Skip to main content
Ir a la página de inicio de la Comisión Europea (se abrirá en una nueva ventana)
español es
CORDIS - Resultados de investigaciones de la UE
CORDIS
Contenido archivado el 2024-06-11

Intelligent forecasting systems for refineries and power systems

CORDIS proporciona enlaces a los documentos públicos y las publicaciones de los proyectos de los programas marco HORIZONTE.

Los enlaces a los documentos y las publicaciones de los proyectos del Séptimo Programa Marco, así como los enlaces a algunos tipos de resultados específicos, como conjuntos de datos y «software», se obtienen dinámicamente de OpenAIRE .

Resultado final

An intelligent forecasting system could occupy a central role in the optimisation of complex systems like refineries and power systems. A forecasting of the different process states would allow a co-ordinated handling of these processes. As a result of this an evident reduction of the environmental pollution and the energy consumption could be realised. The advantages of neural networks in this working field of forecasting in comparison to conventional systems are: - The process behaviour does not have to be explicitly modelled. - It is able to consider non-linear process behaviour. - It has a superior ability to interpolate and to generalise. - It is more robust than conventional methods. The same problems and advantages can be found for AI-automation-systems in power systems. Forecasting methods have a central role in the operation and planning of electric power systems. It is an advantage of the co-operation that different methods (e.g. design of neural networks, preparation of data-sets or for realisation of forecasting systems) can be discussed in the network and experiences could be compared for different application areas. In this way not only do the results benefit from the collaboration, but also the introduction of such complex innovative AI-technologies and know-how should be faster and without a high-risk-level.

Buscando datos de OpenAIRE...

Se ha producido un error en la búsqueda de datos de OpenAIRE

No hay resultados disponibles

Mi folleto 0 0