본문 바로가기
KERD
논문KCI 등재

몰드 경화 공정 중 패키지 휨 예측을 위한 비용 절감형 머신러닝 방법

Cost-effective Machine Learning Method for Predicting Package Warpage during Mold Curing

이은호|김태현|박성환
한국마이크로전자및패키징학회 (The Microelectronics And Packaging Society)|2024.09|마이크로전자 및 패키징학회지 (Jornal of the Microelectronics and Packaging Society)|제31권 제3호|pp. 24-37|DOI doi.org/10.6117/kmeps.2024.31.3.024

0

조회

0

다운로드

1

인용

0

참고문헌

키워드

FEM simulationWarpageCuring processCost-effectivePhysics informed machine Learning
주제분류재료공학

초록

반도체 패키지의 초박형화로 인해 작은 열하중에서도 Warpage가 크게 발생하며, 이는 제품 신뢰성에 심각한 영향을 미칠 수 있다. 특히 몰드 경화 공정에서의 Warpage 예측은 복합적인 열-화학-기계적 현상으로 인해 어려운 문제이다. 본 연구는 몰드 경화 공정에서 Warpage를 예측하기 위한 비용 절감형 머신러닝 모델 구축 방법을 분석하였다. 경화 공정에서 시간과 온도에 따른 경화도를 특성화하고, 이를 통해 재료의 기계적 특성을 수치화하였다. ABAQUS UMAT을 사용해 특성화된 재료 특성으로 FEM 시뮬레이션 모델을 개발하였으며, 패키지의 적층 구조에 따른 Local Warpage를 예측하는 Warpage formula를 제안하고 FEM 시뮬레이션 결과와 비교하여 검증하였다. 개발된 모델과 이론식을 통해 다양한 설계 인자를 고려한 몰드 경화 공정에서 Warpage를 저비용으로 예측할 수 있는 방법을 제시하였다. 이 방법은 머신러닝 입력 변수로 Warpage formula를 사용하고, 훈련 데이터 세트를 효율적으로 구축하여 Single IC 패키지 기준으로 98% 이상의 예측 정확도와 96.5%의 시뮬레이션 시간 절약을 가능하게 한다.

Abstract

Due to the thin nature of semiconductor packages, even minor thermal loads can cause significant warpage, impacting product reliability through issues like delamination or cracking. The mold curing process, which encloses the package to protect the semiconductor chip, is particularly challenging to predict due to the complex thermal, chemical, and mechanical interactions. This study proposes a cost-effective machine learning model to predict warpage in the mold curing process. We developed methods to characterize the curing degree based on time and temperature and quantify the material's mechanical properties accordingly. A Finite Element Method (FEM) simulation model was created by integrating these properties into ABAQUS UMAT to predict warpage for various design factors. Additionally, a Warpage formula was developed to estimate local warpage based on the package's stacking structure. This formula combines bending theory with thermo-chemical-mechanical properties and was validated through FEM simulation results. The study presents a method to construct a machine learning model for warpage prediction using this formula and proposes a cost-effective approach for building a training dataset by analyzing input variables and design factors. This methodology achieves over 98% prediction accuracy and reduces simulation time by 96.5%.

참고문헌 (45)

  1. C. Kim, "Packaging Substrate Bending Prediction due to Residual Stress", J. Microelectron. Packag. Soc, 20(1), pp.21~26 (2013)
  2. J. Zhao, "Effects of package design on top PoP package warpage", 2008 58th Electronic Components and Technology Conference, pp.1082~1088 (2008)
  3. M. Joshi, "Molded underfill (MUF) technology for flip chip packages in mobile applications", 2010 Proceedings 60th Electronic Components and Technology Conference (ECTC), pp.1250~1257 (2010)
  4. 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)
  5. W. K. Loh, "Recent trends of package warpage and measurement metrologies", 2016 International Conference on Electronics Packaging (ICEP), pp.89~93 (2016)
  6. S. -H. Chae, "Characterization of viscoelasticity of molding compounds in time domain", International Electronic Packaging Technical Conference and Exhibition, pp.435~441 (2009)
  7. D. -H. Lee, "A Numerical Study on the Effect of Initial Shape on Inelastic Deformation of Solder Balls under Various Mechanical Loading Conditions", J. Microelectron. Packag. Soc, 30(4), pp.50~60 (2023)
  8. C. -C. Lee, "Simulation methodology development of warpage estimation for epoxy molding compound under considerations of stress relaxation characteristics and curing conditions applied in semiconductor packaging", Materials Science in Semiconductor Processing, 145, pp.106637~ (2022)
  9. T. -C. Chiu, "Effects of curing and chemical aging on warpage—Characterization and simulation", IEEE Transactions on Device and Materials Reliability, 11(2), pp.339~348 (2011)
  10. D. Yang, "Modeling of cure-induced warpage of plastic IC packages", 5th International Conference on Thermal and Mechanical Simulation and Experiments in Microelectronics and Microsystems (EuroSimE 2004), pp.33~40 (2004)
  11. M. -Y. Lin, "Warpage and residual stress analyses of post-mold cure process of IC packages", The International Journal of Advanced Manufacturing Technology, 124, pp.1017~1039 (2023)
  12. P. -Y. Lin, "Warpage modeling of ultra-thin packages based on chemical shrinkage and cure-dependent viscoelasticity of molded underfill", IEEE Transactions on Device and Materials Reliability, 20(1), pp.67~73 (2020)
  13. Y. -J. Lin, "Modeling of viscoelastic behavior of an epoxy molding compound during and after curing", IEEE Transactions on Components, Packaging and Manufacturing Technology, 1(11), pp.1755~1760 (2011)
  14. C. Yang, "Time-Dependent Warpage Analysis for PCB Considering Viscoelastic Properties of Prepreg", J. Microelectron. Packag. Soc, 31(2), pp.23~27 (2024)
  15. S. -S. Yeh, "Viscoelastic Modeling for Heterogeneous Fan-out Wafer Molding Process", 2020 IEEE 70th Electronic Components and Technology Conference (ECTC), pp.1081~1086 (2020)
  16. P. -Y. Lin, "Modeling and characterization of curedependent viscoelasticity of molded underfill in ultrathin packages", IEEE Transactions on Components, Packaging and Manufacturing Technology, 10(9), pp.1491~1498 (2020)
  17. S. -S. Yeh, "An integrated warpage prediction model based on chemical shrinkage and viscoelasticity for molded underfill", 2018IEEE 68th Electronic Components and Technology Conference (ECTC), pp.249~254 (2018)
  18. J. Kim, "Fault detection prediction using a deep belief network-based multi-classifier in the semiconductor manufacturing process", International Journal of Software Engineering and Knowledge Engineering, 29(08), pp.1125~1139 (2019)
  19. C. -F. Chien, "Data mining for yield enhancement in semiconductor manufacturing and an empirical study", Expert Systems with Applications, 33(1), pp.192~198 (2007)
  20. K. Nakata, "A comprehensive big-data-based monitoring system for yield enhancement in semiconductor manufacturing", IEEE Transactions on Semiconductor Manufacturing, 30(4), pp.339~344 (2017)
  21. G. Köksal, "A review of data mining applications for quality improvement in manufacturing industry", Expert Systems with Applications, 38(10), pp.13448~13467 (2011)
  22. S. Cheon, "Convolutional neural network for wafer surface defect classification and the detection of unknown defect class", IEEE Transactions on Semiconductor Manufacturing, 32(2), pp.163~170 (2019)
  23. D. -Y. Liu, "Machine learning for semiconductors", Chip, 1(4), pp.100033~ (2022)
  24. T. -H. Kim, "Application of convolutional neural network to predict anisotropic effective thermal conductivity of semiconductor package", IEEE Access, 10, pp.51995~52007 (2022)
  25. T. Y. Kang, "Signal-Based Fault Detection and Diagnosis on Electronic Packaging and Applications of Artificial Intelligence Techniques", J. Microelectron. Packag. Soc, 30(1), pp.30~41 (2023)
  26. G. E. Batista, "A study of the behavior of several methods for balancing machine learning training data", ACM SIGKDD explorations newsletter, 6(1), pp.20~29 (2004)
  27. H. Chen, "Novel machine learning approaches for modeling variations in semiconductor manufacturing", pp.2017
  28. S. Lynn, "Virtual metrology for plasma etch using tool variables", 2009 IEEE, 2009, 143~148
  29. T. -H. Lin, "NN-based key-variable selection method for enhancing virtual metrology accuracy", IEEE Transactions on Semiconductor Manufacturing, 22(1), pp.204~211 (2009)
  30. J. R. Beattie, "Exploration of principal component analysis : deriving principal component analysis visually using spectra", Applied Spectroscopy, 75(4), pp.361~375 (2021)
  31. D. Jiang, "A novel framework for semiconductor manufacturing final test yield classification using machine learning techniques", IEEE Access, 8, pp.197885~197895 (2020)
  32. G. E. Karniadakis, "Physics-informed machine learning", Nature Reviews Physics, 3, pp.422~430 (2021)
  33. T. Ahmed, "Warpage prediction of Injection-molded PVC part using ensemble machine learning algorithm", Materialstoday : Proceedings, 50(5), pp.565~569 (2022)
  34. Z. Shu, "Using Extra Trees Machine Learning Algorithm to Predict the Asymmetric Warpage Geometry of Panel Level Packaging", 2022 17th International Microsystems, Packaging, Assembly and Circuits Technology Conference (IMPACT), pp.1~4 (2022)
  35. S. W. Liu, "Prediction of fan-out panel level warpage using neural network model with edge detection enhancement", 2020 IEEE 70th Electronic Components and Technology Conference (ECTC), pp.1626~1631 (2020)
  36. S. K. P anigrahy, "Integration of Artificial Neural Network and Finite Element Simulation for Package Warpage Prediction", 2023IEEE 25th Electronics Packaging Technology Conference (EPTC), pp.926~931 (2023)
  37. E. -H. Lee, "A model for irreversible deformation phenomena driven by hydrostatic stress, deviatoric stress and an externally applied field", International Journal of Engineering Science, 169, pp.103573~ (2021)
  38. M. R. Kamal, "Thermoset characterization for moldability analysis", Polymer Engineering & Science, 14(3), pp.231~239 (1974)
  39. A. Armillotta, "Warpage of FDM parts : Experimental tests and analytic model", Robotics and Computer-Integrated Manufacturing, 50, pp.140~152 (2018)
  40. F. X. Che, "Study on process induced wafer level warpage of fan-out wafer level packaging", 2016 IEEE 66th Electronic Components and Technology Conference (ECTC), pp.1879~1885 (2016)
  41. C. Chen, "Warpage prediction and optimization for embedded silicon fan-out waferlevel packaging based on an extended theoretical model", IEEE Transactions on Components, Packaging and Manufacturing Technology, 9(5), pp.845~853 (2019)
  42. M. A. Eltaher, "Determination of neutral axis position and its effect on natural frequencies of functionally graded macro", nanobeams, 2013, pp.99, 193~201
  43. S. Timoshenko, "Analysis of bi-metal thermostats", Journal of the Optical Society of America, 11(3), pp.233~255 (1925)
  44. M. -Y. Tsai, "A theoretical solution for thermal warpage of flip-chip packages", IEEE Transactions on Components, Packaging and Manufacturing Technology, 10(1), pp.72~78 (2020)
  45. G. Yang, "A quantitative model to understand the effect of gravity on the warpage of fan-out panel-level packaging", IEEE Transactions on Components, Packaging and Manufacturing Technology, 11(11), pp.2022~2030 (2021)

관련 논문AI추천

심층신경망 및 베이지안 최적화 기반 패키지 휨 최적화 시간 단축권대일, 이중언한국마이크로전자및패키징학회 · 마이크로전자 및 패키징학회지2024 · 제31권 제3호차세대 패키징에서의 워피지: 이종집적을 위한 도전 과제, 측정 기법 및 저감 전략김택수, 이선우, 주민상한국마이크로전자및패키징학회 · 마이크로전자 및 패키징학회지2025 · 제32권 제1호반도체 패키지용 PCB의 구조 모델링 방법에 따른 패키지의 warpage 수치적 연구전현찬, 조승현한국마이크로전자및패키징학회 · 마이크로전자 및 패키징학회지2018 · 제25권 제4호웨이퍼 레벨 패키지 신뢰성 수명 예측을 위한 인공지능 기술 연구동향김광석, 이동근, 정건주한국마이크로전자및패키징학회 · 마이크로전자 및 패키징학회지2025 · 제32권 제1호등가 이방성 점탄성 모델 기반 열 응력에 따른 휨 해석 기법 개발김학성, 김헌수한국마이크로전자및패키징학회 · 마이크로전자 및 패키징학회지2022 · 제29권 제3호팬아웃 웨이퍼 레벨 패키지 공정 중 재료 물성의 불확실성이 휨 현상에 미치는 영향강기훈, 권대일, 김금택한국마이크로전자및패키징학회 · 마이크로전자 및 패키징학회지2019 · 제26권 제1호

이 간행물의 다른 논문 (14건)

저온 Cu 하이브리드 본딩을 위한 폴리머 본딩박종경, 김지훈pp. 1-9Flexible DDI Package의 Bonding 기술 발전정예환, 김경태pp. 10-17극압 임프린트 리소그래피를 통한 자성고무 복합재 표면 미세 패터닝 기술강은빈, 김유나, 박운익pp. 18-23배선 및 본딩 접합 구조에서 정렬 오차에 따른 전기 신호 전달 효율 변화에 대한 분석오승환, 홍슬기pp. 38-41고주파 EMI 차폐 필름을 위한 트라이모달 실버 페이스트의 개발과 유연성, 내구성 및 차폐 특성에 대한 평가남수용, 박세훈, 김유빈, 김선우, 구모세, 남현진pp. 42-49
원문 보기