基于机器学习的芯片老化状态估计算法研究

doi:10.16257/j.cnki.1681-1070.2024.0176

电子与封装 ›› 2024, Vol. 24 ›› Issue (11): 110101 . doi: 10.16257/j.cnki.1681-1070.2024.0176

• ICTC2024（集成电路测试大会）专题 • 下一篇

基于机器学习的芯片老化状态估计算法研究

宋国栋¹，邵家康²，陈诚¹

1. 中国电子科技集团公司第五十八研究所，江苏无锡 ?214035; 2. 华中科技大学武汉集成电路学院，武汉 430074

收稿日期:2024-10-12 出版日期:2024-11-25 发布日期:2024-11-25
作者简介:宋国栋（1984—），男，硕士，高级工程师，主要从事数字和数模混合集成电路测试技术的研究。

Research on Chip Aging State Estimation Algorithm Based on Machine Learning

SONG Guodong¹, SHAO Jiakang², CHEN Cheng¹

1. ChinaElectronics Technology Group Corporation No.58 ResearchInstitute, Wuxi 214035, China; 2. School of Integrated Circuits, Huazhong University of Science and Technology, Wuhan 430074, China

Received:2024-10-12 Online:2024-11-25 Published:2024-11-25

摘要/Abstract

摘要： 随着芯片的集成度越来越高，其晶体管数量也越来越多，老化速度加快。由于工业应用、装备系统等领域对芯片可靠性的要求较高，因此研究估计芯片老化的方法至关重要。总结现有的芯片老化估计和预警的技术方法，将机器学习算法应用于芯片老化状态估计，实验结果表明，极端梯度提升树算法的效果较好。对现有的极端梯度提升树算法进行贝叶斯优化，寻找模型的最优参数，使用优化后的算法估计的状态值与真实值的均方误差比优化前降低了0.13~0.25，优化后的模型预测结果较为精准。

关键词: 芯片老化, 机器学习, 贝叶斯优化

Abstract: With the increasing integration of chips, the number of transistors is also increasing, and the aging rate is accelerating. Because of the high requirement of chip reliability in industrial applications, equipment systems and other fields, it is very important to study the method of estimating chip aging. The existing technical methods of chip aging estimation and early warning are summarized, and the machine learning algorithm is applied to chip aging state estimation. Experimental results show that the extreme gradient boosting tree algorithm has a better effect. Bayesian optimization is carried out on the existing extreme gradient boosting tree algorithm to find the optimal parameters of the model. The mean square error between the estimated state value and the true value by using the optimized algorithm is 0.13~0.25 lower than that before optimization, and the optimized model is more accurate in predicting the results.

Key words: chip aging, machine learning, Bayesian optimization

中图分类号:

TN406

宋国栋，邵家康，陈诚. 基于机器学习的芯片老化状态估计算法研究[J]. 电子与封装, 2024, 24(11): 110101 .

SONG Guodong, SHAO Jiakang, CHEN Cheng. Research on Chip Aging State Estimation Algorithm Based on Machine Learning[J]. Electronics & Packaging, 2024, 24(11): 110101 .

参考文献

[1] LOH G H, NAFFZIGER S, LEPAK K. Understanding chiplets today to anticipate future integration opportunities and limits[C/OL]//2021 Design, Automation & Test in Europe Conference & Exhibition (DATE), 2021.
[2] HESS C, INANI A, JOAG A, et al. Stackable short flow characterization vehicle test chip to reduce test chip designs, mask cost and engineering wafers[C]//2010 21st Annual IEEE/SEMI Advanced Semiconductor Manufacturing Conference (ASMC), San Francisco, 2010.
[3] KEANE J, WANG X F, PERSAUD D, et al. An all-in-one silicon odometer for separately monitoring HCI, BTI, and TDDB[J]. IEEE Journal of Solid-State Circuits, 2010, 45(4): 817-829.
[4]马俊祥, 梁华国, 李丹青, 等. 一种低开销的旁路重构RO的片上老化测量方案[J]. 微电子学, 2022, 52(6): 1090-1095.
[5] WANG T H. On-chip current measurement for multi-site electromigration monitoring[D]. Ames: Iowa State University, 2011.
[6] WOOTERS S N, CABE A C, QI Z Y, et al. Tracking on-chip age using distributed, embedded sensors[J]. IEEE Transactions on Very Large Scale Integration (VLSI) Systems, 2012, 20(11): 1974-1985.
[7] 陈朝晖, 张弛, 刘玮, 等. 一种支持SoC数字电路老化及寿命的评估方法[J]. 微电子学, 2024, 54(3): 511-516.
[8] 邢璐. 数字集成电路老化故障预测和老化监测技术研究[D]. 合肥: 合肥工业大学, 2014.
[9] JEDEC. Failure mechanisms and models for semiconductor devices: JEP122-A[S]. Arlington: JEDEC Solid-State Technology Association, 2001.
[10] WANG H, HUANG D R, LIU R, et al. STREAM: Stress and thermal aware reliability management for 3-D ICs[J]. IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems, 2019, 38(11): 2058-2071.
[11] WANG L, WANG X H, MAK T. Adaptive routing algorithms for lifetime reliability optimization in network-on-chip[J]. IEEE Transactions on Computers, 2016, 65(9): 2896-2902.
[12] HUANG L T, CHEN S Y, WU Q, et al. A lifetime-aware mapping algorithm to extend MTTF of networks-on-chip[C]//2018 23rd Asia and South Pacific Design Automation Conference (ASP-DAC), Jeju Island, 2018.
[13] 韩艳旺. 闪存控制芯片CR2511老化测试系统的设计与实现[D]. 天津: 天津大学, 2016.
[14] 陈卓. 基于SVM的NAND Flash耐久度预测方法及硬件实现[D]. 武汉: 华中科技大学, 2021.
[15] 刘玉龙, 吕权权, 吴浩, 等. 基于深度学习的电子元件焊点缺陷检测方法[J]. 电子与封装, 2023, 23(6): 060206.

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

基于机器学习的芯片老化状态估计算法研究

Research on Chip Aging State Estimation Algorithm Based on Machine Learning

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 3

编辑推荐

Metrics

本文评价

[1]	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-.
[2]	梁达平;赵利民;王鸿斌. 基于贝叶斯学习的PID温控算法在芯片烘箱中的应用^*[J]. 电子与封装, 2022, 22(8): 80202-.
[3]	张筱迪,毛明晖,卢昶衡,王文武,贾冯睿,龙旭. 基于有限元分析和机器学习的跌落所致封装结构力学行为预测[J]. 电子与封装, 2021, 21(2): 20204-.