DC Field | Value | Language |
---|---|---|
dc.contributor.advisor | 남영석 | - |
dc.contributor.author | Cho, Hyunho | - |
dc.contributor.author | 조현호 | - |
dc.date.accessioned | 2024-07-30T19:30:26Z | - |
dc.date.available | 2024-07-30T19:30:26Z | - |
dc.date.issued | 2024 | - |
dc.identifier.uri | http://library.kaist.ac.kr/search/detail/view.do?bibCtrlNo=1095968&flag=dissertation | en_US |
dc.identifier.uri | http://hdl.handle.net/10203/321300 | - |
dc.description | 학위논문(석사) - 한국과학기술원 : 기계공학과, 2024.2,[iii, 32 :] | - |
dc.description.abstract | The heterogeneous integration package, gaining attention as a next-generation packaging technology, offers high design freedom but can lead to serious issues like thermal crack, delamination, and performance degradation due to severe temperature gradients caused by non-uniform heat flux distribution. In this thesis, a direct liquid cooling module using multiple jet impingement arrays was designed, and the optimal nozzle arrangement was explored to minimize temperature non-uniformity of package substrate with non-uniform heat flux distribution and energy consumption for cooling. For this purpose, the multi-objective optimization based on genetic algorithms was conducted using finite element method-based numerical analysis model and convolutional neural network metamodel. Additionally, a design optimization framework, combining hierarchical exploration and active learning, was developed to reduce the time and resources required for optimization. It was confirmed that the optimized nozzle arrangements for three cases exhibited superior performance compared to intuitively arranged regular nozzle arrays. | - |
dc.language | eng | - |
dc.publisher | 한국과학기술원 | - |
dc.subject | 이종 집적 패키지▼a다목적 최적화▼a제트 충돌 어레이▼a직접 액체 냉각▼a합성곱 신경망▼a능동 학습▼a유전 알고리즘▼a계층적 탐색 | - |
dc.subject | Heterogeneous integration package▼aMulti-objective optimization▼aJet impingement array▼aDirect liquid cooling▼aConvolutional neural network▼aActive learning▼aGenetic algorithm▼aHierarchical exploration | - |
dc.title | An active learning approach to performance optimization of jet array impingement-based cooling module for heterogeneous integration semiconductor packages | - |
dc.title.alternative | 이종 집적 반도체 패키지용 제트 충돌 어레이 기반 냉각 모듈의 성능 최적화를 위한 능동 학습 접근법 | - |
dc.type | Thesis(Master) | - |
dc.identifier.CNRN | 325007 | - |
dc.description.department | 한국과학기술원 :기계공학과, | - |
dc.contributor.alternativeauthor | Nam, Youngsuk | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.