Bingnan Wang
- Phone: 617-621-7558
- Email:
-
Position:
Research / Technical Staff
Senior Principal Research Scientist -
Education:
Ph.D., Iowa State University, 2009 -
Research Areas:
External Links:
Bingnan's Quick Links
-
Biography
Bingnan's doctoral work focused on the study of wave propagation in novel electromagnetic materials, including photonic crystals and meta-materials. His research interests include electromagnetics and photonics, and their applications to communications, imaging, and energy systems.
-
Recent News & Events
-
EVENT Prof. Yuejie Chi of Carnegie Mellon University to Deliver Keynote at MERL's Virtual Open House Date & Time: Wednesday, November 15, 2023; 3:00-3:40pm (EST)
Location: Virtual Event
Speaker: Prof. Yuejie Chi, Carnegie Mellon University
MERL Contact: Bingnan WangBrief- MERL is excited to announce the featured keynote speaker for our Virtual Open House 2023: Prof. Yuejie Chi from Carnegie Mellon University.
Our virtual open house this year will take place on November 15, 2023, 1:00pm - 5:30pm (EST). Prof. Chi’s talk is scheduled for 3:00-3:40pm (EST). For details and agenda of the event, please visit: https://merl.com/events/voh23
Join us to learn more about who we are, what we do, and discuss our internship, post-doc, and full-time employment opportunities. To register, go to: https://mailchi.mp/merl/voh23
Title: Sample Complexity of Q-learning: from Single-agent to Federated Learning
Abstract: Q-learning, which seeks to learn the optimal Q-function of a Markov decision process (MDP) in a model-free fashion, lies at the heart of reinforcement learning practices. However, theoretical understandings on its non-asymptotic sample complexity remain unsatisfactory, despite significant recent efforts. In this talk, we first show a tight sample complexity bound of Q-learning in the single-agent setting, together with a matching lower bound to establish its minimax sub-optimality. We then show how federated versions of Q-learning allow collaborative learning using data collected by multiple agents without central sharing, where an importance averaging scheme is introduced to unveil the blessing of heterogeneity.
- MERL is excited to announce the featured keynote speaker for our Virtual Open House 2023: Prof. Yuejie Chi from Carnegie Mellon University.
-
EVENT MERL's Virtual Open House 2023 Date & Time: Wednesday, November 15, 2023; 1:00 - 5:30 EST
Location: Virtual Event
MERL Contact: Bingnan WangBrief- Join us for MERL's Virtual Open House (VOH) 2023 on November 15th. Live sessions will be held from 1:00-5:30pm EST, including an overview of recent activities by our research groups, a featured guest speaker and live interaction with our research staff through the Gather platform. Registered attendees will be able to browse our virtual booths at their convenience and connect with our research staff to learn about engagement opportunities, including internship/post-doc openings as well as visiting faculty positions.
For agenda and details of the event: https://www.merl.com/events/voh23
To register for the VOH, go to:
https://mailchi.mp/merl/voh23
- Join us for MERL's Virtual Open House (VOH) 2023 on November 15th. Live sessions will be held from 1:00-5:30pm EST, including an overview of recent activities by our research groups, a featured guest speaker and live interaction with our research staff through the Gather platform. Registered attendees will be able to browse our virtual booths at their convenience and connect with our research staff to learn about engagement opportunities, including internship/post-doc openings as well as visiting faculty positions.
See All News & Events for Bingnan -
-
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.
-
-
Internships with Bingnan
-
EA0072: Internship - Electric Machine Topology Optimization
MERL is seeking a motivated and qualified intern to conduct research on shape and topology optimization of electrical machines. The ideal candidate should have a solid background and demonstrated research experience in mathematical optimization methods, including topology optimization, robust optimization, and sensitivity analysis, as well as machine learning methods. Hands-on coding experience with the implementation of topology optimization algorithms and finite-element simulation are desirable. Knowledge and experience with electric machine principle, design and finite-element analysis is a strong plus. Senior Ph.D. students in related expertise are encouraged to apply. Start date for this internship is flexible and the duration is around 3 months.
-
EA0073: Internship - Fault Detection for Electric Machines
MERL is seeking a motivated and qualified individual to conduct research on electric machine fault analysis and detection methods. Ideal candidates should be Ph.D. students with a solid background and publication record in one more research area on electric machines: electric and magnetic modeling, machine design and prototyping, harmonic analysis, fault detection, and predictive maintenance. Knowledge on data analysis and machine learning algorithms, and strong programming skills using Python/PyTorch are expected. Research experience on modeling and analysis of electric machines and fault diagnosis is desired. Senior Ph.D. students in related expertise, such as electrical engineering, mechanical engineering, and applied physics are encouraged to apply. Start date for this internship is flexible and the duration is 3 months.
-
EA0076: Internship - 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 about 3 months.
-
EA0120: Internship - Machine Learning for 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 about 3 months.
-
-
MERL Publications
- , "Induction Motor Fault Classification with Topological Data Analysis", IEEE Energy Conversion Congress and Exposition (ECCE), October 2024.BibTeX TR2024-145 PDF
- @inproceedings{Wang2024oct,
- author = {Wang, Bingnan}},
- title = {Induction Motor Fault Classification with Topological Data Analysis},
- booktitle = {IEEE Energy Conversion Congress and Exposition (ECCE)},
- year = 2024,
- month = oct,
- url = {https://www.merl.com/publications/TR2024-145}
- }
- , "Supervised Contrastive Learning for Electric Motor Bearing Fault Detection", International Conference on Electrical Machines (ICEM), September 2024.BibTeX TR2024-120 PDF
- @inproceedings{Zhang2024sep,
- author = {Zhang, Hengrui and Wang, Bingnan}},
- title = {Supervised Contrastive Learning for Electric Motor Bearing Fault Detection},
- booktitle = {International Conference on Electrical Machines (ICEM)},
- year = 2024,
- month = sep,
- url = {https://www.merl.com/publications/TR2024-120}
- }
- , "Control Co-Design for Electric Vehicles with Driving Cycle Synthesis Encoding Road Traffic and Driver Characteristics", IEEE Conference on Control Technology and Applications (CCTA) 2024, DOI: 10.1109/CCTA60707.2024.10666575, August 2024.BibTeX TR2024-114 PDF
- @inproceedings{Park2024aug,
- author = {Park, Seho and Wang, Yebin and Qiao, Hongtao and Sakamoto, Yusuke and Wang, Bingnan and Liu, Dehong}},
- title = {Control Co-Design for Electric Vehicles with Driving Cycle Synthesis Encoding Road Traffic and Driver Characteristics},
- booktitle = {IEEE Conference on Control Technology and Applications (CCTA) 2024},
- year = 2024,
- month = aug,
- doi = {10.1109/CCTA60707.2024.10666575},
- url = {https://www.merl.com/publications/TR2024-114}
- }
- , "Data-efficient Machine Learning Methods for Electric Motor Surrogate Models", Biennial IEEE Conference on Electromagnetic Field Computation (CEFC), June 2024.BibTeX TR2024-064 PDF
- @inproceedings{Wang2024jun2,
- author = {Wang, Bingnan and Sakamoto, Yusuke}},
- title = {Data-efficient Machine Learning Methods for Electric Motor Surrogate Models},
- booktitle = {Biennial IEEE Conference on Electromagnetic Field Computation (CEFC)},
- year = 2024,
- month = jun,
- url = {https://www.merl.com/publications/TR2024-064}
- }
- , "Permanent Magnet Motor Torque Waveform Prediction Using Learned Gap Flux", Biennial IEEE Conference on Electromagnetic Field Computation (CEFC), June 2024.BibTeX TR2024-065 PDF
- @inproceedings{Sakamoto2024jun,
- author = {Sakamoto, Yusuke and Wang, Bingnan and Yamamoto, Tatsuya and Nishimura, Yuki}},
- title = {Permanent Magnet Motor Torque Waveform Prediction Using Learned Gap Flux},
- booktitle = {Biennial IEEE Conference on Electromagnetic Field Computation (CEFC)},
- year = 2024,
- month = jun,
- url = {https://www.merl.com/publications/TR2024-065}
- }
- , "Induction Motor Fault Classification with Topological Data Analysis", IEEE Energy Conversion Congress and Exposition (ECCE), October 2024.
-
Videos
-
MERL Issued Patents
-
Title: "System and Method for Detecting a Fault of an Operation of a Synchronous Motor"
Inventors: Lin, Chungwei; Wang, Bingnan; Nabi, Saleh
Patent No.: 11,683,000
Issue Date: Jun 20, 2023 -
Title: "Motor Designs having Spline Structure Connecting Motor shaft and Stator Structure"
Inventors: Wang, Hongyu; Zhou, Lei; Wang, Bingnan
Patent No.: 11,539,251
Issue Date: Dec 27, 2022 -
Title: "Multi-Layer Axial and Radial flux Vernier Permanent Magnet Motor"
Inventors: Zhou, Lei; Wang, Bingnan; Lin, Chungwei; Liu, Dehong; Wang, Yebin; Teo, Koon Hoo
Patent No.: 11,502,564
Issue Date: Nov 15, 2022 -
Title: "Electric Machine with Combined Axial- and Radial-Flux"
Inventors: Zhou, Lei; Wang, Bingnan; Wang, Hongyu
Patent No.: 11,482,894
Issue Date: Oct 25, 2022 -
Title: "Method for Static Eccentricity Fault Detection of Induction Motors"
Inventors: Zhou, Lei; Wang, Bingnan; Lin, Chungwei
Patent No.: 11,411,521
Issue Date: Aug 9, 2022 -
Title: "Modeling Interior Permanent Magnet Synchronous Machines Considering Permeability of Rotor"
Inventors: Wang, Bingnan; Shin, Kyung-Hun
Patent No.: 11,366,944
Issue Date: Jun 21, 2022 -
Title: "System and Method for Estimating Temperature and Heat Loss in Electric Motors"
Inventors: Wang, Bingnan; Wang, Yebin; Ma, Tong; Lin, Chungwei; Komatsu, Taiga
Patent No.: 11,293,986
Issue Date: Apr 5, 2022 -
Title: "Method for Estimating Bearing Fault Severity for Induction Motors"
Inventors: Wang, Bingnan; Zhang, Shen; Kanemaru, Makoto; Lin, Chungwei; Liu, Dehong; Teo, Koon Hoo
Patent No.: 11,099,101
Issue Date: Aug 24, 2021 -
Title: "RAIL STATE MONITORING APPARATUS"
Inventors: Tsujita, Wataru; MAKINO, Kenzo; Wang, Bingnan; TAKAMI, Atsushi
Patent No.: 11001282
Issue Date: May 11, 2021 -
Title: "Optical Waveguide Interferometer"
Inventors: Kojima, Keisuke; Wang, Bingnan; Koike-Akino, Toshiaki; Nishikawa, Satoshi; Akiyama, Koichi; Yagyu, Eiji; Shinohara, Kosuke
Patent No.: 10,996,400
Issue Date: May 4, 2021 -
Title: "Systems and Methods for On-Orbit Fabrication of Structures by 3D Printing"
Inventors: Yerazunis, William S.; Weiss, Avishai; Wang, Bingnan
Patent No.: 10,906,290
Issue Date: Feb 2, 2021 -
Title: "Negative Electroluminescent Cooling Device"
Inventors: Lin, Chungwei; Wang, Bingnan; Teo, Koon Hoo
Patent No.: 10,840,163
Issue Date: Nov 17, 2020 -
Title: "Thermal Emitter for Energy Conversion Technical Field"
Inventors: Wang, Bingnan; Lin, Chungwei; Wang, Jianjian; Teo, Koon Hoo
Patent No.: 10,797,633
Issue Date: Oct 6, 2020 -
Title: "Methods and Systems for Terahertz-Based Positioning"
Inventors: Wang, Pu; Fu, Haoyu; Orlik, Philip V.; Koike-Akino, Toshiaki; Ma, Rui; Wang, Bingnan
Patent No.: 10,795,151
Issue Date: Oct 6, 2020 -
Title: "Near-Field Based Thermoradiative Device"
Inventors: Wang, Bingnan; Lin, Chungwei; Teo, Koon Hoo
Patent No.: 10,658,968
Issue Date: May 19, 2020 -
Title: "Thermophotovoltaic Energy Converter"
Inventors: Lin, Chungwei; Wang, Bingnan; Teo, Koon Hoo
Patent No.: 10,497,821
Issue Date: Dec 3, 2019 -
Title: "Polarization-Dependent Position Encoder"
Inventors: Wang, Bingnan; Tsujita, Wataru; Sadamoto, Kota; Sawa, Yoshitsugu
Patent No.: 10,451,447
Issue Date: Oct 22, 2019 -
Title: "Contactless Sensor"
Inventors: Wang, Bingnan; Teo, Koon Hoo; Orlik, Philip V.
Patent No.: 10,288,759
Issue Date: May 14, 2019 -
Title: "Digital Beamforming Transmitter Array System with Hardware Sharing and Reduction"
Inventors: Wang, Bingnan; Peng, Zhengyu; Kim, Kyeong-Jin; Wang, Pu; Ma, Rui; Teo, Koon Hoo
Patent No.: 10,270,510
Issue Date: Apr 23, 2019 -
Title: "Compact Photonic Devices"
Inventors: Kojima, Keisuke; Teng, Min; Koike-Akino, Toshiaki; Wang, Bingnan
Patent No.: 10,234,627
Issue Date: Mar 19, 2019 -
Title: "Beamforming Transmission with Analog Hardware Resource Sharing"
Inventors: Kim, Kyeong-Jin; Peng, Zhengyu; Wang, Bingnan; Teo, Koon Hoo
Patent No.: 10,218,550
Issue Date: Feb 26, 2019 -
Title: "Photonic Integrated Circuit"
Inventors: Kojima, Keisuke; Nishikawa, Satoshi; Koike-Akino, Toshiaki; Wang, Bingnan; Yagyu, Eiji
Patent No.: 10,120,132
Issue Date: Nov 6, 2018 -
Title: "Artificial Magnetic Structures for Wireless Power Transfer"
Inventors: Wang, Bingnan; Yerazunis, William S.; Teo, Koon Hoo
Patent No.: 9,842,685
Issue Date: Dec 12, 2017 -
Title: "System and Method for Manipulating Polarizations of Optical Signal"
Inventors: Kojima, Keisuke; Felicetti, Manuela; Koike-Akino, Toshiaki; Wang, Bingnan; Nishikawa, Satoshi; Yagyu, Eiji
Patent No.: 9,557,485
Issue Date: Jan 31, 2017 -
Title: "Wireless Energy Transfer with Negative Index Material"
Inventors: Teo, Koon Hoo; Huang, Da; Wang, Bingnan
Patent No.: 9,461,505
Issue Date: Oct 4, 2016 -
Title: "System and Method for Automatically Optimizing Wireless Power"
Inventors: Yerazunis, William S.; Wang, Bingnan; Teo, Koon Hoo; Duan, Chunjie; Barnwell, III, John C.; Burns, Dan J.
Patent No.: 9,281,875
Issue Date: Mar 8, 2016 -
Title: "Proximity Sensor Detecting Metallic and Non-Metallic Objects"
Inventors: Wang, Bingnan; Long, Jiang; Teo, Koon Hoo
Patent No.: 9,274,075
Issue Date: Mar 1, 2016 -
Title: "Mode-Evolution Compound Converter"
Inventors: Kojima, Keisuke; Wang, Bingnan; Yuan, Wangqing; Yagyu, Eiji
Patent No.: 9,128,242
Issue Date: Sep 8, 2015 -
Title: "Multi-Mode Interference Device"
Inventors: Kojima, Keisuke; Ozbayat, Selman; Koike-Akino, Toshiaki; Wang, Bingnan; Nishikawa, Satoshi; Yagyu, Eiji
Patent No.: 9,116,298
Issue Date: Aug 25, 2015 -
Title: "Multi-Mode Interference Device"
Inventors: Koike-Akino, Toshiaki; Kojima, Keisuke; Wang, Bingnan; Nishikawa, Satoshi; Yagyu, Eiji
Patent No.: 9,097,852
Issue Date: Aug 4, 2015 -
Title: "Compound Optical Combiner"
Inventors: Kojima, Keisuke; Wang, Bingnan; Koike-Akino, Toshiaki; Nishikawa, Satoshi; Yagyu, Eiji
Patent No.: 9,052,461
Issue Date: Jun 9, 2015 -
Title: "Multi-Mode Interference Manipulator"
Inventors: Kojima, Keisuke; Wang, Bingnan; Koike-Akino, Toshiaki; Yuan, Wangqing; Nishikawa, Satoshi
Patent No.: 8,942,517
Issue Date: Jan 27, 2015 -
Title: "Wireless Energy Transfer Using Array of Resonant Objects"
Inventors: Wang, Bingnan; Teo, Koon Hoo
Patent No.: 8,890,366
Issue Date: Nov 18, 2014 -
Title: "System and Method for Analyzing Spiral Resonators"
Inventors: Wang, Bingnan; Teo, Koon Hoo; Ellstein, David
Patent No.: 8,831,917
Issue Date: Sep 9, 2014 -
Title: "Wireless Energy Transfer with Anisotropic Metamaterials"
Inventors: Wang, Bingnan; Huang, Da; Teo, Koon Hoo
Patent No.: 8,786,135
Issue Date: Jul 22, 2014
-
Title: "System and Method for Detecting a Fault of an Operation of a Synchronous Motor"