Machine Learning Enabled Design Automation and Optimization for Electric Transportation Power Systems
This webinar is sponsored by the IEEE Power Electronics Society Design Methodologies Conference
Presenters: Yue Cao, Oregon State University and Jana Doppa, Washington State University
Date: Thursday, April 29, 2021, 1:30 pm ET
Abstract: This talk presents an automated design and optimization framework enabled by machine learning (ML) for electric transportation power systems. As these systems become increasingly complex and involve the co-design of multiple inter-dependent subsystems and components, a large amount of engineering time and effort is required to explore all possible designs due to large design spaces. Multi-physical domain models and simulations, essential to measure a given design’s performance, are typically computationally expensive to run – sometimes taking hours to days, depending on the system complexity. Providing an approach to drastically simplify this process – as in time and cost reduction – will allow faster and cheaper research and development throughout the transportation sector. Synergistic integration of advances in machine learning with physical domain knowledge paves one feasible pathway to practically realize this vision. Bayesian optimization (BO) is an effective machine learning framework to solve design automation problems with expensive experiments. This paper proposes a novel BO algorithm referred to as Max-value Entropy Search for Multi-objective Optimization with Constraints (MESMOC) to solve multi-objective optimization (MOO) problems with black-box constraints that can only be evaluated through design simulations. The key idea is to build statistical models of both design objectives and constraints, and use them to intelligently select the sequence of designs for evaluation based on the principle of output space entropy search – maximize the information gain about the optimal Pareto front – to efficiently uncover (approximate) Pareto optimal designs. MESMOC is capable of drastically reducing the number of design simulations to discover a high-quality Pareto front. A heavy-duty vertical-takeoff-landing (VTOL) unmanned aerial vehicle (UAV) power system is selected to demonstrate the effectiveness of the ML-based MESMOC algorithm. In several experimental trials, the ML algorithm uncovered the entire optimal Pareto front while only exploring ~4% of the design space. The proposed ML algorithm, when compared to a popular genetic algorithm, showcases superior performance.
Dr. Yue Cao is an Assistant Professor in the Energy Systems Group at Oregon State University (OSU). Before joining OSU, he was a research scientist on the propulsions team at Amazon Prime Air in Seattle, WA. He has been a power electronics engineer intern with special projects group at Apple Inc., Halliburton Company, Flanders Electric, and Oak Ridge National Laboratory. His research interests include power electronics, motor drives, and energy storage with applications in transportation electrification and renewable energy integration.
Dr. Cao received M.S. and Ph.D. (2017) in Electrical Engineering from the University of Illinois at Urbana–Champaign (UIUC), and B.S. in electrical engineering and mathematics from the University of Tennessee, Knoxville. Dr. Cao is the Tutorials Chair of ECCE 2021. In 2020, he established a joint IEEE PES/PELS Chapter at OSU. He is currently an Associate Editor for IEEE Transactions on Transportation Electrification.
Dr. Jana Doppa is a George and Joan Berry Chair Associate Professor in the School of Electrical Engineering and Computer Science at Washington State University (WSU), Pullman. He earned his PhD with the Artificial Intelligence group at Oregon State University (2014); and his M.Tech from Indian Institute of Technology (IIT), Kanpur, India (2006). His general research interests are in the broad field of Artificial Intelligence (AI), where he focuses on machine learning, and data-driven science and engineering for application domains including electronic design automation, computer architecture, material science, and agriculture.
Dr. Doppa received the NSF CAREER Award (2019), a Google Faculty Research Award (2015), and the Outstanding Innovation in Technology Award from Oregon State University (2015). Dr. Doppa is an elected editorial board member of the Journal of Artificial Intelligence Research.
This webinar is jointly sponsored by the IEEE Transportation Electrification Community and the IEEE Power Electronics Society Technical Committee on Electrical Machines, Drives and Automation, and IEEE Power Electronics Society Technical Committee on Emerging Power Electronic Technologies
Abstract: In this lecture, a broad review of vehicles for farming operation will be given starting from tillage to crop harvesting. Vehicles that have significant use of power electronics will be covered such as Exact-Emerge Planter for seeding operation followed mention of Exact-Apply for crop care and management of plants (corns etc.) that are nutrient deficient. This will lead discussions towards how power electronics supports crop-care system to exactly apply prescription such as fertilizers, pesticides, fungicide, etc. Discussions of this lecture are targeted to create awareness among power electronics and engineering professionals that how your vocation could enable putting food on plate of 9 billion people by 2050 and provide them shelter and transportation infrastructure. This lecture would also cover how electrification is becoming enabling technology in off-road heavy-duty vehicle space. Discussions of this lecture will cover that how wide bandgap (WBG) power electronics could enable many functions, forms, and features in heavy-duty off-road vehicles such as equipment required for agriculture, construction, and mining operations. The Silicon Carbide (SiC) and Gallium Nitride (GaN) based power electronics indeed could offer system level solution that are performance-superior and cost-competitive compared to state-of-art silicon semiconductor-based power electronics. These system approaches will be mentioned in midst of this presentation.
Dr. Brij N. Singh is a Technical Fellow - Power Electronics Engineering in John Deere USA. He has earned BE from MMM Technical University, Gorakhpur, ME from IIT Roorkee, and Ph.D. from IIIT Delhi, all in Electrical Engineering.
Jointly Sponsored by the IEEE Transportation Electrification Community and the IEEE Power Electronics Society Technical Committee on Aerospace Power
Presenter: Cong Li, GE Global Research Center, Niskayuna, NY
Date: Wednesday, July 21, 2021, 9:00 am New York Time
Abstract: This webinar provides engineers with techniques to develop and construct electromagnetically compatible Wide Bandgap (WBG) power electronic converters used in aviation applications. Real-world examples and issues are demonstrated with high-frequency construction methods necessary to meet the Electromagnetic Compatibility (EMC) requirements. The webinar provides fundamental EMC theory for SiC power electronics, a new “SOLVE” EMC design flow for WBG power converters, and practical design, construction, and measurement techniques.
Dr. Cong Li (S’09-M’15-SM’19) received the Ph.D. degree in electrical engineering specializing in power electronics from The Ohio State University, Columbus, OH, USA, in 2014.
Please note you will need to be a member to access the past webinars on the TEC website.