This content is not included in your SAE MOBILUS subscription, or you are not logged in.
Neural Network Application to Evaluate Thermodynamic Properties of ICE's Combustion Gases
ISSN: 0148-7191, e-ISSN: 2688-3627
Published April 11, 2005 by SAE International in United States
Annotation ability available
In this paper, the authors have investigated a new neural network application for the determination of thermodynamic properties for various gases for internal combustion engines applications.
The Neural Network has been trained using experimental data available in literature (specific heat at constant pressure, enthalpy, entropy and equilibrium constants for thirteen gases of practical interest inside ICE applications).
In the present study a two-layer Elman network feedback from the first-layer output to the first layer input as well as “tansig” neurons in its hidden and out layers has been implemented.
After the training, neural network has been tested through a comparison with the NASA equations and JANAF equations, showing the capability to cover with a single model wide range of temperature with an accuracy equal or greater than others mathematical function. Thermodynamic properties of gases have been calculated depending on temperature. In order to evaluate the relative percent error Neural Network thermodynamic results have been compared with experimental data.
Neural Networks have been implemented to calculate the thermodynamic properties of several gases: N, O, H, H2, O2, N2, CO, OH, NO, CO2, Ar, N2O and H2O.
CitationBrusca, S., Lanzafame, R., and Messina, M., "Neural Network Application to Evaluate Thermodynamic Properties of ICE's Combustion Gases," SAE Technical Paper 2005-01-1128, 2005, https://doi.org/10.4271/2005-01-1128.
- Acton O. Caputo C. “Introduzione allo studio delle macchine” UTET 1979
- Spencer H. M. Flannagan G. N. “Empirical Heat Capacity equations of Gases” J. Am. Chem. Soc. 64 1942
- Gordon S. McBride B.J. “Computer Program for Calculation of Complex Chemical Equilibrium Composition and Applications” NASA Reference Publication 1311 1994
- Floreano, D. “Manuale sulle reti neurali” Il Mulino 1996
- Ingrassia, S. Davino, C. “Reti neuronali e metodi statistic” Franco Angeli 2002
- Hopfield, J. J. Tank, D. W. “Computing with Neural Circuits: A Model Properties Like Those of Two State Neurons” Science 233 625 633
- Elman, J. L. “Finding structure in time” Cognitive Science 14 1990 179 211
- Lanzafame, R. Santangelo, G. “A Neural Logic Program as a New Method for the Development of Fluids Thermodynamic Properties” The International Association of Science and Thecnology for Development - IASTED International Conference July 27 1 August 1997 Banff, Canada
- Glushko V.P. Gurvich L.V. Bergman G.A. Veyts I.V. Medvedev V.A. Khachkuruzov G.A. Yungman V.S. “Thermodynamic Properties of Individual Substances” Academy of Sciences Moscow, USSR 1991 2 27 30
- Woolley H.W. “Ideal Gas Thermodynamic Functions for Water” J. Research of National Bureau of Standards 92 1 1987 35 53
- Glushko V.P. Gurvich L.V. Bergman G.A. Veyts I.V. Medvedev V.A. Khachkuruzov G.A. Yungman V.S. “Thermodynamic Properties of Individual Substances” Academy of Sciences Moscow, USSR 1979 2 29 30
- Chase M.W. Jr. NIST-JANAF Thermochemical Tables Fourth J. Phys. Chem. Ref. Data, Monograph 9 1998 1 1951
- Gordon S. McBride B. “Thermodynamic Data to 20000 K for monatomic gas”
- Gurvich L.V. et al. “Thermodynamic Properties of Individual Substances” 1 Nauka Moscow
- Gurvich L.V. Veyts I.V. Alcock C.B. “Thermodynamic Properties of Individual Substances” Fourth 1 Hemisphere Publishing Corp. Ew York 1989 http://www.grc.nasa.gov/WWW/CEAWeb/
- Horlock Winterbone “The Thermodynamics and Gas Dynamics of Internal Combustion Engines” Oxford Science Publications 1986