Nuclear Engineering and Technology

Korean Nuclear Society (한국원자력학회)
권호 표지
DOI QR코드

DOI QR Code

Detonation cell size model based on deep neural network for hydrogen, methane and propane mixtures with air and oxygen

  • Malik, Konrad (Warsaw University of Technology, Institute of Heat Engineering) ;
  • Zbikowski, Mateusz (Warsaw University of Technology, Institute of Heat Engineering) ;
  • Teodorczyk, Andrzej (Warsaw University of Technology, Institute of Heat Engineering)
  • Received : 2018.08.11
  • Accepted : 2018.11.06
  • Published : 2019.04.25
Download PDF
⟨ Previous Next ⟩

Abstract

The aim of the present study was to develop model for detonation cell sizes prediction based on a deep artificial neural network of hydrogen, methane and propane mixtures with air and oxygen. The discussion about the currently available algorithms compared existing solutions and resulted in a conclusion that there is a need for a new model, free from uncertainty of the effective activation energy and the reaction length definitions. The model offers a better and more feasible alternative to the existing ones. Resulting predictions were validated against experimental data obtained during the investigation of detonation parameters, as well as with data collected from the literature. Additionally, separate models for individual mixtures were created and compared with the main model. The comparison showed no drawbacks caused by fitting one model to many mixtures. Moreover, it was demonstrated that the model may be easily extended by including more independent variables. As an example, dependency on pressure was examined. The preparation of experimental data for deep neural network training was described in detail to allow reproducing the results obtained and extending the model to different mixtures and initial conditions. The source code of ready to use models is also provided.

Keywords

References

  1. M. Dehjourian, R. Sayareh, M. Rahgoshay, G. Jahanfarnia, A.S. Shirani, Investigation of a hydrogen mitigation system during large break loss-of-coolant accident for a two-loop pressurized water reactor, Nuclear Engineering and Technology 48 (5) (2016) 1174-1183, https://doi.org/10.1016/j.net.2016.04.002.
  2. A. Venetsanos, T. Huld, P. Adams, J. Bartzis, Source, dispersion and combustion modelling of an accidental release of hydrogen in an urban environment, J. Hazard Mater. 105 (1-3) (2003) 1-25, https://doi.org/10.1016/j.jhazmat.2003.05.001.
  3. V. Molkov, A. Grigorash, R. Eber, D. Makarov, Vented gaseous deflagrations, J. Hazard Mater. 116 (1-2) (2004) 1-10, https://doi.org/10.1016/j.jhazmat.2004.08.027.
  4. P. Middha, O.R. Hansen, J. Grune, A. Kotchourko, CFD calculations of gas leak dispersion and subsequent gas explosions: validation against ignited impinging hydrogen jet experiments, J. Hazard Mater. 179 (1-3) (2010) 84-94, https://doi.org/10.1016/j.jhazmat.2010.02.061.
  5. M. Zbikowski, D. Makarov, V. Molkov, Numerical simulations of large-scale detonation tests in the RUT facility by the LES model, J. Hazard Mater. 181 (1-3) (2010) 949-956, https://doi.org/10.1016/j.jhazmat.2010.05.105.
  6. J. Shepherd, Chemical kinetics of hydrogen-air-diluent detonations, in: Dynamics of Explosions, American Institute of Aeronautics and Astronautics, 1986, pp. 263-293, https://doi.org/10.2514/5.9781600865800.0263.0293.
  7. L.J. Rodriguez-Aragon, J. Lopez-Fidalgo, Optimal designs for the arrhenius equation, Chemometr. Intell. Lab. Syst. 77 (1-2) (2005) 131-138, https://doi.org/10.1016/j.chemolab.2004.06.007.
  8. A. Teodorczyk, J. Lee, R. Knystautas, Propagation mechanism of quasi-detonations, Symposium (International) on Combustion 22 (1) (1989) 1723-1731, https://doi.org/10.1016/s0082-0784(89)80185-7.
  9. S. Dorofeev, Deflagration to detonation transition in large confined volume of lean hydrogen-air mixtures, Combust. Flame 104 (1-2) (1996) 95-110, https://doi.org/10.1016/0010-2180(95)00113-1.
  10. K. Shchelkin, I. Troshin, Gasdynamics of Combustion, Mono Book Corporation, 1965.
  11. A.N. Dremin, Toward Detonation Theory (Shock Wave and High Pressure Phenomena), Springer, 2012.
  12. A. Gavrikov, A. Efimenko, S. Dorofeev, A model for detonation cell size prediction from chemical kinetics, Combust. Flame 120 (1-2) (2000) 19-33, https://doi.org/10.1016/s0010-2180(99)00076-0.
  13. J. Yu, B. Hou, A. Lelyakin, Z. Xu, T. Jordan, Gas detonation cell width prediction model based on support vector regression, Nuclear Engineering and Technology 49 (7) (2017) 1423-1430, https://doi.org/10.1016/j.net.2017.06.014.
  14. C. Olm, I.G. Zsely, R. Palvolgyi, T. Varga, T. Nagy, H.J. Curran, T. Turanyi, Comparison of the performance of several recent hydrogen combustion mechanisms, Combust. Flame 161 (9) (2014) 2219-2234, https://doi.org/10.1016/j.combustflame.2014.03.006.
  15. A. Jach, W. Rudy, A. Teodorczyk, A. Pekalski, Validation of Detailed Chemical Kinetics Mechanisms for Reproduction of Ignition Delay Times of C2-c5 Alkenes doi:10.13140/rg.2.2.15956.50564.
  16. W. Rudy, A. Jach, A. Pekalski, A. Teodorczyk, Chemical Reaction Mechanisms Validation Based on Ignition Delay Time of C1-c5 Hydrocarbons doi:10.13140/rg.2.2.29305.36963.
  17. Y. Lecun, L. Bottou, Y. Bengio, P. Haffner, Gradient-based learning applied to document recognition, Proc. IEEE 86 (11) (1998) 2278-2324, https://doi.org/10.1109/5.726791.
  18. J. Tompson, K. Schlachter, P. Sprechmann, K. Perlin, Accelerating Eulerian Fluid Simulation with Convolutional Networks, ArXiv e-printsarXiv: 1607.03597.
  19. Z. Shang, Application of artificial intelligence CFD based on neural network in vapor-water two-phase flow, Eng. Appl. Artif. Intell. 18 (6) (2005) 663-671, https://doi.org/10.1016/j.engappai.2005.01.007.
  20. A. Elkamel, A. Al-Ajmi, M. Fahim, Modeling the hydrocracking process using artificial neural networks, Petrol. Sci. Technol. 17 (9-10) (1999) 931-954, https://doi.org/10.1080/10916469908949757.
  21. P.H. Ibarguengoytia, M.A. Delgadillo, U.A. Garcia, A. Reyes, Viscosity virtual sensor to control combustion in fossil fuel power plants, Eng. Appl. Artif. Intell. 26 (9) (2013) 2153-2163, https://doi.org/10.1016/j.engappai.2013.05.004.
  22. L. Elliott, D. Ingham, A. Kyne, N. Mera, M. Pourkashanian, C. Wilson, The use of ignition delay time in genetic algorithms optimisation of chemical kinetics reaction mechanisms, Eng. Appl. Artif. Intell. 18 (7) (2005) 825-831, https://doi.org/10.1016/j.engappai.2005.02.006.
  23. K. Malik, M. Zbikowski, P. Lesiak, A. Teodorczyk, Numerical and experimental investigation of methane-oxygen detonation in a 9 m long tube, Journal of KONES 23 (4) (2016) 311-318, https://doi.org/10.5604/12314005.1217241.
  24. R. Knystautas, Measurement of cell size in hydrocarbon-air mixtures and predictions of critical tube diameter, critical initiation energy and detonability limits, Prog. Astronaut. Aeronaut. 94 (1984) 23-37.
  25. R. Zipf, V. Gamezo, M. Sapko, W. Marchewka, K. Mohamed, E. Oran, D. Kessler, E. Weiss, J. Addis, F. Karnack, D. Sellers, Methane-air detonation experiments at NIOSH lake lynn laboratory, J. Loss Prev. Process. Ind. 26 (2) (2013) 295-301, https://doi.org/10.1016/j.jlp.2011.05.003.
  26. L. Wang, H. Ma, Z. Shen, B. Xue, Y. Cheng, Z. Fan, Experimental investigation of methane-oxygen detonation propagation in tubes, Appl. Therm. Eng. 123 (2017) 1300-1307, https://doi.org/10.1016/j.applthermaleng.2017.05.045.
  27. D.W. Stamps, S.R. Tieszen, The influence of initial pressure and temperature on hydrogen-air-diluent detonations, Combust. Flame 83 (3-4) (1991) 353-364, https://doi.org/10.1016/0010-2180(91)90082-m.
  28. K. Hornik, Approximation capabilities of multilayer feedforward networks, Neural Network. 4 (2) (1991) 251-257, https://doi.org/10.1016/0893-6080(91)90009-t.
  29. D.G. Goodwin, H.K. Moffat, R.L. Speth, Cantera: an Object-oriented Software Toolkit for Chemical Kinetics, Thermodynamics, and Transport Processes, 2017. http://www.cantera.org.
  30. M.F. Triola, Elementary Statistics, thirteenth ed., Pearson, 2017.
  31. SDToolbox, http://shepherd.caltech.edu/EDL/public/cantera/html/SD_Toolbox/, accessed: 2018-01-20.
  32. A.E. Hoerl, R.W. Kennard, Ridge regression: biased estimation for nonorthogonal problems, Technometrics 12 (1) (1970) 55-67, https://doi.org/10.1080/00401706.1970.10488634.
  33. J. Bergstra, R. Bardenet, Y. Bengio, B. Kegl, Algorithms for hyper-parameter optimization, in: P.B.F.P.K.W.J. Shawe-Taylor, R.S. Zemel (Eds.), 25th Annual Conference on Neural Information Processing Systems (NIPS 2011), Vol. 24 of Advances in Neural Information Processing Systems, Neural Information Processing Systems Foundation, Granada, Spain, 2011.
  34. G. Klima, FCNN4R: Fast Compressed Neural Networks for R, R Package, 2016 version 0.6.2.
  35. M.W. Browne, Cross-validation methods, J. Math. Psychol. 44 (1) (2000) 108-132, https://doi.org/10.1006/jmps.1999.1279.
  36. M. Riedmiller, Rprop - Description and Implementation Details: Technical Report, Inst. f. Logik, Komplexitat u. Deduktionssysteme, 1994.
  37. G.P. Smith, D.M. Golden, M. Frenklach, B. Eiteener, M. Goldenberg, C.T. Bowman, R.K. Hanson, W.C. Gardiner, V.V. Lissianski, Z.W. Qin, GRI-Mech 3.0, URL, , 2000. http://www.me.berkeley.edu/gri\_mech/.

Cited by

  1. ConvXGB: A new deep learning model for classification problems based on CNN and XGBoost vol.53, pp.2, 2021, https://doi.org/10.1016/j.net.2020.04.008
  2. Inhibition effect and mechanism of ultra-fine water mist on CH4/air detonation: Quantitative research based on CFD technology vol.148, 2021, https://doi.org/10.1016/j.psep.2020.10.007
  3. Predictive modelling of turbofan engine components condition using machine and deep learning methods vol.23, pp.2, 2019, https://doi.org/10.17531/ein.2021.2.16