DOI QR코드

DOI QR Code

Gas detonation cell width prediction model based on support vector regression

  • Yu, Jiyang (Department of Engineering Physics, Tsinghua University) ;
  • Hou, Bingxu (CNNC China Zhongyuan Engineering Corporation) ;
  • Lelyakin, Alexander (Institute for Nuclear and Energy Technologies, Karlsruhe Institute of Technology) ;
  • Xu, Zhanjie (Institute for Nuclear and Energy Technologies, Karlsruhe Institute of Technology) ;
  • Jordan, Thomas (Institute for Nuclear and Energy Technologies, Karlsruhe Institute of Technology)
  • Received : 2016.11.28
  • Accepted : 2017.06.19
  • Published : 2017.10.25

Abstract

Detonation cell width is an important parameter in hydrogen explosion assessments. The experimental data on gas detonation are statistically analyzed to establish a universal method to numerically predict detonation cell widths. It is commonly understood that detonation cell width, ${\lambda}$, is highly correlated with the characteristic reaction zone width, ${\delta}$. Classical parametric regression methods were widely applied in earlier research to build an explicit semiempirical correlation for the ratio of ${\lambda}/{\delta}$. The obtained correlations formulate the dependency of the ratio ${\lambda}/{\delta}$ on a dimensionless effective chemical activation energy and a dimensionless temperature of the gas mixture. In this paper, support vector regression (SVR), which is based on nonparametric machine learning, is applied to achieve functions with better fitness to experimental data and more accurate predictions. Furthermore, a third parameter, dimensionless pressure, is considered as an additional independent variable. It is found that three-parameter SVR can significantly improve the performance of the fitting function. Meanwhile, SVR also provides better adaptability and the model functions can be easily renewed when experimental database is updated or new regression parameters are considered.

Keywords

References

  1. J. Shepherd, Detonation in gases, Proc. Combust. Inst. 32 (2009) 83-98. https://doi.org/10.1016/j.proci.2008.08.006
  2. G. Ciccarelli, T. Ginsberg, J.L. Boccio, Detonation Cell Size Measurements in High-temperature Hydrogen-air-steam Mixtures at the BNL High-temperature Combustion Facility, Rep. No. NUREG/CR-6391; BNL-NUREG-52482, U.S. Nuclear Regulatory Commission, Rockville, MD, 1997.
  3. S.B. Dorofeev, V.P. Sidorov, M.S. Kuznetsov, I.D. Matsukov, V.I. Alekseev, Effect of scale on the onset of detonations, Shock Waves 10 (2000) 137-149. https://doi.org/10.1007/s001930050187
  4. W. Breitung, C. Chan, S. Dorofeev, A. Eder, B. Gelfand, M. Heitsch, R. Klein, A. Malliakos, E. Shepherd, E. Studer, P. Thibault, Flame Acceleration and Deflagration-to-detonation Transition in Nuclear Safety, Nuclear Safety Rep. No. NEA/CSNI/R(2000)7, OECD Nuclear Energy Agency, Issy-les-Moulineaux, France, 2000, pp. 1-455.
  5. S. Dorofeev, A. Bezmelnitsin, V. Sidorov, DDT Scaling for Severe Accidents. Detonation Cell Size Data as a Function of Composition and Initial Conditions, Rep. No. RRC "Kurchatov Institute" RRC KI, 80-05, 1997.
  6. K. Shchelkin, Y. Troshin, Gas Dynamics of Detonations, Mono Book Corp., Baltimore, MD, 1965.
  7. J. Shepherd, I.O. Moen, S.B. Murray, P.A. Thibalut, Analyses of the cellular structure of detonations, in: Symposium (International) on Combustion (Vol. 21, No. 1)Elsevier, Amsterdam, Netherlands, 1988, pp. 1649-1658.
  8. H. Lee, D. Stewart, Calculation of linear detonation instability: one-dimensional instability of plane detonation, J. Fluid Mech. 216 (1990) 103-132. https://doi.org/10.1017/S0022112090000362
  9. S. Sch€offel, F. Ebert, A numerical investigation of the reestablishment of a quenched gaseous detonation in a Galilei-transformed system, in: Proceedings of the 16th International Symposium on Shock Tubes and Waves, Aachen, FRG, 1987, pp. 779-786.
  10. A. Gavrikov, A.A. Efimenko, S.B. Dorofeev, A model for detonation cell size prediction from chemical kinetics, Combust. Flame 120 (2000) 19-33. https://doi.org/10.1016/S0010-2180(99)00076-0
  11. R. Akbar, M. Kaneshige, E. Schultz, J. Shepherd, Detonations in $H_2-N_2O-CH_4-NH_3-O_2-N_2$ Mixtures, Explosion Dynamics Laboratory Rep. No. FM97-3, Graduate Aeronautical Laboratories, California Institute of Technology, Pasadena, CA, 2000.
  12. W. Hardle, E. Mammen, Comparing nonparametric versus parametric regression fits, Ann. Stat. 21 (1993) 1926-1947. https://doi.org/10.1214/aos/1176349403
  13. J. Shepherd, AIAA Progress in Astronautics and Aeronautics, vol. 106, AIAA, New York, 1986, p. 263.
  14. M. Kaneshige, J.E. Shepherd, Detonation Database, Technical Rep. FM97-F98, GALCIT, 1997 [cited 2017 Jul 17]. Available from: http://www.galcit.caltech.edu/detn_db/html/.
  15. D.Goodwin, H.K.Moffat, R.L. Speth, Cantera: an Object-Oriented Software Toolkit for Chemical Kinetics, Thermodynamics, and Transport Processes (Version 2.2.1), 2016 [cited 2017 Jul 17]. Available from: http://www.cantera.org.
  16. J.G. Carbonell, R.S. Michalski, T.M. Mitchell, An overview of machine learning, in: Machine Learning, Springer, Berlin, Germany, 1983, pp. 3-23.
  17. A. Smola, B. Scholkopf, A tutorial on support vector regression, Stat. Comput. 14 (2004) 199-222. https://doi.org/10.1023/B:STCO.0000035301.49549.88
  18. D. Basak, S. Pal, D.C. Patranabis, Support vector regression, Neural Inf. Process. Lett. Rev. 11 (2007) 203-224.
  19. R. Kohavi, A study of cross-validation and bootstrap for accuracy estimation and model selection, in: Proc. International Joint Conference on Artificial Intelligence, vol. 14, Morgan Kaufmann, San Francisco, CA, 1995, pp. 1137-1145.
  20. F. Pedregosa, Scikit-learn: machine learning in python, J. Mach. Learn. Res. 12 (2011) 2825-2830.

Cited by

  1. Detonation cell size model based on deep neural network for hydrogen, methane and propane mixtures with air and oxygen vol.51, pp.2, 2017, https://doi.org/10.1016/j.net.2018.11.004
  2. A flammability limit model for hydrogen-air-diluent mixtures based on heat transfer characteristics in flame propagation vol.51, pp.7, 2017, https://doi.org/10.1016/j.net.2019.05.005
  3. Estimation of Wind Turbine Energy Production Value by Using Machine Learning Algorithms and Development of Implementation Program vol.43, pp.6, 2017, https://doi.org/10.1080/15567036.2019.1631410