基于机器学习电子封装互连材料研究现状

doi:10.3901/JME.2023.22.222

PDF(638 KB)

机械工程学报 ›› 2023, Vol. 59 ›› Issue (22) : 222-233. DOI: 10.3901/JME.2023.22.222

扫码查看或转发全文

材料科学与工程

基于机器学习电子封装互连材料研究现状

张墅野^1,2, 段晓康¹, 罗克宇¹, 许孙武¹, 张志昊³, 陈捷狮⁴, 何鹏¹

作者信息 +

Current Status of Electronic Packaging Materials Using Machine Learning

ZHANG Shuye^1,2, DUAN Xiaokang¹, LUO Keyu¹, XU Sunwu¹, ZHANG Zhihao³, CHEN Jieshi⁴, HE Peng¹

Author information +

文章历史 +

摘要

随着“后摩尔时代”到来，先进封装技术使芯片性能不断提升，传统的材料开发制备以及封装互连研究难以适应时代需要。根据工业4.0的愿景，采用机器学习的算法在封装材料开发预测、封装工艺优化、焊点可靠性等方面进行高效预测工作，是未来发展的趋势之一。材料领域应用机器学习的过程，包括收集数据、数据预处理、调参优化三方面。封装领域中大多数预测问题可以归类为分类问题，传统监督学习应用最为广泛，常用算法有支持向量机、人工神经网络等。深度学习在封装问题的预测中大放异彩，如卷积神经网络模型等深度学习算法已经逐渐应该用于预测中，并且获得极佳的预测效果。尽管机器学习辅助电子封装研究尚处于萌芽状态，但仍然能够看到机器学习在电子封装领域具有巨大研究及实用价值。

Abstract

With the advent of “post-Moore era”, advanced packaging technology improves the performance of chips, and traditional materials development and preparation and research of packaging interconnect are difficult to meet the needs of the era. According to the vision of industry 4.0, it is one of the future development trends to use machine learning algorithm to efficiently predict packaging material development, packaging process optimization, solder joint reliability. The process of applying machine learning in material field includes data collection, data preprocessing and parameter tuning optimization. Deep learning shines in the prediction of packaging problems. Deep learning algorithms such as convolutional neural network model have gradually been applied to prediction and achieved excellent prediction results. Although the research of machine learning-assisted electronic packaging is still in its infancy, machine learning still has great research and practical value.

导出引用

张墅野, 段晓康, 罗克宇, 许孙武, 张志昊, 陈捷狮, 何鹏. 基于机器学习电子封装互连材料研究现状[J]. 机械工程学报, 2023, 59(22): 222-233 https://doi.org/10.3901/JME.2023.22.222

ZHANG Shuye, DUAN Xiaokang, LUO Keyu, XU Sunwu, ZHANG Zhihao, CHEN Jieshi, HE Peng. Current Status of Electronic Packaging Materials Using Machine Learning[J]. Journal of Mechanical Engineering, 2023, 59(22): 222-233 https://doi.org/10.3901/JME.2023.22.222

参考文献

[1] WANG Q, ZHANG S, LIN T, et al, Highly mechanical and high-temperature properties of Cu-Cu joints using citrate-coated nanosized Ag paste in air[J]. Progress in Natural Science, 2021, 31(1):129.
[2] MITTAL J, LIN K. Carbon nanotube-based interconnections[J]. Journal of Materials Science, 2017, 52(2):643-662.
[3] LEE L, KANG L, KWON Y, et al, FOWLP technology as wafer level system in packaging (SiP) solution[C]//International Conference on Electronics Packaging, 19-22 April 2017, Yamagata, 2017 International Conference on Electronics Packaging, 08 June 2017, Yamagata.
[4] ZHANG S, XU X, LIN T, et al. Recent advances in nano-materials for packaging of electronic devices[J]. Journal of Materials Science:Materials in Electronics, 2019, 30(15):13855-13868.
[5] YANG M, KO Y, BANG J, et al. Growth inhibition of interfacial intermetallic compounds by pre-coating oriented Cu6Sn5grains on Cu substrates[J]. Journal of Alloys and Compounds, 2017, 701:533-541.
[6] JIN T, PAN Y, JEON G J, et al. Ultrathin nanofibrous membranes containing insulating microbeads for highly sensitive flexible pressure sensors[J]. ACS Applied Materials & Interfaces, 2020, 12(11):13348-13359.
[7] TOM M. Machine learning[M]. Maidenhead, UK:Tracepro, 1997.
[8] WANG F, ZHANG J, ZHENG, et al. Where does AlphaGo go:From church-turing thesis to AlphaGo thesis and beyond[J]. Acta Automatica Sinica, 2016, 3(2):113-120.
[9] HUANG C, HUANG H. Process optimization of SnCuNi soldering material using artificial parametric design[J]. Journal of Intelligent Manufacturing, 2014, 25(4):813-823.
[10] GUO H, ZHOU D, PANG L, et al. Microwave dielectric properties of low firing temperature stable scheelite structured (Ca,Bi)(Mo,V)O-4 solid solution ceramics for LTCC applications[J]. Journal of the European Ceramic Society, 2019, 39(7):2365-2373.
[11] LIU Y, LIU T, HUANG T, et al. Exploring dielectric constant and dissipation factor of LTCC using machine learning[J]. Materials, 2021, 14(19):5784.
[12] JIN K, LUO H, WANG Z, et al. Composition optimization of a high-performance epoxy resin based on molecular dynamics and machine learning[J]. Materials & Design, 2020, 194:108932.
[13] DOBLIES A, BOLL B, FIEDLER B, et al. Prediction of thermal exposure and mechanical behavior of epoxy resin using artificial neural networks and Fourier transform infrared spectroscopy[J]. Polymers, 2019, 11(2):363.
[14] ZHANG S, ZHU B, ZHOU X, et al. Wettability and interfacial morphology of Sn-3.0Ag-0.5Cu solder on electroless nickel plated ZnS transparent ceramic[J]. Journal of Materials Science:Materials in Electronics, 2019, 30(19):17972-17985.
[15] WANG J, CHEN J, ZHANG Z, et al. Effects of doping trace Ni element on interfacial behavior of Sn/Ni (polycrystal/single-crystal) joints[J]. Soldering & Surface Mount Technology, 2022, 34(2):124-133.
[16] ZHANG S, YANG M, WU Y, et al. A study on the optimization of anisotropic conductive films for Sn-3Ag-0.5Cu-based flex-on-board application at a 250℃ bonding temperature[J]. IEEE Transactions on Components, Packaging and Manufacturing Technology, 2018, 8(3):383-391.
[17] ZHANG S, LIN T, HE P, et al. A study on the bonding conditions and nonconductive filler contents on cationic epoxy-based Sn-58Bi solder ACFs joints for reliable flex-on-board applications[J]. IEEE Transactions on Components, Packaging and Manufacturing Technology, 2017, 7(12):2087-2094.
[18] JONATHAN S, LIMING C, SILVANA B, et al. Predicting the stability of ternary intermetallics with density functional theory and machine learning[J]. Journal of Chemical Physics, 2018(148):241728.
[19] LIU Y, PU L, YANG Y, et al. A high-entropy alloy as very low melting point solder for advanced electronic packaging[J]. Materials Today Advances, 2020(7):100101.
[20] ZHANG L, SHI J, LI H, et al. Interfacial microstructure and mechanical properties of ZrB2-SiC-C ceramic and GH99 superalloy joints brazed with a Ti-modified FeCoNiCrCu high-entropy alloy[J]. Materials & Design, 2016(97):230-238.
[21] BRIDGES D, ZHANG S, LANG S, et al, Laser brazing of a nickel-based superalloy using a Ni-Mn-Fe-Co-Cu high entropy alloy filler metal[J]. Materials Letters, 2018(215):11-14.
[22] SHEN Y, LIN C, LI J, et al. Effect of FeCoNiCrCu0.5 high-entropy-alloy substrate on Sn grain size in Sn-3.0Ag-0.5Cu solder[J]. Scientific Reports, 2019(9):3658.
[23] SHEN Y, HSIEH, CHEN S, et al. Investigation of FeCoNiCu properties:Thermal stability, corrosion behavior, wettability with Sn-3.0Ag-0.5Cu and interlayer formation of multi-element intermetallic compound[J]. Applied Surface Science, 2021(546):148931.
[24] ZHANG L, CHEN H, TAO X, et al. Machine learning reveals the importance of the formation enthalpy and atom-size difference in forming phases of high entropy alloys[J]. Materials & Design, 2020(193):108835.
[25] HUANG W, MARTIN P, ZHUANG H L. Machine learning phase prediction of high-entropy alloys[J]. Acta Materialia, 2019, 169:225-236.
[26] KRISHNA Y, JAISWAL U, RAHUL M. Machine learning approach to predict new multiphase high entropy alloys[J]. Scripta Materialia, 2021(197):113804.
[27] LIN Y, DENG W, SHIE J, et al. Optimization of reflow soldering process for BGA packages by artificial neural network[J]. Microelectronics International, 2007, 21(2):64-70.
[28] TSAI T, TSAI C. Development of a closed-loop diagnosis system for reflow soldering using neural networks and support vector regression[J]. The International Journal of Industrial Engineering:Theory, Applications and Practice, 2014, 21(1):19-33.
[29] HUANG C. Innovative parametric design for environmentally conscious adhesive dispensing process[J]. Journal of Intelligent Manufacturing, 2013, 26(1):1-12.
[30] YUN T, SIM K, KIM H, Support vector machine-based inspection of solder joints using circular illumination[J]. Electronics Letters, 2000, 36(11):949-951.
[31] MA L, XIE W, ZHANG Y, et al. Extreme learning machine based defect detection for solder joints[J]. Journal of Internet Technology, 2020, 21(5):1535-1543.
[32] GOTO K, KATO K, SAITO T, et al. Adversarial autoencoder for detecting anomalies in soldered joints on printed circuit boards[J]. Journal of Electronic Imaging, 2020, 29(4):041013-041022.
[33] TSAN T, SHIH T, FUH C. TsanKit:Artificial intelligence for solder ball head-in-pillow defect inspection[J]. Machine Vision and Applications, 2021, 32(3):66-83.
[34] SU L, WANG L, LI K, et al. Automated X-ray recognition of solder bump defects based on ensemble-ELM[J]. Science China Technological Sciences, 2019, 62(9):1512-1519.
[35] WEI W, WEI L, NIE L, et al. Using active thermography and modified SVM for intelligent diagnosis of solder bumps[J]. Infrared Physics & Technology, 2015(72):163-169.
[36] FAN M, WEI L, HE Z, et al. Defect inspection of solder bumps using the scanning acoustic microscopy and fuzzy SVM algorithm[J]. Microelectronics Reliability, 2016(65):192-197.
[37] ZHANG L, UME L, GAMALSKI J, et al. Study of flip chip solder joint cracks under temperature cycling using a laser ultrasound inspection system[J]. IEEE Transactions on Components and Packaging Technologies, 2009, 32(1):120-126.
[38] ERDAHL D, ALLEN M, UME I, et al. Structural modal analysis for detecting open solder bumps on flip chips[J]. IEEE Transactions on Advanced Packaging, 2008, 31(1):118-126.
[39] LIU S, UME I. Vibration analysis based modeling and defect recognition for flip-chip solder-joint inspection[J]. Journal of Electronic Packaging, 2002, 124(3):221-226.
[40] LI K, WANG L, WU J, et al. Using GA-SVM for defect inspection of flip chips based on vibration signals[J]. Microelectronics Reliability, 2018(81):159-166.
[41] WU H, GAO W, XU X. Solder joint recognition using mask R-CNN method[J]. IEEE Transactions on Components, Packaging, and Manufacturing Technology, 2020, 10(3):525-530.
[42] ZHOU J, XIAO X, EN Y, et al, Thermo-mechanical fatigue reliability optimization of PBGA solder joints based on ANN-PSO[J]. Journal of Central South University of Technology, 2008, 15(5):689-693.
[43] YUAN C, FAN X, ZHANG G. Solder joint reliability risk estimation by AI-assisted simulation framework with genetic algorithm to optimize the initial parameters for AI models[J]. Materials, 2021, 14(7):4835-4844.
[44] SAMAVATIAN V, FOTUHI-FIRUZABAD M. Correlation-driven machine learning for accelerated reliability assessment of solder joints in electronics[J]. Scientific Reports, 2020, 10(1):14821-14830.
[45] YUAN C, LEE C. Solder joint reliability modeling by sequential artificial neural network for glass wafer level chip scale package[J]. IEEE Access, 2020(8):143494-143501.
[46] KUNWAR A, MALLA P, SUN J, et al. Convolutional neural network model for synchrotron radiation imaging datasets to automatically detect interfacial microstructure:An in situ process monitoring tool during solar PV ribbon fabrication[J]. Solar Energy, 2021(221):230-244.
[47] ANIL K, LILI A, LIU J, et al. A data-driven framework to predict the morphology of interfacial Cu6Sn5 IMC in SAC/Cu system during laser soldering[J]. Journal of Materials Science & Technology, 2020(50):115-127.
[48] DELE-AFOLABI T, HANIM A, OIOKUPOLUYI J, et al. Interfacial IMC evolution and shear strength of MWCNTs-reinforced Sn-5Sb composite solder joints:Experimental characterization and artificial neural network modelling[J]. Journal of Materials Research and Technology-JMR&T, 2021(13):1020-1031.
[49] ANIL K, JOHAN H, SUKEHARU N, et al. Combining multi-phase field simulation with neural network analysis to unravel thermomigration accelerated growth behavior of Cu6Sn5 IMC at cold side Cu-Sn interface[J]. International Journal of Mechanical Sciences, 2020(184):105843.
[50] ANIL K, YURI C, JOHAN H, et al. Integration of machine learning with phase field method to model the electromigration induced Cu6Sn5 IMC growth at anode side Cu/Sn interface[J]. Journal of Materials Science & Technology, 2020(59):203-219.
[51] MESSINA J, LUO R, XU K, et al. Machine learning to predict aluminum segregation to magnesium grain boundaries[J]. Scripta Materialia, 2021(204):114-150.
[52] KOROLEV V, MITROFANOV A, KUCHERINENKO Y, et al. Accelerated modeling of interfacial phases in the Ni-Bi system with machine learning interatomic potential[J]. Scripta Materialia, 2020(186):14-18.