NEWTWEN
Francesco Pase is a skilled AI research engineer currently leading the ML R&D team at NEWTWEN, focusing on integrating data-driven models with physics and engineering to address real-world challenges. In addition to this role, Francesco is also a mentor at Lead The Future Mentorship, a nonprofit organization dedicated to supporting talent in Science and Engineering. Francesco has an extensive academic background, including a PhD in Information Engineering from Università degli Studi di Padova and experience as a visiting researcher at Imperial College London. Previous industry experience includes internships at Nokia Bell Labs and InstaDeep Ltd, where work involved federated learning and deep reinforcement learning, respectively. Recognized as one of the top interns at Nokia Bell Labs, Francesco has a strong foundation in machine learning, communications networks, and research methodologies.
This person is not in any teams
This person is not in any offices
NEWTWEN
1 followers
We develop software that generates real-time embedded digital twin solutions for model predictive control and diagnostics of electromechanical systems, enhancing performance, longevity, and reliability.In essence, our toolchain creates a precise digital replica of a physical device, such as an electric motor or generator, in order to accuratelymodel the electrodynamic and thermodynamic behavior of the system across a wide range of operating conditions.We then apply our proprietary mathematical approach to exponentially reduce the computational complexity of this model—so much so, in fact, that our digital twin can be integrated into the device itself to compute in real-time, “on-chip,” as part of an amazingly fast and accurate firmware solution.By accurately predicting temperatures and other critical system parameters thousands of times per second, our Digital Twin On-Chip solutions not only provide unprecedented insight for real-time control techniques to enhance system performance, but also pave the way for data-as-a-service capabilities such as predictive maintenance, monitoring of component aging, and anomaly detection.