서브메뉴
검색
Digitalization, Machine Learning Modeling and Control of an Experimental Electrochemical Reactor
Digitalization, Machine Learning Modeling and Control of an Experimental Electrochemical Reactor
상세정보
- 자료유형
- 학위논문 서양
- 최종처리일시
- 20250211152007
- ISBN
- 9798382819075
- DDC
- 660
- 저자명
- Citmaci, Berkay.
- 서명/저자
- Digitalization, Machine Learning Modeling and Control of an Experimental Electrochemical Reactor
- 발행사항
- [Sl] : University of California, Los Angeles, 2024
- 발행사항
- Ann Arbor : ProQuest Dissertations & Theses, 2024
- 형태사항
- 382 p
- 주기사항
- Source: Dissertations Abstracts International, Volume: 85-12, Section: B.
- 주기사항
- Advisor: Christofides, Panagiotis D.
- 학위논문주기
- Thesis (Ph.D.)--University of California, Los Angeles, 2024.
- 초록/해제
- 요약Greenhouse gas emissions from industry and transportation contribute significantly to climate change and its associated adverse impacts on the environment and economy. With the increase in electricity supply from clean energy sources, electrochemical reduction of carbon dioxide (CO2) has received increasing attention; however, a first-principles model for electrochemical CO2 reduction has not been fully developed because of the complexity of its reaction mechanism. At this point, data driven methods and machine learning (ML) can be used to model the process. At UCLA, we have constructed an experimental rotating cylinder electrode cell (RCE) setup to develop a deeper understanding of the process, and design scale-up strategies. The experimental equipment is digitalized on a computer interface using Smart Manufacturing principles, legacy sensors (such as Gas Chromatogram (GC)) are automated, and voluminous steady state and dynamic data sets are generated. Leveraging these datasets and data analytics, machine learning and hybrid models are built using machine learning methods, such as Support Vector Machines (SVR), and artificial neural networks (ANN) and recurrent neural networks (RNN), that are capable of capturing nonlinearities and time dependencies. These models are used to optimize the most profitable setpoints and are used in single-input single-output (SISO) and multi-input multi-output (MIMO) feedback control schemes using multiple proportional integral (PI) controllers and model predictive control. This study proposes approaches for experimental implementation such as incorporating delayed GC feedback into control loops, training dynamic ML models with dead times, data variability and noise, and linearizing the RNN models using Koopman operators for fast real-time optimization.The electrochemical CO2 reduction process has potential to use other chemical processes as CO2 source while sustainably producing other useful chemicals. In addition to the RCE setup, an experimental electrically-heated steam methane reforming (SMR) setup for hydrogen production from natural gas is digitalized, modeled, and controlled. A lumped parameter approach is used for fast calculations, and an extended Luenberger observer is used to compensate for missing and delayed sensor feedback. Finally, a model predictive controller using the estimation scheme is experimentally implemented to control hydrogen flow rates by manipulating the current, showing much faster response compared to PI control.
- 일반주제명
- Chemical engineering
- 일반주제명
- Industrial engineering
- 일반주제명
- Chemistry
- 일반주제명
- Engineering
- 키워드
- Digitalization
- 기타저자
- University of California, Los Angeles Chemical Engineering 0294
- 기본자료저록
- Dissertations Abstracts International. 85-12B.
- 전자적 위치 및 접속
- 로그인 후 원문을 볼 수 있습니다.
MARC
008250123s2024 us c eng d■001000017162391
■00520250211152007
■006m o d
■007cr#unu||||||||
■020 ▼a9798382819075
■035 ▼a(MiAaPQ)AAI31330698
■040 ▼aMiAaPQ▼cMiAaPQ
■0820 ▼a660
■1001 ▼aCitmaci, Berkay.
■24510▼aDigitalization, Machine Learning Modeling and Control of an Experimental Electrochemical Reactor
■260 ▼a[Sl]▼bUniversity of California, Los Angeles▼c2024
■260 1▼aAnn Arbor▼bProQuest Dissertations & Theses▼c2024
■300 ▼a382 p
■500 ▼aSource: Dissertations Abstracts International, Volume: 85-12, Section: B.
■500 ▼aAdvisor: Christofides, Panagiotis D.
■5021 ▼aThesis (Ph.D.)--University of California, Los Angeles, 2024.
■520 ▼aGreenhouse gas emissions from industry and transportation contribute significantly to climate change and its associated adverse impacts on the environment and economy. With the increase in electricity supply from clean energy sources, electrochemical reduction of carbon dioxide (CO2) has received increasing attention; however, a first-principles model for electrochemical CO2 reduction has not been fully developed because of the complexity of its reaction mechanism. At this point, data driven methods and machine learning (ML) can be used to model the process. At UCLA, we have constructed an experimental rotating cylinder electrode cell (RCE) setup to develop a deeper understanding of the process, and design scale-up strategies. The experimental equipment is digitalized on a computer interface using Smart Manufacturing principles, legacy sensors (such as Gas Chromatogram (GC)) are automated, and voluminous steady state and dynamic data sets are generated. Leveraging these datasets and data analytics, machine learning and hybrid models are built using machine learning methods, such as Support Vector Machines (SVR), and artificial neural networks (ANN) and recurrent neural networks (RNN), that are capable of capturing nonlinearities and time dependencies. These models are used to optimize the most profitable setpoints and are used in single-input single-output (SISO) and multi-input multi-output (MIMO) feedback control schemes using multiple proportional integral (PI) controllers and model predictive control. This study proposes approaches for experimental implementation such as incorporating delayed GC feedback into control loops, training dynamic ML models with dead times, data variability and noise, and linearizing the RNN models using Koopman operators for fast real-time optimization.The electrochemical CO2 reduction process has potential to use other chemical processes as CO2 source while sustainably producing other useful chemicals. In addition to the RCE setup, an experimental electrically-heated steam methane reforming (SMR) setup for hydrogen production from natural gas is digitalized, modeled, and controlled. A lumped parameter approach is used for fast calculations, and an extended Luenberger observer is used to compensate for missing and delayed sensor feedback. Finally, a model predictive controller using the estimation scheme is experimentally implemented to control hydrogen flow rates by manipulating the current, showing much faster response compared to PI control.
■590 ▼aSchool code: 0031.
■650 4▼aChemical engineering
■650 4▼aIndustrial engineering
■650 4▼aChemistry
■650 4▼aEngineering
■653 ▼aDigitalization
■653 ▼aElectrochemical process
■653 ▼aExperimental control
■653 ▼aLumped parameter modeling
■653 ▼aMachine learning modeling
■653 ▼aModel predictive control
■690 ▼a0542
■690 ▼a0537
■690 ▼a0546
■690 ▼a0485
■71020▼aUniversity of California, Los Angeles▼bChemical Engineering 0294.
■7730 ▼tDissertations Abstracts International▼g85-12B.
■790 ▼a0031
■791 ▼aPh.D.
■792 ▼a2024
■793 ▼aEnglish
■85640▼uhttp://www.riss.kr/pdu/ddodLink.do?id=T17162391▼nKERIS▼z이 자료의 원문은 한국교육학술정보원에서 제공합니다.
