Multi-Physical Modeling
Optimal design & robust control through multi-physical modeling.
Our work involves the development of state-of-art modeling and simulation tools for complex, heterogeneous systems. We apply these models for the optimal design and robust control of a variety of systems including HVAC systems, zero-energy buildings, automobiles, and robotic systems.
Quick Links
-
Researchers
Christopher R.
Laughman
Bingnan
Wang
Scott A.
Bortoff
Hongtao
Qiao
Ankush
Chakrabarty
Chungwei
Lin
Yebin
Wang
Gordon
Wichern
Vedang M.
Deshpande
Toshiaki
Koike-Akino
Dehong
Liu
Ye
Wang
Stefano
Di Cairano
Abraham
Goldsmith
Koon Hoo
Teo
Hassan
Mansour
Philip V.
Orlik
Kieran
Parsons
Arvind
Raghunathan
Hongbo
Sun
Luigi
Vanfretti
Abraham P.
Vinod
-
Awards
-
AWARD Best Paper Award at SDEMPED 2023 Date: August 30, 2023
Awarded to: Bingnan Wang, Hiroshi Inoue, and Makoto Kanemaru
MERL Contact: Bingnan Wang
Research Areas: Applied Physics, Data Analytics, Multi-Physical ModelingBrief- MERL and Mitsubishi Electric's paper titled “Motor Eccentricity Fault Detection: Physics-Based and Data-Driven Approaches” was awarded one of three best paper awards at the 14th IEEE International Symposium on Diagnostics for Electric Machines, Power Electronics and Drives (SDEMPED 2023). MERL Senior Principal Research Scientist Bingnan Wang presented the paper and received the award at the symposium. Co-authors of the paper include Mitsubishi Electric researchers Hiroshi Inoue and Makoto Kanemaru.
SDEMPED was established as the only international symposium entirely devoted to the diagnostics of electrical machines, power electronics and drives. It is now a regular biennial event. The 14th version, SDEMPED 2023 was held in Chania, Greece from August 28th to 31st, 2023.
- MERL and Mitsubishi Electric's paper titled “Motor Eccentricity Fault Detection: Physics-Based and Data-Driven Approaches” was awarded one of three best paper awards at the 14th IEEE International Symposium on Diagnostics for Electric Machines, Power Electronics and Drives (SDEMPED 2023). MERL Senior Principal Research Scientist Bingnan Wang presented the paper and received the award at the symposium. Co-authors of the paper include Mitsubishi Electric researchers Hiroshi Inoue and Makoto Kanemaru.
See All Awards for MERL -
-
News & Events
-
NEWS Ankush Chakrabarty served as Co-Chair of ACM BALANCES 2023 Date: November 14, 2023
Where: Istanbul, Turkey
MERL Contact: Ankush Chakrabarty
Research Areas: Control, Data Analytics, Machine Learning, Multi-Physical Modeling, OptimizationBrief- Ankush Chakrabarty, Principal Research Scientist in the Multiphysical Systems team at MERL, served as Co-Chair at the 3rd ACM International Workshop on Big Data and Machine Learning for Smart Buildings and Cities (BALANCES'23). The workshop places spotlights on two different IEA EBC Annexes: the Annex 81 - Data-Driven Smart Buildings and Annex 82 - Energy Flexible Buildings Towards Resilient Low Carbon Energy Systems.
-
TALK [MERL Seminar Series 2023] Prof. Faruque Hasan presents talk titled A Process Systems Engineering Perspective on Carbon Capture: Key Challenges and Opportunities Date & Time: Tuesday, September 19, 2023; 1:00 PM
Speaker: Faruque Hasan, Texas A&M University
MERL Host: Scott A. Bortoff
Research Areas: Applied Physics, Machine Learning, Multi-Physical Modeling, OptimizationAbstractCarbon capture, utilization, and storage (CCUS) is a promising pathway to decarbonize fossil-based power and industrial sectors and is a bridging technology for a sustainable transition to a net-zero emission energy future. This talk aims to provide an overview of design and optimization of CCUS systems. I will also attempt to give a brief perspective on emerging interests in process systems engineering research (e.g., systems integration, multiscale modeling, strategic planning, and optimization under uncertainty). The purpose is not to cover all aspects of PSE research for CCUS but rather to foster discussion by presenting some plausible future directions and ideas.
See All News & Events for Multi-Physical Modeling -
-
Internships
-
MS2108: Knowledge Transfer for Deep System Identification
MERL is seeking a highly motivated and qualified intern to collaborate with the Multiphysical Systems (MS) team in research on knowledge transfer methods for deep learning, e.g. meta/transfer learning to be used for system identification using data from real building energy systems. The ideal candidate is expected to be working towards a Ph.D. in applying deep learning to system identification problems, with special emphasis in one or more of: generative modeling, probabilistic deep learning, and learning for estimation/control. Fluency in PyTorch is necessary. Previous peer-reviewed publications in related research topics and/or experience with state-of-the-art generative models for time-series is a plus. Publication of results obtained during the internship is expected. The minimum duration of the internship is 12 weeks; start time is flexible with slight preference towards late Spring/early Summer 2024.
-
EA2099: Machine Learning for Electric Motor Design
MERL is seeking a motivated and qualified intern to conduct research on machine learning based electric motor design and optimization. Ideal candidates should be Ph.D. students with a solid background and publication record in electric machine design, optimization, and machine learning. Hands-on experience with the implementation of optimization algorithms, machine learning and deep learning methods is required. Strong programming skills using Python/PyTorch are expected. Knowledge and experience with electric machine principle, design and finite-element analysis are highly desirable. Start date for this internship is flexible and the duration is 3-6 months.
-
MS2095: Data-driven Modeling and Control of Thermo-fluid Systems
MERL is seeking a highly motivated and qualified individual to conduct research in dynamic modeling and simulation of vapor compression systems in the summer of 2024. Knowledge of data-driven modeling techniques is required. Experience with sampling-based control methods is preferred. Experience in working with thermo-fluid systems is a plus. The intern is expected to collaborate with MERL researchers to build models, develop algorithms, and prepare manuscripts for scientific publications. Senior Ph.D. students in applied mathematics, chemical/mechanical engineering and other related areas are encouraged to apply. The expected duration of the internship is 3 months, and the start date is flexible.
See All Internships for Multi-Physical Modeling -
-
Recent Publications
- "Electric Machine Inverse Design with Variational Auto-Encoder (VAE)", IEEE Energy Conversion Congress and Exposition (ECCE), October 2023.BibTeX TR2023-134 PDF
- @inproceedings{Xu2023nov,
- author = {Xu, Yihao and Wang, Bingnan and Sakamoto, Yusuke and Yamamoto, Tatsuya and Nishimura, Yuki and Koike-Akino, Toshiaki and Wang, Ye},
- title = {Electric Machine Inverse Design with Variational Auto-Encoder (VAE)},
- booktitle = {IEEE Energy Conversion Congress and Exposition (ECCE)},
- year = 2023,
- month = oct,
- url = {https://www.merl.com/publications/TR2023-134}
- }
, - "Reliability-based Sizing of Electric Propulsion System for Turboelectric Aircraft", IEEE Industrial Electronics Society (IECON), October 2023.BibTeX TR2023-129 PDF
- @inproceedings{Wang2023oct,
- author = {Wang, Yebin and Lin, Chungwei and Fang, Huazhen and Takegami, Tomoki},
- title = {Reliability-based Sizing of Electric Propulsion System for Turboelectric Aircraft},
- booktitle = {IEEE Industrial Electronics Society (IECON)},
- year = 2023,
- month = oct,
- url = {https://www.merl.com/publications/TR2023-129}
- }
, - "Theoretical analysis of cycling losses in air source heat pump systems", International Congress of Refrigeration (ICR), September 2023.BibTeX TR2023-127 PDF
- @inproceedings{Qiao2023sep,
- author = {Qiao, Hongtao and Laughman, Christopher R.},
- title = {Theoretical analysis of cycling losses in air source heat pump systems},
- booktitle = {International Congress of Refrigeration (ICR)},
- year = 2023,
- month = sep,
- url = {https://www.merl.com/publications/TR2023-127}
- }
, - "A Virtual Testbed for Robust and Reproducible Calibration of Building Energy Simulation Models", 18th IBPSA International Conference and Exhibition Building Simulation, September 2023.BibTeX TR2023-114 PDF
- @inproceedings{Zhan2023sep,
- author = {Zhan, Sicheng and Chakrabarty, Ankush and Laughman, Christopher R. and Chong, Adrian},
- title = {A Virtual Testbed for Robust and Reproducible Calibration of Building Energy Simulation Models},
- booktitle = {18th IBPSA International Conference and Exhibition Building Simulation},
- year = 2023,
- month = sep,
- url = {https://www.merl.com/publications/TR2023-114}
- }
, - "Motor Eccentricity Fault Detection: Physics-Based and Data-Driven Approaches", IEEE International Symposium on Diagnostics for Electric Machines, Power Electronics and Drives (SDEMPED), August 2023.BibTeX TR2023-107 PDF
- @inproceedings{Wang2023aug,
- author = {Wang, Bingnan and Inoue, Hiroshi and Kanemaru, Makoto},
- title = {Motor Eccentricity Fault Detection: Physics-Based and Data-Driven Approaches},
- booktitle = {IEEE International Symposium on Diagnostics for Electric Machines, Power Electronics and Drives (SDEMPED)},
- year = 2023,
- month = aug,
- url = {https://www.merl.com/publications/TR2023-107}
- }
, - "Digital Twins for Vapor Compression Cycles: Challenges & Opportunities", International Congress of Refrigeration (ICR), August 2023.BibTeX TR2023-103 PDF
- @inproceedings{Laughman2023aug,
- author = {Laughman, Christopher R. and Deshpande, Vedang M. and Qiao, Hongtao and Bortoff, Scott A. and Chakrabarty, Ankush},
- title = {Digital Twins for Vapor Compression Cycles: Challenges & Opportunities},
- booktitle = {International Congress of Refrigeration (ICR)},
- year = 2023,
- month = aug,
- url = {https://www.merl.com/publications/TR2023-103}
- }
, - "Impedance Control of a Delta Robot", World Congress of the International Federation of Automatic Control (IFAC), July 2023.BibTeX TR2023-090 PDF
- @inproceedings{Bortoff2023jul,
- author = {Bortoff, Scott A. and Sanders, Haley and Girindhar, Deepika},
- title = {Impedance Control of a Delta Robot},
- booktitle = {World Congress of the International Federation of Automatic Control (IFAC)},
- year = 2023,
- month = jul,
- url = {https://www.merl.com/publications/TR2023-090}
- }
, - "Moving Horizon Estimation for Digital Twins using Deep Autoencoders", World Congress of the International Federation of Automatic Control (IFAC), Ishii, H. and Ebihara, Y. and Imura, J. and Yamakita, M., Eds., DOI: 10.1016/j.ifacol.2023.10.207, July 2023, pp. 5500-5505.BibTeX TR2023-088 PDF
- @inproceedings{Chakrabarty2023jul2,
- author = {Chakrabarty, Ankush and Vinod, Abraham P. and Mansour, Hassan and Bortoff, Scott A. and Laughman, Christopher R.},
- title = {Moving Horizon Estimation for Digital Twins using Deep Autoencoders},
- booktitle = {World Congress of the International Federation of Automatic Control (IFAC)},
- year = 2023,
- editor = {Ishii, H. and Ebihara, Y. and Imura, J. and Yamakita, M.},
- pages = {5500--5505},
- month = jul,
- publisher = {Elseiver},
- doi = {10.1016/j.ifacol.2023.10.207},
- url = {https://www.merl.com/publications/TR2023-088}
- }
,
- "Electric Machine Inverse Design with Variational Auto-Encoder (VAE)", IEEE Energy Conversion Congress and Exposition (ECCE), October 2023.
-
Videos
[MERL Seminar Series Fall 2023] A Process Systems Engineering Perspective on Carbon Capture: Key Challenges and Opportunities [MERL Seminar Series Spring 2023] Investigating Multi-Agent Reinforcement Learning for Grid-Interactive Smart Communities using CityLearn [MERL Seminar Series Spring 2022] Exact Structural Analysis of Multimode Modelica Models [MERL Seminar Series 2021] Harnessing machine learning to build better Earth system models for climate projection [MERL Seminar Series 2021] Use the [Magnetic] Force for Good: Sustainability Through Magnetic Levitation Co-simulation of HVAC Equipment and Airflow Modelica-Based Modeling and Control of a Delta Robot