My research interests are in the field of diagnosis, aiming to propose theoretical and numerical methods for the analysis and design of efficient monitoring and diagnosis tools, fulfilling the specific requirements of dynamic systems in varied environments. To address this diversity, my research draws on formalisms borrowed to the fields of Automatic Control and Artificial Intelligence. Applications include anomaly detection, root cause analysis, fault signature generation, measure and test selection. 

My currents interests are organized along three lines:

Model-based diagnosis

  • Set-membership estimation and filtering
  • Distributed diagnosis via structural analysis
  • Hybrid system reachability analysis and estimation
  • Diagnosability analysis

Data-driven diagnosis

  • Dynamic clustering
  • Temporal pattern learning

Hybrid anomaly detection and diagnosis

  • Tuning-free and frugal anomaly detection methods
  • Intertwined data and knowledge for anomaly detection and diagnosis