상세 보기
Physics-informed neural networks for thermal spreading of multilayer multichip power modules
- Kim, Yonghun;
- Yoon, Changhyeon;
- Lee, Haeun;
- Bae, Seonu;
- Kang, Nana;
- ... Lee, Sooyoung;
- ... Lee, Hyoungsoon;
- 외 3명
WEB OF SCIENCE
0SCOPUS
0초록
Efficient thermal management in multilayer, multi-source power modules remains a critical barrier to advancing high-performance electronic systems. Analytical models are limited to highly simplified geometries, while finite volume method (FVM) requires extensive meshing and prohibitive computational cost for iterative design exploration. Here, we present a physics-informed neural network (PINN) integrated with a Gaussian process (GP) surrogate to enable mesh-free, physically consistent thermal prediction and rapid design optimization. The PINN achieves prediction errors below 2.4% for single-source validation and below 2.0% for a realistic seven-layer, multi-source power module, while the complete PINN-GP workflow reduced the estimated design-exploration time from approximately 15,000 to 200 h compared with sequential FVM evaluation. Coupling the PINN with a GP surrogate enables efficient identification of optimal geometric parameters, achieving up to 4.1% reduction in thermal spreading resistance. This PINN-GP framework provides a scalable pathway for thermal analysis and design optimization in next-generation power modules.
키워드
- 제목
- Physics-informed neural networks for thermal spreading of multilayer multichip power modules
- 저자
- Kim, Yonghun; Yoon, Changhyeon; Lee, Haeun; Bae, Seonu; Kang, Nana; Han, Changwoo; Shin, Dongmin; Cho, Jungwan; Lee, Sooyoung; Lee, Hyoungsoon
- 발행일
- 2026-11
- 유형
- Article
- 권
- 180
- 언어
- ENG
- 출판사
- Elsevier Ltd
- 발행국가
- 영국
- ISSN
- E 1879-0178
P 0735-1933