서브메뉴
검색
Automated Exploration of High-Mix, Low Volume Direct Write Design Spaces Through Artificial Intelligence
Automated Exploration of High-Mix, Low Volume Direct Write Design Spaces Through Artificial Intelligence
Detailed Information
- 자료유형
- 학위논문 서양
- 최종처리일시
- 20260209102905
- ISBN
- 9798265400345
- DDC
- 000
- 서명/저자
- Automated Exploration of High-Mix, Low Volume Direct Write Design Spaces Through Artificial Intelligence
- 발행사항
- [Sl] : Georgia Institute of Technology, 2023
- 발행사항
- Ann Arbor : ProQuest Dissertations & Theses, 2023
- 형태사항
- 108 p
- 주기사항
- Source: Dissertations Abstracts International, Volume: 87-05, Section: B.
- 주기사항
- Advisor: Kalidindi, Surya.
- 학위논문주기
- Thesis (Ph.D.)--Georgia Institute of Technology, 2023.
- 초록/해제
- 요약Additive manufacturing has experienced considerable growth over the recent decades from technological infancy to functional use across a range of industries and applications. This growth has come with increased challenges as optimal function of production parts requires the marriage of both the proper material and geometry. This challenging optimization problem is currently solved through the intervention of AM experts to ensure proper process parameters are selected. While acceptable in some cases, the need for such interventions obstructs AM from reaching its full potential to deliver customized solutions in a high-mix, low-volume (HMLV) circumstance. Thus, there is a crucial need for solutions that accommodate frequent changeovers that are innate to HMLV without sacrificing the ability to analyze the complex properties of interest. Artificial Intelligence (AI) and its specific success with image analysis represents an opportunity assist in AM for HMLV manufacturing and ease the burden from AM experts. The proposed research will utilize direct ink write (DIW) to demonstrate the capabilities of AI to impact HMLV manufacturing in the following case studies: The first study will develop a generalizable image analysis and AI tool to classify DIW printed linear self-supporting filaments and demonstrate the tool's value when paired with domain expert knowledge to automate optimal process parameter discovery. The second study will utilize similar image analysis and AI methodology on the DIW printing of quantum dot (QD) ink drops, a vastly different AM application, to classify the spatial ink distribution of the printed drops. The third study will apply further AI techniques to build upon the image analysis and AI tool using data-driven exploration to discover sufficient parameters to DIW print complex non-linear self-supporting geometries. This case will extend beyond the realm of expert domain knowledge as seen in the first study and instead demonstrate the power of AI to assist in exploring complex process parameter spaces. The tools constructed over the course of these three studies will showcase the value AI-driven analysis can provide HMLV manufacturing - a field whose needs are often left unfulfilled by standard modern AI practice.
- 일반주제명
- Support vector machines
- 일반주제명
- Computer science
- 기본자료저록
- Dissertations Abstracts International. 87-05B.
- 전자적 위치 및 접속
- 로그인 후 원문을 볼 수 있습니다.
MARC
008260203s2023 us c eng d■001000017365966
■00520260209102905
■006m o d
■007cr#unu||||||||
■020 ▼a9798265400345
■035 ▼a(MiAaPQ)AAI32315638
■035 ▼a(MiAaPQ)GeorgiaTech73168
■040 ▼aMiAaPQ▼cMiAaPQ
■0820 ▼a000
■1001 ▼aJohnson, Marshall.
■24510▼aAutomated Exploration of High-Mix, Low Volume Direct Write Design Spaces Through Artificial Intelligence
■260 ▼a[Sl]▼bGeorgia Institute of Technology▼c2023
■260 1▼aAnn Arbor▼bProQuest Dissertations & Theses▼c2023
■300 ▼a108 p
■500 ▼aSource: Dissertations Abstracts International, Volume: 87-05, Section: B.
■500 ▼aAdvisor: Kalidindi, Surya.
■5021 ▼aThesis (Ph.D.)--Georgia Institute of Technology, 2023.
■520 ▼aAdditive manufacturing has experienced considerable growth over the recent decades from technological infancy to functional use across a range of industries and applications. This growth has come with increased challenges as optimal function of production parts requires the marriage of both the proper material and geometry. This challenging optimization problem is currently solved through the intervention of AM experts to ensure proper process parameters are selected. While acceptable in some cases, the need for such interventions obstructs AM from reaching its full potential to deliver customized solutions in a high-mix, low-volume (HMLV) circumstance. Thus, there is a crucial need for solutions that accommodate frequent changeovers that are innate to HMLV without sacrificing the ability to analyze the complex properties of interest. Artificial Intelligence (AI) and its specific success with image analysis represents an opportunity assist in AM for HMLV manufacturing and ease the burden from AM experts. The proposed research will utilize direct ink write (DIW) to demonstrate the capabilities of AI to impact HMLV manufacturing in the following case studies: The first study will develop a generalizable image analysis and AI tool to classify DIW printed linear self-supporting filaments and demonstrate the tool's value when paired with domain expert knowledge to automate optimal process parameter discovery. The second study will utilize similar image analysis and AI methodology on the DIW printing of quantum dot (QD) ink drops, a vastly different AM application, to classify the spatial ink distribution of the printed drops. The third study will apply further AI techniques to build upon the image analysis and AI tool using data-driven exploration to discover sufficient parameters to DIW print complex non-linear self-supporting geometries. This case will extend beyond the realm of expert domain knowledge as seen in the first study and instead demonstrate the power of AI to assist in exploring complex process parameter spaces. The tools constructed over the course of these three studies will showcase the value AI-driven analysis can provide HMLV manufacturing - a field whose needs are often left unfulfilled by standard modern AI practice.
■590 ▼aSchool code: 0078.
■650 4▼aSupport vector machines
■650 4▼aComputer science
■690 ▼a0800
■690 ▼a0984
■71020▼aGeorgia Institute of Technology.
■7730 ▼tDissertations Abstracts International▼g87-05B.
■790 ▼a0078
■791 ▼aPh.D.
■792 ▼a2023
■793 ▼aEnglish
■85640▼uhttp://www.riss.kr/pdu/ddodLink.do?id=T17365966▼nKERIS▼z이 자료의 원문은 한국교육학술정보원에서 제공합니다.
Preview
Export
ChatGPT Discussion
AI Recommended Related Books
Подробнее информация.
- Бронирование
- не существует
- моя папка
- Первый запрос зрения
- Non-Book Loan Application
- Nighttime Book Loan Application
Available after logging in.


