ML-ACCEPT: Machine-Learning-enhanced Automated Circuit Configuration and Evaluation of Power Converters

NSF I-Corps Team for Customer Discovery:

DOE ARPA-E R&D Project:

Compared to existing methods, the ML-ACCEPT software suite makes the design of power converters more cost- and time-efficient (e.g., 100X faster than human expert design with comparable performance) by

1) integrating recent breakthroughs in machine learning, power electronics, simulation software, and optimization to research, develop, and demonstrate a suite of machine-learning-enhanced hypothesis generation tools for power converter design; and

2) facilitating the integration of the proposed software tools into existing power-converter design work-flows.

The project is in part supported by the. U.S. Department of Energy - Advanced Research Projects Agency–Energy (ARPA-E), the U.S. National Science Foundation (NSF), Michigan Translation Research and Commercialization (MTRAC) for Advanced Transportation Innovation Hub, and the University of Michigan.

More information is available upon request.

Please email Dr. Wencong Su <wencong@umich.edu>.

Selected Publication:

F. Leno da Silva, R. Glatt, W. Su, V. Bui, F. Chang, M. Wang, Y. Murphey, C. Huang, L. Xue, R. Zeng, “AutoTG: Reinforcement Learning-based Symbolic Optimization for AI-assisted Power Converter Design,” IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems, 2023. (under review)
V. Bui, F. Chang, W. Su, M. Wang, Y. Murphey, F. Leno da Silva, C. Huang, L. Xue, and R. Glatt, "Deep Neural Network-Based Surrogate Model for Optimal Component Sizing of Power Converters using Deep Reinforcement Learning," IEEE Access, vol.10, pp.78702-78712, 2022. (Paper)
S. Wang, Y. Murphey, W. Su, M. Wang, V. Bui, F. Chang, C. Huang, L. Xue, F. Da Silva, and R. Glatt, "An Intelligent System for Automatic Selection of DC-DC Converter Topology with Optimal Design," the 26th Association for the Advancement of Artificial Intelligence (AAAI) - AI-based Design and Manufacturing Workshop, Feb. 22 - March 1, 2022. (Poster) (Paper)
R. Glatt, F. Da Silva, V. Bui, C. Huang, L. Xue, M. Wang, F. Chang, Y. Murphey, and W. Su, "Deep Symbolic Optimization for Electric Component Sizing in Fixed Topology Power Converters," the 26th Association for the Advancement of Artificial Intelligence (AAAI) - AI-based Design and Manufacturing Workshop, Feb. 22 - March 1, 2022. (Poster) (Paper)

Pending Patent:

"AUTOMATED CIRCUIT TOPOLOGY SELECTION AND CONFIGURATION"