Ograniczanie wyników
Preferencje help
Widoczny [Schowaj] Abstrakt
Liczba wyników
Powiadomienia systemowe
  • Sesja wygasła!

Znaleziono wyników: 2

Liczba wyników na stronie
first rewind previous Strona / 1 next fast forward last
Wyniki wyszukiwania
Wyszukiwano:
w słowach kluczowych:  GriMech 3
help Sortuj według:

help Ogranicz wyniki do:
first rewind previous Strona / 1 next fast forward last
1
Content available The CH4 combustion model
EN
The paper presents results of research on the possibility of approximation of the results of calculations using the GriMech 3 kinetic mechanism by an artificial neural network (ANN). Application of kinetic mechanisms for modeling of combustion process in the finite element method requires considerable computing power which is associated with high costs of modeling. It is therefore necessary to seek alternative solutions in this area. The paper focuses on the possibility of application of ANN to approximate the total heat release from the combustion of methane. We built and trained ANN allows the approximation of the total heat release from the combustion process with a mean square error not exceeding 0.04% and the individual error for one result equal to 1.9%. Inputs for this model are the temperature and pressure of the combustion process and 52 mole fractions of chemical species in combusted mixture taken into account in the GriMech 3 kinetic model. For this reason, we tried to build and train the ANN approximating the mentioned mole fractions of chemical species. During the study we tested different configurations of ANN’s, containing different numbers of hidden layers and different numbers of neurons in the output and the hidden layer. The best results were obtained for the approximation of the ANN with one hidden layer containing 38 neurons. It was built and trained 52 ANN’s, one for each chemical species. Unfortunately, even for obtained small values of mean square errors of approximation, errors of individual results often exceed 100% of the results obtained from the kinetic calculations. For this reason, the application of ANN in the presented form to approximate mole fractions of chemical species is impossible.
2
Content available The ann approximation of the CH4 combustion model
EN
This paper presents the research effect of the modeling of the CH4 combustion process in different conditions. Presented model was prepared with using the GriMech 3 chemical kinetic mechanism of methane combustion. Its mechanism developed by research unit from University of Berkley and verified by more than 140 science publications. Mechanism GriMech 3 consist of description of reactions between 52 assumed chemical species and thermodynamic data of these reactions and chemical species. The paper presents algorithm of calculations the summarize heat release from combustion process and changing of chemical species mole fractions. Calculations was prepared for different temperature from 1100K to 3600K, different pressure from 2MPa to 5MPa and different combusted mixture composition (changing the humidity of air from 4,5 to 30gH2O/kg of air and air-fuel excess ratio from 0.8 to 2.5). Obtained results of calculations show dependences between mentioned parameters and time of combustion process. Increase temperature and/or pressure of combustion accelerate the combustion process and same process stay sudden. Increasing the quantity of air in fuel mixture causes a significant drop of the maximum heat release but accelerates the combustion process. The changing of quantity of water in combusted mixture not give the significant effect in heat release but changes mole fractions of a few chemical species.
first rewind previous Strona / 1 next fast forward last
JavaScript jest wyłączony w Twojej przeglądarce internetowej. Włącz go, a następnie odśwież stronę, aby móc w pełni z niej korzystać.