Ziel
Although reactive polymer composite moulding techniques have significant advantages for the production of high quality composite parts their production cycle is governed by the lengthy polymerisation phase making their adoption by the manufacturers tricky, requiring significant amount of experimentation and over-engineered solutions while issues like resin aging, mixing ratio quality, batch-to-batch and other deviations may turn out the production unreliable. So in order to turn composite material production to an agile industrial process it is important to have: -automatic process control tools ensuring the optimal production of the materials -self-learning process tools that can handle efficiently production and material deviations without requiring extensive (and unrealistic) lab trials and scientific models -Knowledge-based databases and model-based simulations that can provide the essential information to cope automatically with different matrices, batch-to-batch variations and small scale productions -Robust and reliable process monitoring that can sense the state of the moulded materials, providing accurate real-time information on the status of the process. So in iReMo for the first time the following technologies will be applied to the liquid moulding and pultrusion of composite materials: -Robust neural network modeling through bootstrap aggregated neural networks which will be used in optimisation and control. -Reliable optimisation control by incorporating model prediction confidence bounds in the optimisation objective function -Iterative learning control based on neural network models -Self-learning material models -Self-calibrating process monitoring tools combined with all the supporting innovations for fast and wireless sensors and fast and intelligent databases. These tools will be applied for the control of three real industrial applications with a broad impact so the effectiveness of the proposed process control will be demonstrated.
Wissenschaftliches Gebiet (EuroSciVoc)
CORDIS klassifiziert Projekte mit EuroSciVoc, einer mehrsprachigen Taxonomie der Wissenschaftsbereiche, durch einen halbautomatischen Prozess, der auf Verfahren der Verarbeitung natürlicher Sprache beruht. Siehe: https://op.europa.eu/en/web/eu-vocabularies/euroscivoc.
CORDIS klassifiziert Projekte mit EuroSciVoc, einer mehrsprachigen Taxonomie der Wissenschaftsbereiche, durch einen halbautomatischen Prozess, der auf Verfahren der Verarbeitung natürlicher Sprache beruht. Siehe: https://op.europa.eu/en/web/eu-vocabularies/euroscivoc.
- NaturwissenschaftenInformatik und InformationswissenschaftenDatenbank
- Technik und TechnologieWerkstofftechnikVerbundwerkstoffe
- NaturwissenschaftenChemiewissenschaftenPolymerwissenschaft
- Technik und TechnologieElektrotechnik, Elektronik, InformationstechnikElektrotechnikSensoren
- NaturwissenschaftenInformatik und Informationswissenschaftenkünstliche IntelligenzComputational Intelligence
Sie müssen sich anmelden oder registrieren, um diese Funktion zu nutzen
Programm/Programme
Thema/Themen
Aufforderung zur Vorschlagseinreichung
FP7-NMP-2008-SMALL-2
Andere Projekte für diesen Aufruf anzeigen
Finanzierungsplan
CP-FP - Small or medium-scale focused research projectKoordinator
53810 Change
Frankreich