서브메뉴
검색
Optical-Based Microsecond Latency MHD Mode Tracking Through Deep Learning
Optical-Based Microsecond Latency MHD Mode Tracking Through Deep Learning
상세정보
- 자료유형
- 학위논문 서양
- 최종처리일시
- 20250211152008
- ISBN
- 9798383194478
- DDC
- 530
- 저자명
- Wei, Yumou.
- 서명/저자
- Optical-Based Microsecond Latency MHD Mode Tracking Through Deep Learning
- 발행사항
- [Sl] : Columbia University, 2024
- 발행사항
- Ann Arbor : ProQuest Dissertations & Theses, 2024
- 형태사항
- 152 p
- 주기사항
- Source: Dissertations Abstracts International, Volume: 86-01, Section: B.
- 주기사항
- Advisor: Mauel, Michael E.;Navratil, Gerald A.
- 학위논문주기
- Thesis (Ph.D.)--Columbia University, 2024.
- 초록/해제
- 요약Active feedback control in magnetic confinement fusion devices is desirable to mitigate plasma instabilities and enable robust operation. Among various diagnostics, optical high-speed cameras provide a powerful, non-invasive diagnostic and can be suitable for these applications.This thesis reports the first application of high-speed imaging videography and deep learning as real-time diagnostics of rotating MHD modes in a tokamak device. The developed system uses a convolutional neural network (CNN) to predict the amplitudes of the \uD835\uDC5B=1 sine and cosine mode components using solely optical measurements acquired from one or more cameras. Using the newly assembled high-speed camera diagnostics on the High Beta Tokamak - Extended Pulse (HBT-EP) device, an experimental dataset consisting of camera frame images and magnetic-based mode measurements was assembled and used to develop the mode-tracking CNN model. The optimized models outperformed other tested conventional algorithms given identical image inputs.A prototype controller based on a field-programmable gate array (FPGA) hardware was developed to perform real-time mode tracking using the high-speed camera diagnostic with the mode-tracking CNN model. In this system, a trained model was directly implemented in the firmware of an FPGA device onboard the frame grabber hardware of the camera's data readout system. Adjusting the model size and its implementation-related parameters allowed achieving an optimal trade-off between a model's prediction accuracy, its FPGA resource utilization and inference speed. Through fine-tuning these parameters, the final implementation satisfied all of the design constraints, achieving a total trigger-to-output latency of 17.6 \uD835\uDF07s and a throughput of up to 120 kfps. These results are on-par with the existing GPU-based control system using magnetic sensor diagnostic, indicating that the camera-based controller will be capable to perform active feedback control of MHD modes on HBT-EP.
- 일반주제명
- Plasma physics
- 일반주제명
- Computer engineering
- 일반주제명
- Physics
- 일반주제명
- Information technology
- 키워드
- CNN model
- 키워드
- Magnetic sensor
- 기타저자
- Columbia University Applied Physics
- 기본자료저록
- Dissertations Abstracts International. 86-01B.
- 전자적 위치 및 접속
- 로그인 후 원문을 볼 수 있습니다.
MARC
008250123s2024 us c eng d■001000017162404
■00520250211152008
■006m o d
■007cr#unu||||||||
■020 ▼a9798383194478
■035 ▼a(MiAaPQ)AAI31330889
■040 ▼aMiAaPQ▼cMiAaPQ
■0820 ▼a530
■1001 ▼aWei, Yumou.
■24510▼aOptical-Based Microsecond Latency MHD Mode Tracking Through Deep Learning
■260 ▼a[Sl]▼bColumbia University▼c2024
■260 1▼aAnn Arbor▼bProQuest Dissertations & Theses▼c2024
■300 ▼a152 p
■500 ▼aSource: Dissertations Abstracts International, Volume: 86-01, Section: B.
■500 ▼aAdvisor: Mauel, Michael E.;Navratil, Gerald A.
■5021 ▼aThesis (Ph.D.)--Columbia University, 2024.
■520 ▼aActive feedback control in magnetic confinement fusion devices is desirable to mitigate plasma instabilities and enable robust operation. Among various diagnostics, optical high-speed cameras provide a powerful, non-invasive diagnostic and can be suitable for these applications.This thesis reports the first application of high-speed imaging videography and deep learning as real-time diagnostics of rotating MHD modes in a tokamak device. The developed system uses a convolutional neural network (CNN) to predict the amplitudes of the \uD835\uDC5B=1 sine and cosine mode components using solely optical measurements acquired from one or more cameras. Using the newly assembled high-speed camera diagnostics on the High Beta Tokamak - Extended Pulse (HBT-EP) device, an experimental dataset consisting of camera frame images and magnetic-based mode measurements was assembled and used to develop the mode-tracking CNN model. The optimized models outperformed other tested conventional algorithms given identical image inputs.A prototype controller based on a field-programmable gate array (FPGA) hardware was developed to perform real-time mode tracking using the high-speed camera diagnostic with the mode-tracking CNN model. In this system, a trained model was directly implemented in the firmware of an FPGA device onboard the frame grabber hardware of the camera's data readout system. Adjusting the model size and its implementation-related parameters allowed achieving an optimal trade-off between a model's prediction accuracy, its FPGA resource utilization and inference speed. Through fine-tuning these parameters, the final implementation satisfied all of the design constraints, achieving a total trigger-to-output latency of 17.6 \uD835\uDF07s and a throughput of up to 120 kfps. These results are on-par with the existing GPU-based control system using magnetic sensor diagnostic, indicating that the camera-based controller will be capable to perform active feedback control of MHD modes on HBT-EP.
■590 ▼aSchool code: 0054.
■650 4▼aPlasma physics
■650 4▼aComputer engineering
■650 4▼aPhysics
■650 4▼aInformation technology
■653 ▼aHigh-speed imaging
■653 ▼aConvolutional neural network
■653 ▼aCNN model
■653 ▼aMagnetic sensor
■653 ▼aCamera diagnostic
■690 ▼a0759
■690 ▼a0800
■690 ▼a0464
■690 ▼a0489
■690 ▼a0605
■71020▼aColumbia University▼bApplied Physics.
■7730 ▼tDissertations Abstracts International▼g86-01B.
■790 ▼a0054
■791 ▼aPh.D.
■792 ▼a2024
■793 ▼aEnglish
■85640▼uhttp://www.riss.kr/pdu/ddodLink.do?id=T17162404▼nKERIS▼z이 자료의 원문은 한국교육학술정보원에서 제공합니다.
