심층신경망 및 베이지안 최적화 기반 패키지 휨 최적화 시간 단축
Time Reduction for Package Warpage Optimization based on Deep Neural Network and Bayesian Optimization
0
조회
0
다운로드
0
인용
0
참고문헌
키워드
초록
최근 대리 모델에 머신 러닝 기술을 접목하여 복잡한 설계에 대한 최적화를 빠르게 달성하는 방법론이 활발히연구되고 있다. 훈련된 머신 러닝 대리 모델은 복잡한 유한요소해석 시뮬레이션 대비 컴퓨팅 자원을 적게 소모하면서 동일한 해석 결과를 출력할 수 있다. 또한 훈련된 모델에 최적화를 결합하면 반복 시뮬레이션 대비 더 빠르게 최적의 설계변수를 도출할 수 있다. 본 연구에서는 패키지 휨을 최소화하는 설계 변수 조합을 효과적으로 탐색하기 위하여 심층신경망과 베이지안 최적화를 적용하였다. 심층신경망 모델은 유한요소해석 시뮬레이션으로 획득한 설계 변수-휨 데이터셋을바탕으로 훈련하였고, 해당 모델에 베이지안 최적화를 적용하여 휨을 최소화하는 최적의 설계 변수를 탐색하였다. 구축한 심층신경망 및 베이지안 최적화 모델은 실제 시뮬레이션 결과와 99% 이상 일치하는 동시에, 최적 설계 변수 탐색에소요되는 시간은 15초에 불과하여, 1회의 시뮬레이션과 비교해도 57% 이상 최적화 시간을 단축할 수 있다.
Abstract
Recently, applying a machine learning to surrogate modeling for rapid optimization of complex designs have been widely researched. Once trained, the machine learning surrogate model can predict similar outputs to Finite Element Analysis (FEA) simulations but require significantly less computing resources. In addition, combined with optimization methodologies, it can identify optimal design variable with less time requirement compared to iterative simulation. This study proposes a Deep Neural Network (DNN) model with Bayesian Optimization (BO) approach for efficiently searching the optimal design variables to minimize the warpage of electronic package. The DNN model was trained by using design variable-warpage dataset from FEA simulation, and the Bayesian optimization was applied to find the optimal design variables which minimizing the warpage. The suggested DNN + BO model shows over 99% consistency compared to actual simulation results, while only require 15 second to identify optimal design variable, which reducing the optimization time by more than 57% compared to FEA simulation.
참고문헌 (35)
- K. Sikka, "Direct bonded heterogeneous integration (DBHi) Si bridge", 2021 IEEE 71st Electronic Components and Technology Conference (ECTC), pp.136~147 (2021)
- J. H. Lau, "Recent advances and trends in advanced packaging", IEEE Transactions on Components, Packaging and Manufacturing Technology, 12(2), pp.228~252 (2022)
- A. Fontanelli, "System-in-package technology: Opportunities and challenges", 9th International Symposium on Quality Electronic Design (isqed 2008), pp.589~593 (2008)
- C. Chen, "Investigation of warpage for multi-die fan-out wafer-level packaging process", Materials, 15(5), pp.1683~ (2022)
- Y. Qiao, "Strategies for inducing heredity of β-Sn texture in micro solder joints during multireflow process", Materials & Design, 204, pp.109671~ (2021)
- S. P. Phansalkar, "Effect of critical properties of epoxy molding compound on warpage prediction : A critical review", Microelectronics Reliability, 130, pp.114480~ (2022)
- W. -C. Chuang, "Exploring the influence of material properties of epoxy molding compound on wafer warpage in Fan-out wafer-level packaging", Materials, 16(9), pp.3482~ (2023)
- S. Bao, "On the optimization of molding warpage for wafer-level glass interposer packaging", J Mater Sci : Mater Electron, 34, pp.1061~ (2023)
- J. Zhao, "Effects of package design on top PoP package warpage", 2008 58th Electronic Components and Technology Conference, pp.1082~1088 (2008)
- W. K. Loh, "Recent trend of package warpage characteristic", 2015 International Conference on Electronics Packaging and iMAPS All Asia Conference (ICEP-IAAC), pp.233~238 (2015)
- H. Hadim, "Multidisciplinary design and optimization methodologies in electronics packaging: state-ofthe-art review", J. Electron. Packag, 130(3) (2008)
- G. Huang, "Machine learning for electronic design automation : A survey", ACM Transactions on Design Automation of Electronic Systems, 26(5), pp.1~46 (2021)
- J. Kudela, "Recent advances and applications of surrogate models for finite element method computations : a review", Soft Computing, 26(24), pp.13709~13733 (2022)
- R. Alizadeh, "Managing computational complexity using surrogate models : a critical review", Research in Engineering Design, 31(3), pp.275~298 (2020)
- X. Chen, "The heat source layout optimization using deep learning surrogate modeling", Structural and Multidisciplinary Optimization, 62(6), pp.3127~3148 (2020)
- F. Kang, "Dynamic parameter inverse analysis of concrete dams based on Jaya algorithm with Gaussian processes surrogate model", Advanced Engineering Informatics, 49, pp.101348~ (2021)
- C. Lyu, "Surrogate model of liquid cooling system for lithiumion battery using extreme gradient boosting", Applied Thermal Engineering, 213, pp.118675~ (2022)
- Y. Yuan, "Robust design optimisation of underplatform dampers for turbine applications using a surrogate model", Journal of Sound and Vibration, 494, pp.115528~ (2021)
- Q. X. Lieu, "An adaptive surrogate model to structural reliability analysis using deep neural network", Expert Systems with Applications, 189, pp.116104~ (2022)
- Y. Seong, "Surrogate model with a deep neural network to evaluate gas–liquid flow in a horizontal pipe", Energies, 13(4), pp.968~ (2020)
- X. Zhang, "Multi-fidelity deep neural network surrogate model for aerodynamic shape optimization", Computer Methods in Applied Mechanics and Engineering, 373, pp.113485~ (2021)
- J. He, "ReLU deep neural networks and linear finite elements", J. Comp. Math, 38(3), pp.502~527 (2020)
- R. Garnett, "Bayesian Optimization" (2023), Cambridge University Press
- B. Lei, "Bayesian optimization with adaptive surrogate models for automated experimental design", npj Computational Materials, 7(194) (2021)
- Y. -F. Lim, "Extrapolative Bayesian optimization with Gaussian process and neural network ensemble surrogate models", Advanced Intelligent Systems, 3(11), pp.2100101~ (2021)
- L. Neng, "An Accurate Simulation Method of Package Warpage Experimental Results Based on FEM", 22nd International Conference on Electronic Packaging Technology (ICEPT), pp.1~4 (2021)
- H. -S. Kim, "Development of Warpage Simulation Method according to Thermal Stress based on Equivalent Anisotropic Viscoelastic Model", J. Microelectron. Packag. Soc, 29(3), pp.43~48 (2022)
- D. -H. Kim, "Warpage simulation of a multilayer printed circuit board and microelectronic package using the anisotropic viscoelastic shell modeling technique that considers the initial warpage", IEEE Transactions on Components, Packaging and Manufacturing Technology, 6(11), pp.1667~1676 (2016)
- A. Moon, "Process Induced Warpage Simulation for Panel Level Package", Journal of the Microelectronics and Packaging Society, 25(4), pp.41~45 (2018)
- J. -H. Baek, "Effect of cure shrinkage of epoxy molding compound on warpage behavior of semiconductor package", Materials Science in Semiconductor Processing, 148, pp.106758~ (2022)
- M. v. Dijk, "Simulation challenges of warpage for wafer-and panel level packaging", 21st International Conference on Thermal, Mechanical and Multi-Physics Simulation and Experiments in Microelectronics and Microsystems (EuroSimE), pp.1~6 (2020)
- G. Kim, "Warpage Analysis during Fan-Out Wafer Level Packaging Process using Finite Element Analysis", Journal of the Microelectronics and Packaging Society, 25(1), pp.41~45 (2018)
- C. L. Gan, "Evolution of epoxy molding compounds and future carbon materials for thermal and mechanical stress management in memory device packaging: a critical review", Journal of Materials Science: Materials in Electronics, 34(2011) (2023)
- J. Kim, "Enhancing predictability of thermal warpage by applying temperature-dependent Poisson's ratio of epoxy molding compound", Polymer Testing, 125, pp.108140~ (2023)