A new predictive neural architecture for solving temperature inverse problems in microwave-assisted drying processes
Ver/
Identificadores
URI: http://hdl.handle.net/10317/1476Compartir
Métricas
Estadísticas
Ver Estadísticas de usoMetadatos
Mostrar el registro completo del ítemGrupo de investigación
Electromagnetismo y MateriaÁrea de conocimiento
Teoría de la Señal y las ComunicacionesFecha de publicación
2004-03Editorial
ElsevierCita bibliográfica
PEDREÑO MOLINA, J.L., MONZÓ CABRERA, J., SÁNCHEZ HERNÁNDEZ, D. A new predictive neural architecture for solving temperature inverse problems in microwave-assisted drying processes. Neurocomputing, vol. 64 : 521-528, 2004. ISSN 0925-2312Revisión por pares
SíPalabras clave
Learning-based predictive systemElectric field estimation
Neural network modeling
Microwave-assisted drying applications
Inverse problem
Resumen
In this paper, a novel learning architecture based on neural networks is used for temperature
inverse modeling in microwave-assisted drying processes. The proposed design combines the
accuracy of the radial basis functions (RBF) and the algebraic capabilities of the matrix
polynomial structures by using a two-level structure. This architecture is trained by
temperature curves, TcðtÞ; previously generated by a validated drying model. The
interconnection of the learning-based networks has enabled the finding of electric field (E)
optimal values which provide the TcðtÞ curve that best fits a desired temperature target in a
specific time slot
Colecciones
- Artículos [1738]
El ítem tiene asociados los siguientes ficheros de licencia:
Redes sociales