique decision rules, Neurocomputing 17 (1) (2007) 1-24.

[19] R. Krishnan, G. Sivakumar, P. Bhattacharya, A search technique for rule extraction from trained neural networks, Pattern Recognit. Lett. 20 (3) (1999) 273-280.

[20] D. Kim, J. Lee, Handling continuous-valued attributes in decision tree with neural network modelling, in: Machine learning: ECML 2000, 11th European Conference on Machine Learning, Barcelona, Catalonia, Spain, May 31-June 2, 2000, pp. 211-219.

[21] R. Setiono, W.K. Leow, J.M. Zurada, Extraction of rules from artificial neural networks for nonlinear regression, IEEE Trans. Neural Netw. 13 (3) (2002) 564-577.

[22] R. Setiono, J.Y.L. Thong, An approach to generate rules from neural networks for regression problems, Eur. J. Oper. Res. 155 (1) (2004) 239-250.

[23] K. Odajim, Y. Hayashi, G. Tianxia, R. Setiono, Greedy rule generation from discrete data and its use in neural network rule extraction, Neural Netw. 21 (7) (2008) 1020-1028.

[24] J. Wang, B. Qin, W. Zhang, W. Shi, Regression rules extraction from artificial neural network based on least squares, in: Proceedings e 2011 7th International Conference on Natural Computation, ICNC, 2011, pp. 203-207, 2011(1).

[25] S.B. Thrun, Extracting Provably Correct Rules from Artificial Neural Networks, University of Bonn, 1993. Retrieved from: http://citeseerx.ist.psu. edu/viewdoc/download?doi=10.1.1.2.2110&rep=rep1&type=pdf.

[26] M.W. Craven, J.W. Shavlik,Extracting tree-structured representations of trained neural networks, Adv. Neural Inf. Process. Syst. 8 (1996) 24-30.

[27] E.W. Saad, D.C. Wunsch, Neural network explanation using inversion, Neural Netw. 20 (1) (2007) 78-93.

[28] E.J. de Fortuny, D. Martens, Active learning based rule extraction for regression, in: 2012 IEEE 12th International Conference on Data Mining Workshops, 2012, pp. 926-933.

[29] M.G. Augasta, T. Kathirvalavakumar,Rule extraction from neural networks e a comparative study, in:Proceedings of the International Conference on Pattern Recognition, 2012. Informatics and Medical Engineering.

[30] E.R. Hruschka, N. Ebecken, Extracting rules from multilayer perceptrons in classification problems: a clustering-based approach, Neurocomputing 70 (1-3) (2006) 384-397.

[31] M.H. Mohamed, Rules extraction from constructively trained neural networks based on genetic algorithms, Neurocomputing 74 (17) (2011) 3180-3192.

[32] R. Al Iqbal, Eclectic extraction of propositional rules from neural networks, in: 14th International Conference on Computer and Information Technology, ICCIT, 2011, pp. 234-239.

[33] M. Lichman, UCI Machine Learning Repository, University of California, School of Information and Computer Science, Irvine, CA, 2013. http://archive.ics.uci.edu/ml (accessed 07 May 2015).

[34] Y. Wu,Some Artificial Intelligence Applications Ofr Carbon Dioxide Capture Process (Unpublished master's thesis), University of Regina, Canada, 2009.