UTILIZATION OF BASIC MULTI-LAYER PERCEPTRON ARTIFICIAL NEURAL NETWORKS TO RESOLVE TURBULENT FINE STRUCTURE CHEMICAL KINETICS APPLIED TO A CFD MODEL OF A METHANE/AIR PILOTED JET FLAME

Year 2018, , 1828 - 1846, 20.12.2017

Ryno Laubscher

https://doi.org/10.18186/journal-of-thermal-engineering.381838

Cited By: 10

Abstract

This work
investigates and proposes an alternative chemistry integration approach to be
used with the eddy dissipation concept (EDC) advanced combustion model. The
approach uses basic multi-layer perceptron (MLP) artificial neural networks
(ANNs) as a chemistry integrator for the reactions that take place in the fine
structure regions created by the turbulence field. The ANNs are therefore
utilised to predict the incremental species changes that occur in these fine
structure regions as a function of the initial species composition, temperature
and the residence time of the mixture in the fine structure regions. The
chemistry integration approach for the EDC model was implemented to model a
piloted methane/air turbulent jet diffusion flame (Sandia Flame D) at a
Reynolds number of 22400. To prove the concept, a five-step methane combustion
mechanism was used to model the chemical reactions of the experimental flame.
The results of the new approach were benchmarked against experimental data and
the simulation results using the standard integration approaches in Fluent. It
was shown that once the ANNs are well-trained (in-sample error minimised as
best possible), it can predict the species mass fractions with relative
accuracy in a manner that is both time and computer-memory efficient compared
with using traditional integration procedures.

Keywords

Computational Fluid Dynamics, Artificial Neural Networks, Machine Learning, Chemical Kinetics, Combustion, Eddy Dissipation Concept

References

• [1] Scharler, R. (2016) CFD simulation of biomass combustion plants-new developments. http://www.ieabcc.nl/workshops/task32_2013_CPH/04_scharler.pdf.
• [2] Magnussen, B. F., & Hjertager, B. H. (1977, December). On mathematical modeling of turbulent combustion with special emphasis on soot formation and combustion. In Symposium (international) on Combustion (Vol. 16, No. 1, pp. 719-729).
• [3] Shiehnejadhesar, A., Mehrabian, R., Scharler, R., Goldin, G. M., & Obernberger, I. (2014). Development of a gas phase combustion model suitable for low and high turbulence conditions. Fuel, 126, 177-187.
• [4] Scharler, R., Fleckl, T., & Obernberge, I. (2003). Modification of a Magnussen Constant of the Eddy Dissipation Model for biomass grate furnaces by means of hot gas in-situ FT-IR absorption spectroscopy. Progress in Computational Fluid Dynamics, an International Journal, 3(2-4), 102-111.
• [5] De, A., Oldenhof, E., Sathiah, P., & Roekaerts, D. (2011). Numerical simulation of delft-jet-in-hot-coflow (djhc) flames using the eddy dissipation concept model for turbulence–chemistry interaction. Flow, Turbulence and Combustion, 87(4), 537-567.
• [6] Byrne, G. D., & Dean, A. M. (1993). The numerical solution of some kinetics models with VODE and CHEMKIN II. Computers & chemistry, 17(3), 297-302.
• [7] Pope, S. B. (1997). Computationally efficient implementation of combustion chemistry using in situ adaptive tabulation.
• [8] Christo, F. C., Masri, A. R., & Nebot, E. M. (1996). Artificial neural network implementation of chemistry with pdf simulation of H 2/CO 2 flames. Combustion and Flame, 106(4), 406-427.
• [9] Barlow, R. S., & Frank, J. (2003). Piloted CH4/Air Flames C, D, E, and F-Release 2.0. Sandia National Laboratories CA.
• [10] Sen, B. A., & Menon, S. (2009). Turbulent premixed flame modeling using artificial neural networks based chemical kinetics. Proceedings of the Combustion Institute, 32(1), 1605-1611.
• [11] Blasco, J. A., Fueyo, N., Dopazo, C., & Ballester, J. (1998). Modelling the temporal evolution of a reduced combustion chemical system with an artificial neural network. Combustion and Flame, 113(1), 38-52.
• [12] Kempf, A., Flemming, F., & Janicka, J. (2005). Investigation of lengthscales, scalar dissipation, and flame orientation in a piloted diffusion flame by LES. Proceedings of the Combustion Institute, 30(1), 557-565.
• [13] Emami, M. D., & Fard, A. E. (2012). Laminar flamelet modeling of a turbulent CH 4/H 2/N 2 jet diffusion flame using artificial neural networks. Applied Mathematical Modelling, 36(5), 2082-2093.
• [14] Christo, F. C., Masri, A. R., Nebot, E. M., & Pope, S. B. (1996, January). An integrated PDF/neural network approach for simulating turbulent reacting systems. In Symposium (International) on Combustion (Vol. 26, No. 1, pp. 43-48).
• [15] Poinsot, T., & Veynante, D. (2005). Theoretical and numerical combustion. RT Edwards, Inc..
• [16] Kuo Kenneth, K. (2005). Principles of combustion.
• [17] Glassman, I., & Yetter, R. A. (1987). Combustion, Chap. 3.
• [18] Wang, L., Liu, Z., Chen, S., & Zheng, C. (2012). Comparison of different global combustion mechanisms under hot and diluted oxidation conditions. Combustion Science and Technology, 184(2), 259-276.
• [19] Westbrook, C. K., & Dryer, F. L. (1984). Chemical kinetic modeling of hydrocarbon combustion. Progress in Energy and Combustion Science, 10(1), 1-57.
• [20] Hindmarsh, A. C. (1983). ODEPACK, A Systematized Collection of ODE Solvers, RS Stepleman et al.(eds.), North-Holland, Amsterdam,(vol. 1 of), pp. 55-64. IMACS transactions on scientific computation, 1, 55-64.
• [21] Kee, R. J., Rupley, F. M., Miller, J. A., & II, C. (1996). a Fortran chemical kinetics package for the analysis of gas-phase chemical kinetics, Report No. SAND89-8009B, Sandia National Laboratories.
• [22] Laubscher, R. (2017). Utilization of artificial neural networks to resolve chemical kinetics in turbulent fine structures of an advanced CFD combustion model (Doctoral dissertation, Stellenbosch: Stellenbosch University).
• [23] Kleiber, M., & Joh, R. (2010). D1 calculation methods for thermophysical properties. In VDI Heat Atlas (pp. 119-152). Springer Berlin Heidelberg.
• [24] Laubscher, R. (2015). Advanced modelling of homogenous volatile combustion through the use of reduced chemical mechanisms. In Proceedings of the Annual Congress-South African Sugar Technologists' Association (No. 88, pp. 138-150).
• [25] Yin, C. (2011). Advanced modeling of oxy-fuel combustion of natural-gas. Tech. Rep., Department of Energy Technology, University of Aalborg.
• [26] Yin, C. (2011). Advanced modeling of oxy-fuel combustion of natural-gas. Tech. Rep., Department of Energy Technology, University of Aalborg.
• [27] Andersen, J., Glarborg, P., Jensen, P. A., & Lovmand Hvid, S. (2009). Experimental and CFD investigation of gas phase freeboard combustion (Doctoral dissertation, DONG Energy A/SDONG Energy A/S).