02
We warmly welcome our new Post Doc Gaëtan Frusque!
Gaëtan Frusque received the B.Eng. and M.Eng. degrees in signal processing from Grenoble Institut National Polytechnique (PHELMA). Before joining the Chair of Intelligent Maintenance Systems in February, he obtained a Ph.D. degree with ENS Lyon. His PhD thesis focused on dynamical graph processing applied to neurophysiological signals. His research interest is in the application of multidimensional signal processing, sparse optimisation and deep learning on real data.
Check out our latest paper on unsupervised transfer learning for anomaly detection
The paper describes a methodology to detect anomalies in operating conditions only experienced by other units in a fleet. It uses adversarial deep learning to ensure the alignment of the different units’ distributions and introduce a new loss, inspired by a dimensionality reduction tool, to enforce the conservation of the inherent variability of each dataset. State-of-the-art once-class approach is used to detect the anomalies.
New paper on a bi-level multi-agent system for optimal scheduling of predictive maintenance interventions
Our paper proposing a bi-level multi-agent system for optimal scheduling of predictive maintenance interventions has just been accepted for publication in the journal Reliability Engineering & System Safety and is available under open access.