Smart grid, Electrical machines, Renewable energy sources, Electric transportation, Deep learning
The ability to handle huge amount of data coming from the sensing activity in smart grid contexts is crucial for reliable user services, requiring proper Digital Signal Processing and Computational Intelligence algorithms. These algorithms efficiently extract necessary information from various abstraction levels of acquired energy data, allowing intelligent decision-making and action implementation onto the grid. Ongoing research topics in this area include:
In the Electrical Machines and Drives field, machine learning and deep learning techniques enhance performance, efficiency, and reliability by detecting faults and malfunctions. Topics under investigation include automated temperature monitoring to prevent malfunctions, fault detection, prediction, and diagnosis of electrical machines, and design optimization using artificial intelligence techniques.
iLabs-SmartEnvironments laboratory, A3lab laboratory
Universities and research institutions: University of Strathclyde, Glasgow (UK), University of Rhode Island, Kingston (USA), University of Lincoln, Lincoln, (UK), Clemson University, Clemson, (USA), Honda Research Institute, Offenbach/Main (Germany), Griffith University, Queensland (Australia), University of Salerno (Italy) for the National PhD in “Photovoltaics” companies: Loccioni, Angeli di Rosora (Italy), MAC Srl, Recanati (Italy), Dowsee Srl, Fabriano (Italy), Honda Research Institute, Offenbach/Main (Germany).