基于SVR数据驱动模型的SiC功率器件关键互连结构热疲劳寿命预测研究*

doi:10.16257/j.cnki.1681-1070.2024.0162

摘要/Abstract

摘要： 烧结纳米银的互连可靠性对于SiC模块至关重要。随着人工智能与封装可靠性领域的交叉研究不断深入，发展基于数据驱动的互连可靠性评价方法已经成为该领域研究的前沿问题之一。以典型SiC互连结构为研究对象，将热疲劳寿命作为评价指标，通过综合研究芯片尺寸、烧结纳米银层尺寸和力学参数等关键因素，构建了基于支持向量回归（SVR）模型的烧结纳米银热疲劳寿命数据驱动预测模型，并对所提出的数据驱动模型进行综合量化考察和验证。通过研究关键互连参数的相关性矩阵，发现增加烧结银层厚度可以提高互连结构的寿命，而烧结银层弹性模量和SiC芯片厚度对互连可靠性有不利影响，该研究结果可用于指导SiC互连层的优化设计。

关键词: 封装技术, 功率模块, 烧结纳米银, 疲劳寿命, 机器学习

Abstract: Interconnect reliability of sintered nano silver is critical for SiC modules. With the deepening of the cross-research between artificial intelligence and packaging reliability, the development of data-driven interconnection reliability evaluation methods has become one of the forefront issues in this field. Taking the typical SiC interconnect structure as the research object, the thermal fatigue life is used as the evaluation index, and the key factors such as chip size, sintered nano silver layer size and mechanical parameters are comprehensively studied, a data-driven prediction model for thermal fatigue life of sintered nano silver based on support vector regression (SVR) model is constructed, and the proposed data-driven model is quantitatively examined and verified comprehensively. By studying the correlation matrix of key interconnect parameters, it is found that increasing the thickness of sintered silver layer can improve the life of interconnect structure, and the elastic modulus of sintered silver and the thickness of SiC chip have adverse effects on the interconnect reliability. The research results can be used to guide the optimization design of SiC interconnect layer.

Key words: packaging technology, power module, sintered nano silver, fatigue life, machine learning

中图分类号:

于鹏举, 代岩伟, 秦飞. 基于SVR数据驱动模型的SiC功率器件关键互连结构热疲劳寿命预测研究^*[J]. 电子与封装, 2024, 24(12): 120201 .

YU Pengju, DAI Yanwei, QIN Fei. Research on Thermal Fatigue Life Prediction of Key Interconnect Structures of SiC Power Devices Based on SVR Data-Driven Model[J]. Electronics & Packaging, 2024, 24(12): 120201 .

参考文献

[1] SUGIURA K, IWASHIGE T, TSURUTA K, et al. Reliability evaluation of SiC power module with sintered Ag die attach and stress-relaxation structure[J]. IEEE Transactions on Components, Packaging and Manufacturing Technology, 2019, 9(4): 609-615.
[2] CHEN C T, CHOE C, KIM D, et al. Lifetime prediction of a SiC power module by micron/submicron Ag sinter joining based on fatigue, creep and thermal properties from room temperature to high temperature[J]. Journal of Electronic Materials, 2021, 50(3): 687-698
[3] HUANG X G, WANG Y C, ZHU Q H, et al. Thermal creep and fatigue failure of the sintered silver solder in a SiC-IGBT module under power cycling[J]. Engineering Failure Analysis, 2023, 154: 107625.
[4] NING P F, LIU J, WANG D D, et al. Assessing the fatigue life of SiC power modules in different package structures[J]. IEEE Access, 2021, 9: 12074-12082.
[5] SUBBARAYAN G, LI Y, MAHAJAN R L. Reliability simulations for solder joints using stochastic finite element and artificial neural network models[J]. Journal of Electronic Packaging, 1996, 118(3): 148-156.
[6] CHOU P H, CHIANG K N, LIANG S Y. Reliability Assessment of wafer level package using artificial neural network regression model[J]. Journal of Mechanics, 2019, 35(6): 829-837.
[7] CHEN Z W, ZHANG Z, DONG F, et al. A hybrid finite element modeling: Artificial neural network approach for predicting solder joint fatigue life in wafer-level chip scale packages[J]. Journal of Electronic Packaging, 2021, 143(1): 011001.
[8] YUAN C C A, LEE C C. Solder joint reliability modeling by sequential artificial neural network for glass wafer level chip scale package[J]. IEEE Access, 2020, 8: 143494-143501.
[9] AHSAN M, HON S T, BATUNLU C, et al. Reliability assessment of IGBT through modelling and experimental testing[J]. IEEE Access, 2020, 8: 39561-39573.
[10] 代岩伟, 秦飞, 于鹏举, 等. 基于数据驱动的电子封装焊点疲劳寿命预测方法研究进展与挑战[J]. 微电子学与计算机, 2023, 40(11): 43-52.
[11] ENGELMAIER W. Fatigue life of leadless chip carrier solder joints during power cycling[J]. IEEE Transactions on Components, Hybrids, and Manufacturing Technology, 1983, 6(3): 232-237.
[12] PRAJAPATI G L, PATLE A. On performing classification using SVM with radial basis and polynomial kernel functions[C]//2010 3rd International Conference on Emerging Trends in Engineering and Technology, Goa, 2010.
[13] FUREY T S, CRISTIANINI N, DUFFY N, et al. Support vector machine classification and validation of cancer tissue samples using microarray expression data[J]. Bioinformatics, 2000, 16(10): 906-914.
[14] ZHOU Z H. Machine learning[M]. Singapore: Springer Singapore, 2021.
[15] CHANG C C, LIN C J. LIBSVM: A library for support vector machines[J]. ACM transactions on intelligent Systems and Technology (TIST), 2011, 2(3): 1-39.
[16] SU M, PENG H, YUAN M, et al. Identification of the interfacial cohesive law parameters of FRP strips externally bonded to concrete using machine learning techniques[J]. Engineering Fracture Mechanics, 2021, 247: 107643.
[17] WU J H, YANG H, ZHANG Y. The research of low temperature sintering nano-sliver paste based on Anand model[C]//Proceedings of the International Symposium on Big Data and Artificial Intelligence, Hong Kong, 2018.
[18] YU H T, QIN F, DAI Y W. Porosity effect on fatigue life of sintered silver during thermal cycling[C]//2022 23rd International Conference on Electronic Packaging Technology (ICEPT), Dalian, 2022.
[19] 陆国权, 刘文, 梅云辉. 双面散热SiC MOSFET模块的封装结构强度设计[J]. 电工电能新技术, 2018, 37(10): 32-38.
[20] CHEN G, ZHANG Z S, MEI Y H, et al. Applying viscoplastic constitutive models to predict ratcheting behavior of sintered nanosilver lap-shear joint[J]. Mechanics of Materials, 2014, 72: 61-71.
[21] CHAUHAN P, OSTERMAN M, LEE S W R, et al. Critical review of the engelmaier model for solder joint creep fatigue reliability[J]. IEEE Transactions on Components and Packaging Technologies, 2009, 32(3): 693-700.
[22] LONG X, LU C H, SU Y T, et al. Machine learning framework for predicting the low cycle fatigue life of lead-free solders[J]. Engineering Failure Analysis, 2023, 148: 107228.

中国半导体行业协会封装分会会刊

中国电子学会电子制造与封装技术分会会刊

基于SVR数据驱动模型的SiC功率器件关键互连结构热疲劳寿命预测研究^*

Research on Thermal Fatigue Life Prediction of Key Interconnect Structures of SiC Power Devices Based on SVR Data-Driven Model

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

本文评价

[1]	黄哲;郑耀庭;姚尧. Cu/SAC305/Cu焊点界面Ag和Sn扩散差异性研究^*[J]. 电子与封装, 2024, 24(9): 90205-.
[2]	王世春;沈若尧;任长友;张欣桐;武帅;邓川;王彤;郭可升;刘宏;郝志峰. 键合参数对电镀金键合性能的影响^*[J]. 电子与封装, 2024, 24(9): 90206-.
[3]	徐艳博;王志杰;刘美;孙志美;牛继勇. 铝焊盘镀钯铜丝多焊球脱焊失效的电化学评价[J]. 电子与封装, 2024, 24(8): 80205-.
[4]	张威;刘坤鹏;张沄渲;于沐瀛;王尚;田艳红. PBGA焊点形态对疲劳寿命的影响^*[J]. 电子与封装, 2024, 24(8): 80206-.
[5]	韩文静;冯春苗;刘发;袁海. 混合集成电路元器件的黏接渗胶问题研究[J]. 电子与封装, 2024, 24(8): 80207-.
[6]	张威;刘坤鹏;王宏;杭春进;王尚;田艳红. 基于能量最小化的CCGA焊点形态仿真研究^*[J]. 电子与封装, 2024, 24(8): 80208-.
[7]	孙浩洋,姬峰,冯青华,兰元飞,王建扬,王明伟. 面向快速散热的HTCC基板微流道性能研究^*[J]. 电子与封装, 2024, 24(7): 70203-.
[8]	周阳磊,吕海强,何日吉,周舟. 高温服役电子元器件的焊接工艺研究^*[J]. 电子与封装, 2024, 24(7): 70205-.
[9]	李圣贤,丁增千. 倒装芯片的底部填充工艺研究[J]. 电子与封装, 2024, 24(7): 70208-.
[10]	梁达平,赵玉祥,张进兵. 基于SECS/GEM协议的芯片烘箱设备智能故障诊断算法设计^*[J]. 电子与封装, 2024, 24(7): 70501-.
[11]	张旋,李海娟,吴道伟,张雷. 2.5D TSV转接板无损检测方法的研究[J]. 电子与封装, 2024, 24(6): 60102-.
[12]	吴鲁超,陆宇青,王珺. 硅通孔3D互连热-力可靠性的研究与展望^*[J]. 电子与封装, 2024, 24(6): 60103-.
[13]	谢勇,肖雨辰,唐会毅,王云春,侯兴哲,吴华,吴保安,谭生,孙玲. 射频组件用键合金带的研究进展^*[J]. 电子与封装, 2024, 24(5): 50201-.
[14]	梁笑笑,吴海峰. 混合集成电路的自动上芯吸嘴开发[J]. 电子与封装, 2024, 24(5): 50202-.
[15]	高杰,樊凤昕,马丹竹,建伟伟,李壮. 基于TEC和平板热管的LED散热器结构优化设计^*[J]. 电子与封装, 2024, 24(5): 50205-.