Pallarés Ranz, Javier
Arauzo Pelet, Inmaculada (dir.)
Universidad de Zaragoza,
2008
ISBN: 978-84-691-7194-3
Abstract: El sistema de predicción de inquemados desarrollado en esta Tesis tiene la misma estructura que los llamados modelos cinéticos de combustión avanzados; sin embargo, obtiene la descripción fluidodinámica y térmica por medio de simulaciones CFD. Para resolver el handicap del alto coste computacional, se ha implementado un sistema de redes neuronales que reproduce las soluciones obtenidas con el código CFD. Además, el sistema de redes neuronales permite interpolar para diferentes condiciones, dando lugar a un sistema de predicción de inquemados que cubre todo el rango de operación de una planta de combustión convencional.
Abstract (other lang.): The predictive system developed in this Thesis has the same structure as the so-called combustion kinetics models, however, it obtains the fluid and thermal description through CFD simulations. To solve the handicap of the high computational cost needed to run a CFD simulation, a neural network system is used to reproduce the solutions given by the CFD code. Moreover, a neural network system permits to interpolate in the range of variation used during the training stage, and thus, a predictive system covering the whole operational range of the plant is obtained.
Abstract (other lang.): The predictive system developed in this Thesis has the same structure as the so-called combustion kinetics models, however, it obtains the fluid and thermal description through CFD simulations. To solve the handicap of the high computational cost needed to run a CFD simulation, a neural network system is used to reproduce the solutions given by the CFD code. Moreover, a neural network system permits to interpolate in the range of variation used during the training stage, and thus, a predictive system covering the whole operational range of the plant is obtained.
Abstract (other lang.): The predictive system developed in this Thesis has the same structure as the so-called combustion kinetics models, however, it obtains the fluid and thermal description through CFD simulations. To solve the handicap of the high computational cost needed to run a CFD simulation, a neural network system is used to reproduce the solutions given by the CFD code. Moreover, a neural network system permits to interpolate in the range of variation used during the training stage, and thus, a predictive system covering the whole operational range of the plant is obtained.
Abstract (other lang.): The predictive system developed in this Thesis has the same structure as the so-called combustion kinetics models, however, it obtains the fluid and thermal description through CFD simulations. To solve the handicap of the high computational cost needed to run a CFD simulation, a neural network system is used to reproduce the solutions given by the CFD code. Moreover, a neural network system permits to interpolate in the range of variation used during the training stage, and thus, a predictive system covering the whole operational range of the plant is obtained.
Pal. clave: Inquemados en cenizas ; Modelización combustión de carbon ; CFD ; Redes neuronales
Knowledge area: Máquinas y motores térmicos
Department: Ingeniería Mecánica
Nota: Presentado: 05 02 2008
Nota: Tesis-Univ. Zaragoza
-
Permalink:
Visitas y descargas
Record created 2014-11-20, last modified 2019-02-19
PDF