Mask defect detection with hybrid deep learning network

Abstract. Background: Deep learning is a very fast-growing field in the area of artificial intelligence with remarkable results in recent years. Many works in the lithography and photomask field have shown progress of technology in this application area and the potential to improve lithography by the automation of processes. Despite this progress, the use of machine learning techniques in the field of mask repair still seems to be at the beginning. Aim: We show that deep learning-based methods can successfully be applied to mask repair applications. Approach: The presented system is a hybrid and modular approach based on a combination of several deep learning networks and analytical methods, enabling the detection of mask pattern defects and the determination of the exact defect shapes from SEM images. In the current version, the system is trained for line/space patterns and contact patterns with typical defect types. The modularity allows for the extensibility to new use cases. The issue of an insufficient amount of training data is addressed using purely computer-generated simplified SEM data in combination with a specific network architecture. Results: The very good functionality and defect detection accuracy of the system are demonstrated with a set of real SEM images with line/space patterns and contact patterns with numerous defects. In particular, a 100% true defect detection rate could be obtained. Conclusions: The presented machine learning approach demonstrates the successful defect identification, location, and shape determination from real mask SEM images.

[1]  J. Arora,et al.  The Digital Twin , 2023, ATZ worldwide.

[2]  Yasunori Goto,et al.  Evaluation of deep learning model for 3D profiling of HAR features using high-voltage CD-SEM , 2021, Advanced Lithography.

[3]  Akira Hamaguchi,et al.  In-line schematic failure analysis technique by defect SEM images , 2021, Advanced Lithography.

[4]  Akinori Kawamura,et al.  Improvement of EPE measurement accuracy on ADI wafer, the method of using machine learning trained with CAD , 2021, Advanced Lithography.

[5]  Liangjiang Yu,et al.  Denoising sample-limited SEM images without clean data , 2021, Advanced Lithography.

[6]  Ya-Chieh Lai,et al.  Pattern similarity profiling using semi-supervised learning algorithm , 2021 .

[7]  Yayi Wei,et al.  Lithography layout classification based on graph convolution network , 2021, Advanced Lithography.

[8]  Liangjiang Yu,et al.  Defect simulation in SEM images using generative adversarial networks , 2021, Advanced Lithography.

[9]  Yayi Wei,et al.  Fast optical proximity correction based on graph convolution network , 2021, Advanced Lithography.

[10]  Elvis Yang,et al.  SRAF placement with generative adversarial network , 2021, Advanced Lithography.

[11]  Magdy A. Bayoumi,et al.  SEM image denoising with unsupervised machine learning for better defect inspection and metrology , 2021, Advanced Lithography.

[12]  Jun Yashima,et al.  A deep learning mask analysis toolset using mask SEM digital twins , 2020, Photomask Technology.

[13]  Fan Tu,et al.  High-end EUV photomask repairs for 5nm technology and beyond , 2020, Photomask Technology.

[14]  Mingyu Liu,et al.  On-machine surface defect detection using light scattering and deep learning. , 2020, Journal of the Optical Society of America. A, Optics, image science, and vision.

[15]  Yayi Wei,et al.  Fast extreme ultraviolet lithography mask near-field calculation method based on machine learning. , 2020, Applied optics.

[16]  M. Dehmer,et al.  An Introductory Review of Deep Learning for Prediction Models With Big Data , 2020, Frontiers in Artificial Intelligence.

[17]  Mohd Ibrahim Shapiai,et al.  Convolutional Neural Network for Imbalanced Data Classification of Silicon Wafer Defects , 2020, 2020 16th IEEE International Colloquium on Signal Processing & Its Applications (CSPA).

[18]  Xiaoyan Chen,et al.  A Light-Weighted CNN Model for Wafer Structural Defect Detection , 2020, IEEE Access.

[19]  Kudrov Maksim,et al.  Classification of Wafer Maps Defect Based on Deep Learning Methods With Small Amount of Data , 2019, 2019 International Conference on Engineering and Telecommunication (EnT).

[20]  Thang Nguyen,et al.  Making digital twins using the Deep Learning Kit (DLK) , 2019, Photomask Technology.

[21]  Danny Kowerko,et al.  A Novel Visual Fault Detection and Classification System for Semiconductor Manufacturing Using Stacked Hybrid Convolutional Neural Networks , 2019, 2019 24th IEEE International Conference on Emerging Technologies and Factory Automation (ETFA).

[22]  Narendra Chaudhary,et al.  Line roughness estimation and Poisson denoising in scanning electron microscope images using deep learning , 2019, Journal of Micro/Nanolithography, MEMS, and MOEMS.

[23]  Qian Xie,et al.  Machine learning based wafer defect detection , 2019, Advanced Lithography.

[24]  Tsukasa Ike,et al.  A CNN-based Transfer Learning Method for Defect Classification in Semiconductor Manufacturing , 2018, 2018 International Symposium on Semiconductor Manufacturing (ISSM).

[25]  Xiaoyu Song,et al.  Litho-Aware Machine Learning for Hotspot Detection , 2018, IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems.

[26]  Chikaaki Kodama,et al.  Subresolution Assist Feature Generation With Supervised Data Learning , 2018, IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems.

[27]  Nikolaos Doulamis,et al.  Deep Learning for Computer Vision: A Brief Review , 2018, Comput. Intell. Neurosci..

[28]  Andreas Erdmann,et al.  Advanced EUV mask and imaging modeling , 2017 .

[29]  Kilian Q. Weinberger,et al.  Densely Connected Convolutional Networks , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[30]  Maximilian Kohlbrenner,et al.  Pre-Training CNNs Using Convolutional Autoencoders , 2017 .

[31]  Jian Sun,et al.  Deep Residual Learning for Image Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[32]  Guigang Zhang,et al.  Deep Learning , 2016, Int. J. Semantic Comput..

[33]  Ioana Graur,et al.  New method of detection and classification of yield-impacting EUV mask defects , 2015, SPIE Photomask Technology.

[34]  Thomas Brox,et al.  U-Net: Convolutional Networks for Biomedical Image Segmentation , 2015, MICCAI.

[35]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[36]  Sounkalo Dembélé,et al.  Scanning electron microscope image signal-to-noise ratio monitoring for micro-nanomanipulation. , 2014, Scanning.

[37]  Yoshua Bengio,et al.  Understanding the difficulty of training deep feedforward neural networks , 2010, AISTATS.

[38]  Andreas Erdmann,et al.  Dr.LiTHO: a development and research lithography simulator , 2007, SPIE Advanced Lithography.

[39]  P. Rack,et al.  Focused, Nanoscale Electron-Beam-Induced Deposition and Etching , 2006 .

[40]  Alan R. Stivers,et al.  Advanced photolithographic mask repair using electron beams , 2005 .

[41]  Hans W. P. Koops,et al.  Electron-beam-based photomask repair , 2004 .

[42]  Tony F. Chan,et al.  Active Contours without Edges for Vector-Valued Images , 2000, J. Vis. Commun. Image Represent..

[43]  D. Joy,et al.  Advanced SEM imaging , 1998 .

[44]  L. Reimer.  Scanning Electron Microscopy: Physics of Image Formation and Microanalysis , 1984 .