Overview and Prospect of Virtual Metrology Technology for Manufacturing Processes
-
摘要:
“零缺陷制造”作为工业4.0的拓展,致力于大幅提升产品良率并最终实现产品零瑕疵。目前,工业过程通常采取物理检测方式对产品进行质量检验,属于离线破坏性试验且检测成本高昂,检测结果无法及时指导生产。虚拟量测通过对生产过程数据进行监控、对产品品质或工艺进行预判,能够将传统离线且具延迟特性的品质抽检改成线上且即时的品质全检。本文首先沿时间线对虚拟量测的发展历程进行了综述;随后介绍了虚拟量测的研究现状和典型应用场景,特别是半导体制造领域;接着汇总了常见的虚拟量测技术方法及其所解决的实际工程问题,比如数据预处理方法、预测建模方法和系统功能设计;最后,对制造过程虚拟量测问题进行了展望,提出了一种集数据预处理与可视化、虚拟量测和质量追溯为一体的工业制造过程智能管理体系。
Abstract:As an outgrowth of Industry 4.0, "zero-defect manufacturing" is dedicated to dramatically improving product yield and ultimately achieving zero-defect products. Presently, the manufacturing process mainly adopts the physical inspection method for product quality inspection, which is an off-line test with high detection cost and delayed guide. By monitoring production process data and predicting product quality or process, virtual metrology (VM) may transform the traditional off-line and delayed quality sampling into online and real-time quality full inspection. Firstly, we summarize the development of VM over time. Then the research status and typical application scenarios of VM, especially in semiconductor manufacturing, are introduced. Subsequently, the common VM techniques and practical engineering problems are outlined, such as data preprocessing, predictive modeling methods and system function design. Finally, we prospect the manufacturing process VM problem, and propose a manufacturing process intelligent management system, which integrates data preprocessing and visualization, VM and quality tracing.
-
Keywords:
- zero-defect manufacturing /
- product yield /
- virtual metrology
-
-
表 1 VM预测算法
Table 1 VM prediction algorithm
方法 算法 优点 限制 线性模型 多元线性回归(MLR) 复杂度低,计算效率高 线性,稳定性较差 偏最小二乘(PLS) 可解释,计算效率高,特征提取 对离群值敏感,线性,可解释性较差 Lasso 计算效率高,特征选择,可解释 线性,高相关变量性能差,若描述元数量超过观测数量则性能低 神经网络 多层感知器(MLP) 非线性,从训练集中的特征子集生成新特征 计算要求高,数据集需求大,黑盒 卷积神经网络(CNN) 非线性,特征提取,鲁棒性强 计算要求高,数据集需求大,黑盒 递归神经网络(RNN) 非线性,有时间记忆 计算要求高,数据集需求大,黑盒 贝叶斯神经网络(BNN) 非线性,因果性,先验知识 计算要求高,数据集需求大,黑盒 核方法 高斯过程回归(GPR) 非线性,计算效率高,内置不确定性量化 计算要求高,可扩展性差,难以调优,高斯性 支持向量回归(SVR) 非线性,效率高,不易过拟合 可扩展性差,难以调优 -
[1] HALPIN J F. Zero defects: A new dimension in quality assurance[M]. New York, USA: McGraw-Hill, 1966.
[2] ZHAO L P, LI B H, YAO Y Y. A novel predict-prevention quality control method of multi-stage manufacturing process towards zero defect manufacturing[J]. Advances in Manufacturing, 2023, 11(2): 280-294. doi: 10.1007/s40436-022-00427-9
[3] 阿曼德·费根堡姆, 杨文士. 全面质量管理[M]. 北京: 机械工业出版社, 1991. ARMAND V F, YANG W S. Total quality management[M]. Beijing: China Machine Press, 1991.
[4] 张璐. "中国制造2025" 背景下制造业转型升级路径选择[J]. 中国集体经济, 2021(4): 9-10. https://www.cnki.com.cn/Article/CJFDTOTAL-ZJTG202104005.htm ZHANG L. Path selection of manufacturing transformation and upgrading under the background of "Made in China 2025"[J]. China Collective Economy, 2021(4): 9-10. https://www.cnki.com.cn/Article/CJFDTOTAL-ZJTG202104005.htm
[5] 丁纯, 李君扬. 德国"工业4.0": 内容、动因与前景及其启示[J]. 德国研究, 2014(4): 49-66. https://www.cnki.com.cn/Article/CJFDTOTAL-DGYJ201404005.htm DING C, LI J Y. German "Industry 4.0": Content, motivation, prospect and enlightenment[J]. Journal of German Studies, 2014(4): 49-66. https://www.cnki.com.cn/Article/CJFDTOTAL-DGYJ201404005.htm
[6] ING C K, LIN C Y, PENG P H, et al. Golden path search algorithm for the KSA scheme[J]. IEEE Transactions on Automation Science and Engineering, 2022, 19(3): 1517-1529. doi: 10.1109/TASE.2021.3129528
[7] HUNG M H, LIN T H, CHENG F T, et al. A novel virtual metrology scheme for predicting CVD thickness in semiconductor manufacturing[J]. IEEE/ASME Transactions on Mechatronics, 2007, 12(3): 308-316. doi: 10.1109/TMECH.2007.897275
[8] WEBER A. Virtual metrology and your technology watch list: Ten things you should know about this emerging technology[J]. Future Fab International, 2007, 22(4): 52-54.
[9] CHENG F T, HUANG H C, KAO C A. Dual-phase virtual metrology scheme[J]. IEEE Transactions on Semiconductor Manufacturing, 2007, 20(4): 566-571. doi: 10.1109/TSM.2007.907633
[10] YUNG-CHENG J C, CHENG F T. Application development of virtual metrology in semiconductor industry[C/OL]//31st Annual Conference of IEEE Industrial Electronics Society. Piscataway, USA: IEEE, 2005[2022-09-06]. https://ieeexplore.ieee.org/document/1568891. DOI: 10.1109/IECON.2015.1568891.
[11] CHANG Y C, FU H S, WANG Y L, et al. Method and system for virtual metrology in semiconductor manufacturing, US20070100487[P]. 2007-05-03.
[12] GRAHAM P. Virtual technologies for advanced manufacturing and metrology[J]. International Journal of Computer Integrated Manufacturing, 2003, 16(7/8): 485-490.
[13] STANLEY K J, STANLEY T D, Maia J. Wafer fabrication: Realizing 300 mm fab productivity improvements through integrated metrology[C/OL]//Winter Simulation Conference on Winter Simulation: Exploring New Frontiers. Piscataway, USA: IEEE, 2002[2022-09-16]. https://ieeexplore.ieee.org/document/1166404. DOI: 10.1145/1030453.1030651.
[14] CHEN P H, WU S, LIN J S, et al. Virtual metrology: A solution for wafer to wafer advanced process control[C/OL]//IEEE International Symposium on Semiconductor Manufacturing. Piscataway, USA: IEEE, 2005[2022-05-30]. https://www.zhangqiaokeyan.com/academic-conference-foreign_meeting——1_thesis/020515021481.html.
[15] SU Y C, HUNG M H, CHENG F T, et al. A processing quality prognostics scheme for plasma sputtering in TFT-LCD manufacturing[J]. IEEE Transactions on Semiconductor Manufacturing, 2006, 19(2): 183-194. doi: 10.1109/TSM.2006.873514
[16] SU Y C, CHENG F T, HUNG M H, et al. Intelligent prognostics system design and implementation[J]. IEEE Transactions on Semiconductor Manufacturing, 2006, 19(2): 195-207. doi: 10.1109/TSM.2006.873512
[17] LENZ B, BARAK B, MUHRWALD J, et al. Virtual metrology in semiconductor manufacturing by means of predictive machine learning model[C/OL]//International Conference on Machine Learning & Applications. Piscataway, USA: IEEE, 2013[2022-10-19]. https://ieeexplore.ieee.org/document/6786103. DOI: 10.1109/ICMLA.2013.186.
[18] CHENG F T, HUANG H C, KAO C A. Development of a dual-phase virtual metrology scheme[C]//IEEE International Conference on Automation Science and Engineering. Piscataway, USA: IEEE, 2007: 270-275.
[19] SU Y C, TSAI W H, CHENG F T, et al. Development of a dual-stage virtual metrology architecture for TFT-LCD manufacturing[C]//2008 IEEE International Conference on Robotics and Automation. Piscataway, USA: IEEE, 2008: 3630-3635.
[20] CHENG F T, CHEN Y T, SU Y C, et al. Method for evaluating reliance level of a virtual metrology system[C]//IEEE International Conference on Robotics and Automation. Piscataway, USA: IEEE, 2007: 1590-1596.
[21] CHENG F T, CHEN Y T, SU Y C, et al. Evaluating reliance level of a virtual metrology system[J]. IEEE Transactions on Semiconductor Manufacturing, 2008, 21(1): 92-103. doi: 10.1109/TSM.2007.914373
[22] HUANG Y T, HUANG H C, CHENG F T, et al. Automatic virtual metrology system design and implementation[C]//IEEE International Conference on Automation Science and Engineering. Piscataway, USA: IEEE, 2008: 223-229.
[23] TSAI W H, CHENG F T, WU W M, et al. Developing a dual-stage indirect virtual metrology architecture[C]//IEEE International Conference on Robotics and Automation. Piscataway, USA: IEEE, 2010: 2107-2112.
[24] HUNG M H, HUANG H C, YANG H C, et al. Development of an automatic virtual metrology framework for TFT-LCD industry[C]//2010 IEEE International Conference on Automation Science and Engineering. Piscataway, USA: IEEE, 2010: 879-884.
[25] HUNG M H, CHEN C F, HUANG H C, et al. Development of an AVM system implementation framework[J]. IEEE Transactions on Semiconductor Manufacturing, 2012, 25(4): 598-613. doi: 10.1109/TSM.2012.2206061
[26] CHENG F T, CHANG Y C, KAO C A, et al. Configuring AVM as a MES component[C]//2010 IEEE/SEMI Advanced Semiconductor Manufacturing Conference. Piscataway, USA: IEEE, 2010: 226-231.
[27] CHENG F T, CHANG Y C, HUANG H C, et al. Benefit model of virtual metrology and integrating AVM into MES[J]. IEEE Transactions on Semiconductor Manufacturing, 2011, 24(2): 261-272. doi: 10.1109/TSM.2011.2104372
[28] KAO C A, CHENG F T, WU W M, et al. Preliminary study of run-to-run control utilizing virtual metrology with reliance index[C]//Automation Science & Engineering. Piscataway, USA: IEEE, 2011: 69-81.
[29] KANG P, KIM D, LEE H J, et al. Virtual metrology for run-to-run control in semiconductor manufacturing[J]. Expert Systems with Applications An International Journal, 2011, 38(3): 2508-2522. doi: 10.1016/j.eswa.2010.08.040
[30] IMAI S I. Virtual metrology for plasma particle in plasma etching equipment[C/OL]//International Symposium on Semiconductor Manufacturing. Piscataway, USA: IEEE, 2007[2022-03-07]. https://ieeexplore.ieee.org/document/4446835. DOI: 10.1109/ISSM.2007.4446835.
[31] Vitale V, Aderhold W, Hunter A, et al. Use of virtual metrology for in-situ visualization of thermal uniformity and handoff adjustment in RTP critical anneals[C]//IEEE/SEMI Advanced Semiconductor Manufacturing Conference. Piscataway, USA: IEEE, 2008: 349-353.
[32] 傅蓓芬, 曹韵, 徐宏宇. 被制裁的半导体产业: 大国底牌之争[J]. 竞争情报, 2023, 19(2): 2-12. https://www.cnki.com.cn/Article/CJFDTOTAL-JZQB202302002.htm FU B F, CAO Y, XU H Y. The sanctioned semiconductor industry: The battle of the great powers[J]. Competitive Intelligence, 2023, 19(2): 2-12. https://www.cnki.com.cn/Article/CJFDTOTAL-JZQB202302002.htm
[33] 崔圆圆. 半导体制造与工业发展[J]. 硅谷, 2011, 17: 6-7. https://www.cnki.com.cn/Article/CJFDTOTAL-GGYT201117024.htm CUI Y Y. Semiconductor manufacturing and industrial development[J]. Silicon Valley, 2011, 17: 6-7. https://www.cnki.com.cn/Article/CJFDTOTAL-GGYT201117024.htm
[34] 朱晶. 全球工业芯片产业现状及对我国工业芯片发展的建议[J]. 中国集成电路, 2021, 30(Z1): 15-19. https://www.cnki.com.cn/Article/CJFDTOTAL-JCDI2021Z1003.htm ZHU J. Current situation of global industrial chip industry and suggestions for the development of China's industrial chip[J]. China Integrated Circuits, 2021, 30(Z1): 15-19. https://www.cnki.com.cn/Article/CJFDTOTAL-JCDI2021Z1003.htm
[35] SU Y C, CHENG F T, HUANG G W, et al. A quality prognostics scheme for semiconductor and TFT-LCD manufacturing processes[C]//30th Annual Conference of IEEE on Industrial Electronics Society. Piscataway, USA: IEEE, 2004: 1972-1977.
[36] FAN S K S, CHANG X W, LIN Y Y. Product-to-product virtual metrology of color filter processes in panel industry[J]. IEEE Transactions on Automation Science and Engineering, 2022, 19(4): 3496-3507. doi: 10.1109/TASE.2021.3124157
[37] JEN C H, FAN S K S, LIN Y Y. Data-driven virtual metrology and retraining systems for color filter processes of TFT-LCD manufacturing[J]. IEEE Transactions on Instrumentation and Measurement, 2022, 71: 1-12.
[38] CHENG F T, CHIU Y C. Applying the automatic virtual metrology system to obtain tube-to-tube control in a PECVD tool[J]. IEEE Transactions on Instrumentation and Measurement, 2013, 45(6): 670-681.
[39] CAI H, FENG J, YANG Q, et al. A virtual metrology method with prediction uncertainty based on Gaussian process for chemical mechanical planarization[J/OL]. Computers in Industry, 2020, 119[2022-08-16]. https://www.semanticscholar.org/paper/103228. DOI: 10.1016/j.compind.2020.103228.
[40] CAI H S, FENG J S, YANG Q B, et al. Reference-based virtual metrology method with uncertainty evaluation for material removal rate prediction based on Gaussian process regression[J]. International Journal of Advanced Manufacturing Technology, 2021, 116(3/4): 1199-1211.
[41] ZHANG F Z, JIANG W L, WANG H G. Virtual metrology for semiconductor chemical mechanical planarization process using wide & deep learning[C]//10th International Conference on Computing and Pattern Recognition. New York, USA: ACM, 2021: 345-349.
[42] CAI H S, FENG J S, ZHU F, et al. Adaptive virtual metrology method based on just-in-time reference and particle filter for semiconductor manufacturing[J/OL]. Measurement, 2022, 168[2022-11-02]. http://www.sciencedirect.com/science/article/pii/S0263224120308757. DOI: 10.1016/j.measurement.2020.108338.
[43] KIM B, PARK K. Modeling plasma etching process using a radial basis function network[J]. Microelectronic Engineering, 2005, 77(2): 150-157. doi: 10.1016/j.mee.2004.09.009
[44] HAN D, MOON S B. Modelling of plasma etching process using radial basis function network and genetic algorithm[J]. Vacuum, 2005, 79(3): 140-147.
[45] ZENG D K, SPANOS C J. Virtual metrology modeling for plasma etch operations[J]. IEEE Transactions on Semiconductor Manufacturing, 2009, 22(4): 419-443. doi: 10.1109/TSM.2009.2031750
[46] LYNN S, RINGWOOD J, RAGNOLI E, et al. Virtual metrology for plasma etch using tool variables[C]//2009 IEEE/SEMI Advanced Semiconductor Manufacturing Conference. Piscataway, USA: IEEE, 2009: 143-148.
[47] ZENG D K, SPANOS C J. Estimation and control in semiconductor etch: Practice and possibilities[J]. IEEE Transactions on Semiconductor Manufacturing, 2010, 23(1): 87-98. doi: 10.1109/TSM.2009.2039250
[48] LYNN S, RINGWOOD J V, MACGEARAILT N. Weighted windowed PLS models for virtual metrology of an industrial plasma etch process[C]//2010 IEEE International Conference on Industrial Technology. Piscataway, USA: IEEE, 2010: 309-314.
[49] LYNN S, RINGWOOD J V, MACGEARAILT N. Global and local virtual metrology models for a plasma etch process[J]. IEEE Transactions on Semiconductor Manufacturing, 2012, 25(1): 94-103. doi: 10.1109/TSM.2011.2176759
[50] LYNN S A, MACGEARAILT N, RINGWOOD J V. Real-time virtual metrology and control for plasma etch[J]. Journal of Process Control, 2012, 22(4): 666-676. doi: 10.1016/j.jprocont.2012.01.012
[51] MONAHAN K M. Enabling DFM and APC strategies at the 32 nm technology node[C/OL]//IEEE International Symposium onSemiconductor Manufacturing. Piscataway, USA: IEEE, 2005[2022-03-10]. https://ieeexplore.ieee.org/document/1513388.
[52] KHAN A A, MOYNE J R, TILBURY D M. An approach for factory-wide control utilizing virtual metrology[J]. IEEE Transactions on Semiconductor Manufacturing, 2007, 20(4): 364-375. doi: 10.1109/TSM.2007.907609
[53] KHAN A A. Predictive inspection based control using diagnostic data for manufacturing processes[D]. Ann Arbor, USA: University of Michigan, 2007.
[54] KHAN A A, MOYNE J R, TILBURY D M. Virtual metrology and feedback control for semiconductor manufacturing process using recursive partial least squares[J]. Journal of Process Control, 2008, 18(10): 961-974. doi: 10.1016/j.jprocont.2008.04.014
[55] MOYNE J, SCHULZE B. Yield management enhanced advanced process control system (YMeAPC): Part I. Description and case study of feedback for optimized multi process control[J]. IEEE Transactions on Semiconductor Manufacturing, 2010, 23(2): 221-235. doi: 10.1109/TSM.2010.2041294
[56] PAN T H, SHENG B Q, WONG S H, et al. A virtual metrology system for predicting end-of-line electrical properties using a MANCOVA model with tools clustering[J]. IEEE Transactions on Industrial Informatics, 2011, 7(2): 187-195. doi: 10.1109/TII.2010.2098416
[57] ROEDER G, WINZER S, SCHELLENBERGER M, et al. Feasibility evaluation of virtual metrology for the example of a trench etch process[J]. IEEE Transactions on Semiconductor Manufacturing, 2014, 27(3): 327-334. doi: 10.1109/TSM.2014.2321192
[58] HUANG H C, SU Y C, CHENG F T, et al. Development of a generic virtual metrology framework[C]//2007 IEEE International Conference on Automation Science and Engineering. Piscataway, USA: IEEE, 2007: 282-287.
[59] HSIEH Y M, LU R, LU J W, et al. Automated classification scheme plus AVM for wafer sawing processes[J]. IEEE Robotics and Automation Letters, 2020, 5(3): 4525-4532. doi: 10.1109/LRA.2020.3000678
[60] IMAI S I, KITABATA M. Prevention of copper interconnection failure in system on chip using virtual metrology[J]. IEEE Transactions on Semiconductor Manufacturing, 2009, 22(4): 432-437. doi: 10.1109/TSM.2009.2031757
[61] LIN L R, CHIU Y C, MO W C, et al. Run-to-run control utilizing the AVM system in the solar industry[C]//International Symposium on Semiconductor Manufacturing/e-Manufacturing and Design Collaboration Symposium. Piscataway, USA, IEEE, 2011: 1-33.
[62] TANAKA T, YASUDA S. Prediction and control of transistor threshold voltage by virtual metrology (virtual PCM) using equipment data[J]. IEEE Transactions on Semiconductor Manufacturing, 2013, 26(3): 339-343. doi: 10.1109/TSM.2013.2269147
[63] YANG H C, TIENG H, CHENG F T. Automatic virtual metrology for wheel machining automation[J]. International Journal of Production Research, 2016, 54(21): 6367-6377. doi: 10.1080/00207543.2015.1109724
[64] TIENG H, TSAI T H, CHEN C F, et al. Automatic virtual metrology and deformation fusion scheme for engine-case manufacturing[J]. IEEE Robotics and Automation Letters, 2018, 3(2): 934-941. doi: 10.1109/LRA.2018.2792690
[65] YANG H C, ADNAN M, HUANG C H, et al. An intelligent metrology architecture with AVM for metal additive manufacturing[J]. IEEE Robotics and Automation Letters, 2019, 4(3): 2886-2893. doi: 10.1109/LRA.2019.2921927
[66] HSIEH Y M, LIN C Y, YANG Y R, et al. Automatic virtual metrology for carbon fiber manufacturing[J]. IEEE Robotics and Automation Letters, 2019, 4(3): 2730-2737. doi: 10.1109/LRA.2019.2917384
[67] LIM D J, KIM S J, HWANG U J, et al, Development of a virtual metrology system for smart manufacturing: A case study of spandex fiber production[J/OL]. Computers in Industry, 2023, 145[2022-12-09]. https://www.sciencedirect.com/science/article/abs/pii/S0166361522002214. DOI: 10.1016/j.compind.2022.103825.
[68] YEH L, CHEN R. Virtual metrology of visualizing copper microstructure featured with computer vision and artificial neural network[C]//2021 IEEE International Symposium on the Physical and Failure Analysis of Integrated Circuits. Piscataway, USA: IEEE, 2021: 1-5.
[69] TIENG H, YANG H C, HUNG M H, et al. A novel virtual metrology scheme for predicting machining precision of machine tools[C]//2013 IEEE International Conference on Robotics and Automation. Piscataway, USA: IEEE, 2013: 264-269.
[70] HUNG M H, LIN Y C, HUANG H C, et al. Development of an advanced manufacturing cloud for machine tool industry based on AVM technology[C]//2013 IEEE International Conference on Automation Science and Engineering. Piscataway, USA: IEEE, 2013: 189-194.
[71] CHEN C C, LIN Y C, HUNG M H, et al. Development of auto-scaling cloud manufacturing framework for machine tool industry[C]//IEEE International Conference on Automation Science and Engineering. Piscataway, USA: IEEE, 2014: 893-898.
[72] TIENG H, YANG H C, CHENG F T. Total precision inspection of machine tools with virtual metrology[J]. Journal of the Chinese Institute of Engineers, 2016, 39(2): 221-235. doi: 10.1080/02533839.2015.1091279
[73] HUANG Y T, CHENG F T, SHIH Y H, et al. Advanced ART2 scheme for enhancing metrology-data-quality evaluation[J]. Journal of the Chinese Institute of Engineers, 2014, 37(8): 1064-1079. doi: 10.1080/02533839.2014.912773
[74] CHENG F T, TIENG H, YANG H C, et al. Industry 4.1 for wheel machining automation[J]. IEEE Robotics and Automation Letters, 2016, 1(1): 332-339. doi: 10.1109/LRA.2016.2517208
[75] CHOU P H, WU M J, CHEN K K. Integrating support vector machine and genetic algorithm to implement dynamic wafer quality prediction system[J]. Expert Systems with Applications, 2010, 37(6): 4413-4424. doi: 10.1016/j.eswa.2009.11.087
[76] KANG P, KIM D, CHO S Z. Evaluating the reliability level of virtual metrology results for flexible process control: A novelty detection based approach[J]. Pattern Analysis and Applications, 2014, 17(4): 863-881. doi: 10.1007/s10044-014-0386-6
[77] KIM D, KANG P, LEE S K, et al. Improvement of virtual metrology performance by removing metrology noises in a training dataset[J]. Pattern Analysis & Applications, 2015, 18(1): 173-189.
[78] HUANG Y T, CHENG F T. Automatic data quality evaluation for the AVM system[J]. IEEE Transactions on Semiconductor Manufacturing, 2011, 24(3): 445-454. doi: 10.1109/TSM.2011.2154910
[79] 蔡剑华, 王先春. 基于形态小波去噪的齿轮故障诊断[J]. 机械强度, 2015, 179(3): 398-402. doi: 10.16579/j.issn.1001.9669.2015.03.020 CAI J H, WANG X C. Gear fault diagnosis based on morphological wavelet denoising[J]. Journal of Mechanical Strength, 2015, 179(3): 398-402. doi: 10.16579/j.issn.1001.9669.2015.03.020
[80] 吴伟, 蔡培升. 基于MATLAB的小波去噪仿真[J]. 信息与电子工程, 2008, 6(3): 220-222. doi: 10.3969/j.issn.1672-2892.2008.03.014 WU W, CAI P S. Wavelet denoising simulation based on MATLAB[J]. Information and Electronic Engineering, 2008, 6(3): 220-222. doi: 10.3969/j.issn.1672-2892.2008.03.014
[81] TIENG H, CHEN C F, CHENG F T, et al. Automatic virtual metrology and target value adjustment for mass customization[J]. IEEE Robotics and Automation Letters, 2017, 2(2): 546-553. doi: 10.1109/LRA.2016.2645507
[82] PARK S, SEONG J, JANG Y, et al. Plasma information-based virtual metrology (PI-VM) and mass production process control[J]. Journal of the Korean Physical Society, 2022, 80(8): 647-669. doi: 10.1007/s40042-022-00452-8
[83] KWON J, RYU S, PARK J, et al. Development of virtual metrology using plasma information variables to predict Si etch profile processed by SF6/O2/Ar capacitively coupled plasma[J]. Materials, 2021, 14(11): 3005-3011. doi: 10.3390/ma14113005
[84] CHOI J E, PARK H, LEE Y, et al. Virtual metrology for etch profile in silicon trench etching with SF6/O2/Ar plasma[J]. IEEE Transactions on Semiconductor Manufacturing, 2011, 35(1): 128-136.
[85] CHIEN K C, CHANG C H, DJURDJANOVIC D. Virtual metrology modeling of reactive ion etching based on statistics-based and dynamics-inspired spectral features[J/OL]. Journal of Vacuum Science and Technology B, 2021, 39(6)[2023-02-16]. https://pubs.aip.org/avs/jvb/article/39/6/064003/590733/Virtual-metrology-modeling-of-reactive-ion-etching?searchresult=1. DOI: 10.1116/6.0001277.
[86] RIZOPOULOS D. Applied predictive modeling[J]. BIOMETRICS, 2018, 74(1): 383-383.
[87] KIM D, KANG S. Effect of irrelevant variables on faulty wafer detection in semiconductor manufacturing[J/OL]. Energies, 2019, 12(13)[2022-11-20]. https://www.mdpi.com/1996-1073/12/13/2530. DOI: 10.3390/en12132530.
[88] LIN T H, CHENG F T, YE A J, et al. A novel key-variable sifting algorithm for virtual metrology[C]//IEEE International Conference on Robotics and Automation. Piscataway, USA: IEEE, 2008: 3636-3641.
[89] LIN T H, CHENG F T, WU W M, et al. NN-based key-variable selection method for enhancing virtual metrology accuracy[J]. IEEE Transactions on Semiconductor Manufacturing, 2009, 22(1): 204-211. doi: 10.1109/TSM.2008.2011185
[90] WU W M, CHENG F T, ZENG D L, et al. Developing a selection scheme for dual virtual-metrology outputs[C]//2008 IEEE International Conference on Automation Science and Engineering. Piscataway, USA: IEEE, 2008: 230-235.
[91] WU W M, CHENG F T, LIN T H, et al. Selection schemes of dual virtual-metrology outputs for enhancing prediction accuracy[J]. IEEE Transactions on Automation Science & Engineering, 2011, 8(2): 311-318.
[92] WU W M, CHENG F T, KONG F W. Dynamic-moving-window scheme for virtual-metrology model refreshing[J]. IEEE Transactions on Semiconductor Manufacturing, 2012, 25(2): 238-246. doi: 10.1109/TSM.2012.2183398
[93] DJEDIDI O, CLAIN R, BORODIN V, et al. Feature selection for virtual metrology modeling: An application to chemical mechanical polishing[C]//33rd Annual SEMI Advanced Semiconductor Manufacturing Conference. Berlin, Germnay: Springer, 2022: 1121-1126.
[94] KORABI T E, BORODIN V, JUGE M, et al. A hybrid feature selection approach for virtual metrology: Application to CMP process[J/OL]. Computers in Industry, 2022, 135[2023-03-09]. https://www.sciencedirect.com/science/article/abs/pii/S0166361521001792. DOI: 10.1016/j.compind.2021.103572.
[95] CHEN C F, CHENG F T, WU C C, et al. Preliminary study of an intelligent sampling decision scheme for the AVM system[C]//IEEE International Conference on Robotics and Automation. Piscataway, USA: IEEE, 2014: 3496-3501.
[96] SHIM J, KANG S, CHO S. Active inspection for cost-effective fault prediction in manufacturing process[J]. Journal of Process Control, 2021, 105: 250-258. doi: 10.1016/j.jprocont.2021.08.008
[97] SHIM J, KANG S. Domain-adaptive active learning for cost-effective virtual metrology modeling[J/OL]. Computers in Industry, 2022, 135[2023-03-09]. https://www.sciencedirect.com/science/article/abs/pii/S0166361521001792. DOI: 10.1016/j.compind.2021.103572.
[98] CHENG F T, CHEN C F, HSIEH Y S, et al. Intelligent sampling decision scheme based on the AVM system[J]. International Journal of Production Research, 2015, 53(7): 2073-2088. doi: 10.1080/00207543.2014.955924
[99] HSIEH Y S, CHENG F T, CHEN C F, et al. Dynamic ISD scheme for the AVM system-A preliminary study[C]//IEEE International Conference on Robotics and Automation. Piscataway, USA: IEEE, 2015: 2060-2065.
[100] CHENG F T, HSIEH Y S, CHEN C F, et al. Automated sampling decision scheme for the AVM system[J]. International Journal of Production Research, 2016, 54(21): 6351-6366. doi: 10.1080/00207543.2015.1072649
[101] KURZ D, DE LUCA C, PILZ J. A sampling decision system for virtual metrology in semiconductor manufacturing[J]. IEEE Transactions on Automation Science and Engineering, 2014, 12(1): 75-83.
[102] TIN T C, TAN S C, YONG H, et al. The implementation of a smart sampling scheme C2O utilizing virtual metrology in semiconductor manufacturing[J]. IEEE Access, 2021, 9: 114255-114266. doi: 10.1109/ACCESS.2021.3103235
[103] NGUYEN C, LI X, BLANTON S, et al. Efficient classification via partial co-training for virtual metrology[C]//25th IEEE International Conference on Emerging Technologies and Factory Automation. Piscataway, USA: IEEE, 2020: 753-760.
[104] YUAN X F, JIA Z Z, LIN L, et al. A SIA-LSTM based virtual metrology for quality variables in irregular sampled time sequence of industrial processes[J/OL]. Chemical Engineering Science, 2022, 249[2023-08-06]. https://www.sciencedirect.com/science/article/abs/pii/S0009250921008642. DOI: 10.1016/j.ces.2021.117299.
[105] LEE K B, CHEON S, KIM C O. A convolutional neural network for fault classification and diagnosis in semiconductor manufacturing processes[J]. IEEE Transactions on Semiconductor Manufacturing, 2017, 30(2): 135-142. doi: 10.1109/TSM.2017.2676245
[106] WEN G, GAO Z, CAI Q, et al. A novel method based on deep convolutional neural networks for wafer semiconductor surface defect inspection[J]. IEEE Transactions on Instrumentation and Measurement, 2020. 69(12): 9668-9680. doi: 10.1109/TIM.2020.3007292
[107] MAGGIPINTO M, TERZI M, MASIERO C, et al. A computer vision-inspired deep learning architecture for virtual metrology modeling with 2-dimensional data[J]. IEEE Transactions on Semiconductor Manufacturing, 2018, 31(3): 376-384. doi: 10.1109/TSM.2018.2849206
[108] SAQLAIN M, ABBAS Q, LEE J Y. A deep convolutional neural network for wafer defect identification on an imbalanced dataset in semiconductor manufacturing processes[J]. IEEE Transactions on Semiconductor Manufacturing, 2020, 33(3): 436-444. doi: 10.1109/TSM.2020.2994357
[109] SHAO H C, PENG C Y, WU J R, et al. From IC layout to die photograph: A CNN-based data driven approach[J]. IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems, 2021, 40(5): 957-970. doi: 10.1109/TCAD.2020.3015469
[110] LIN T H, HUNG M H, LIN R C, et al. A virtual metrology scheme for predicting CVD thickness in semiconductor manufacturing[C]//IEEE International Conference on Robotics and Automation. Piscataway, USA: IEEE, 2006: 1054-1059.
[111] SU Y C, LIN T H, CHENG F T, et al. Implementation considerations of various virtual metrology algorithms[C]//IEEE International Conference on Automation Science and Engineering. Piscataway, USA: IEEE, 2007: 276-281.
[112] SU Y C, LIN T H, CHENG F T, et al. Accuracy and real-time considerations for implementing various virtual metrology algorithms[J]. IEEE Transactions on Semiconductor Manufacturing, 2008, 21(3): 426-437. doi: 10.1109/TSM.2008.2001219
[113] SUSTO G A, PAMPURI S, SCHIRRU A, et al. Multi-step virtual metrology for semiconductor manufacturing: A multilevel and regularization methods-based approach[J]. Computers & Operations Research, 2015, 53: 328-337.
[114] HSIEH Y M, WANG T J, LIN C Y, et al. Convolutional neural networks for automatic virtual metrology[J]. IEEE Robotics and Automation Letters, 2021, 6(3): 5720-5727. doi: 10.1109/LRA.2021.3084882
[115] TIN T C, TAN S C, LEE C K. Virtual metrology in semiconductor fabrication foundry using deep learning neural networks[J]. IEEE Access, 2022, 10: 81960-81973. doi: 10.1109/ACCESS.2022.3193783
[116] CLAIN R, BORODIN V, JUGE M, et al. Virtual metrology for semiconductor manufacturing: Focus on transfer learning[C]//IEEE International Conference on Automation Science and Engineering. Piscataway, USA: IEEE, 2021: 1621-1626.
[117] HSIEH Y M, WANG T J, LIN C Y, et al. Convolutional autoencoder and transfer learning for automatic virtual metrology[J]. IEEE Robotics and Automation Letters, 2022, 7(3): 8423-8430. doi: 10.1109/LRA.2022.3187617
[118] CHOI J, JEONG M K. Deep autoencoder with clipping fusion regularization on multistep process signals for virtual metrology[J]. IEEE Sensors Letters, 2019, 3(1): 1-4.
[119] NIU S, LIU Y, WANG J, et al. A decade survey of transfer learning (2010-2020)[J]. IEEE Transactions on Artificial Intelligence, 2020, 1(2): 151-166. doi: 10.1109/TAI.2021.3054609
[120] LANG C I, SUN F K, VEERASINGAM R, et al. Understanding and improving virtual metrology systems using Bayesian methods[J]. IEEE Transactions on Semiconductor Manufacturing, 2022, 35(3): 511-521. doi: 10.1109/TSM.2022.3170270
[121] NGUYEN C, LI X, BLANTON S, et al. Correlated Bayesian co-training for virtual metrology[J]. IEEE Transactions on Semiconductor Manufacturing, 2023, 36(1): 28-36. doi: 10.1109/TSM.2022.3217350
[122] ZHOU T. Virtual metrology of WAT value with machine learning based method[C]//China Semiconductor Technology International Conference. Piscataway, USA: IEEE, 2022: 112-113.
[123] CHEN C H, ZHAO W D, PANG T, et al. Virtual metrology of semiconductor PVD process based on combination of tree-based ensemble model[J]. ISA Transactions, 2020, 103: 192-202. doi: 10.1016/j.isatra.2020.03.031
[124] HUNG M H, TSAI W H, YANG H C, et al. A novel automatic virtual metrology system architecture for TFT-LCD industry based on main memory database[J]. Robotics and Computer Integrated Manufacturing, 2012, 28(4): 559-568. doi: 10.1016/j.rcim.2012.01.002
[125] YANG W, BLUE J, ROUSSY A, et al. A structure data driven framework for virtual metrology modeling[J]. IEEE Transactions on Automation Science and Engineering, 2020, 17(3): 1297-1306.
[126] SCHUELER S, HARTIG C, TORRES A, et al. Virtual metrology: How to build the bridge between the different data sources[C/OL]//Metrology, Inspection, and Process Control for Semicorductor Manufacting. San Francisco, USA: SPIE, 2021[2022-08-09]. https://www.spiedigitallibrary.org/conference-proceedings-of-spie/11611/2588467/Virtual-metrology——how-to-build-the-bridge-between-the/10.1117/12.2588467.short?SSO=1. DOI: 10.1117/12.2588467.
[127] XU H W, QIN W, LV Y L, et al. Data-driven adaptive virtual metrology for yield prediction in multibatch wafers[J]. IEEE Transactions on Industrial Informatics, 2022, 18(12): 9008-9016. doi: 10.1109/TII.2022.3162268
[128] HUNG M H, CHEN C F, LIN Y C, et al. Refinement of kernel and functional mechanisms for automatic virtual metrology system[C]//IEEE/ASME International Conference on Advanced Intelligent Mechatronics. Piscataway, USA: IEEE, 2012: 472-477.
[129] 吴小菲. 半导体生产过程虚拟量测与过程监控研究[D]. 杭州: 浙江大学, 2021. WU X F. Research on virtual metrology and process monitoring of semiconductor production process[D]. Hangzhou: Zhejiang University, 2021.
[130] KAO C A, CHENG F T, WU W M, et al. Run-to-run control utilizing virtual metrology with reliance index[J]. IEEE Transactions on Semiconductor Manufacturing, 2013, 26(1): 69-81. doi: 10.1109/TSM.2012.2228243
[131] YANG H C, TIENG H, LI Y Y, et al. A virtual-metrology-based machining state conjecture system[C]//IEEE/ASME International Conference on Advanced Intelligent Mechatronics. Piscataway, USA: IEEE, 2012: 462-466.
[132] HSIEH Y S, CHENG F T, YANG H C. Virtual-metrology-based FDC scheme[C]//IEEE International Conference on Automation Science and Engineering. Piscataway, USA: IEEE, 2012: 80-85.
[133] HSIEH Y S, CHENG F T, HUANG H C, et al. VM-based baseline predictive maintenance scheme[J]. IEEE Transactions on Semiconductor Manufacturing, 2013, 26(1): 132-144. doi: 10.1109/TSM.2012.2218837
[134] FAN S, CHANG Y J. An integrated advanced process control framework using run-to-run control, virtual metrology and fault detection[J]. Journal of Process Control, 2013, 23(7): 933-942. doi: 10.1016/j.jprocont.2013.03.013
[135] DRATH R, HORCH A. Industry 4.0: Hit or hype?[J]. IEEE Industrial Electronics Magazine, 2014, 8(2): 56-58. doi: 10.1109/MIE.2014.2312079
[136] JAMES T. Smart factories[J]. Engineering & Technology, 2012, 7(6): 64-67.
[137] HUNG M H, LIN Y C, HUANG H C, et al. Development of a private cloud-based new-generation virtual metrology system[C]//IEEE International Conference on Automation Science and Engineering. Piscataway, USA: IEEE, 2014: 910-915.
[138] HUANG H, LIN Y, HUNG M, et al. Development of cloud-based automatic virtual metrology system for semiconductor industry[J]. Robotics and Computer-Integrated Manufacturing, 2015, 34: 30-43. doi: 10.1016/j.rcim.2015.01.005
[139] HUNG M H, LI Y Y, LIN Y C, et al. Development of a novel cloud-based multi-tenant model creation service for automatic virtual metrology[J]. Robotics and Computer-Integrated Manufacturing, 2017, 44: 174-189. doi: 10.1016/j.rcim.2016.09.003
[140] LIN Y C, HUNG M H, HUANG H C, et al. Development of advanced manufacturing cloud of things (AMCoT)-A smart manufacturing platform[J]. IEEE Robotics and Automation Letters, 2017, 2(3): 1809-1816. doi: 10.1109/LRA.2017.2706859