Every joule of energy matters. The efficient operation of electromechanical systems is crucial for a successful clean energy transition. Automation and closed-loop feedback control, although necessary, can waste energy and induce wear as deteriorated systems struggle to maintain system setpoints. In this talk I will present two research avenues that enable informed decisions for system maintenance and flexible energy management. First, I will present electrical monitoring of electromechanical systems for the efficient operation and maintenance of individual machines. These techniques are rooted in new machine learning approaches for problems with concept drift and a limited training dataset. Then I will present Pareto-optimized thermal control of multi-zone buildings for reducing energy use while maintaining thermal comfort. Finally, I will discuss new opportunities for using electrical monitoring and control for demand-side management to establish a more sustainable grid. Examples will be illustrated with field data from marine microgrids and university buildings.

Dr. Daisy Green is currently a Postdoctoral Associate with the Department of Architecture at the Massachusetts Institute of Technology (MIT) in the Building Technology Group. She received the M.S. and Ph.D. degrees in electrical engineering and computer science from MIT in 2018 and 2022, respectively, as part of the Electromechanical Systems Group. She received the B.S. degree in electrical engineering from the University of Hawai‘i at Mānoa in 2015. Her research interests include signal processing, estimation, machine learning and control for condition monitoring and energy management.