Post-Doctoral position GRINCOMP

Descrizione

Post-Doctoral position GRINCOMP Sintesi in italiano (traduzione automatica): La posizione di Ricercatore post-dottorato è parte di un progetto multidisciplinare che coinvolge due unità di ricerca: il laboratorio LISTIC e il laboratorio SYMME, entrambi situati a Bourget-du-Lac. Il progetto GRINCOMP si concentra sullo sviluppo di metodi avanzati di intelligenza artificiale basati su Graph Neural Networks (GNNs) per il monitoraggio e la manutenzione predittiva di strutture composite bio-based. Le mansioni principali includono la progettazione e lo sviluppo di modelli di machine learning per analizzare dati multi-sensore e multi-fisica. È richiesta una laurea in Informatica o un campo correlato, con competenze in intelligenza artificiale, machine learning e materiali compositi. Il candidato ideale avrà esperienza nella modellazione di dati complessi e nell'analisi di dataset sperimentali. This position is part of a multidisciplinary project involving two research units: the ‘ Systèmes, Traitement de l’Information et de la Connaissance’ Laboratory (LISTIC), which is leading the project, and the 'SYstèmes et Matériaux pour la Mecatronique’ laboratory (SYMME), both located in Bourget-du-Lac. The GRINCOMP project (Graph-based Intelligence for Natural-fiber Composites) aims to develop advanced AI methods based on Graph Neural Networks (GNNs) for the monitoring and predictive maintenance of bio-based composite structures. These materials, combining natural fibers and thermoplastic matrices, exhibit complex behaviors under coupled environmental and mechanical stresses. The research will focus on modeling multi-sensor and multi-physics data (temperature, humidity, mechanical strain, electrical signals) using graph-based representations. The developed models will support tasks such as state estimation, anomaly detection, and remaining useful life prediction. The project contributes to the development of sustainable, intelligent materials for future energy systems. Research Field Computer Science – Artificial Intelligence Machine Learning / Graph Neural Networks Signal Processing / Data Science Composite Materials, bio-based composite The successful candidate will design and develop advanced machine learning models to analyze multi-sensor, multi-physics data collected from instrumented composite materials. Main objectives include: Designing graph-based representations of sensor networks embedded in materials Developing and training Graph Neural Networks for: Internal state estimation (temperature, humidity) Anomaly and damage detection Remaining Useful Life (RUL) prediction Working with real experimental datasets from instrumented composite structures Annuncio in inglese. Fonte: Euraxess (Commissione europea).