Vol. 1 No. 1 (2021): Issue 1
Articles

Wafer Defect Inspection via Unsupervised Anomaly Detection

PDF
  • Klaus Müller,
  • Anne Schmidt,
  • Peter Wagner

Published 2021-09-13

Keywords

  • Wafer,
  • Defect,
  • Inspection,
  • Anomaly,
  • Deep Learning

How to Cite

Müller, K., Schmidt, A., & Wagner, P. (2021). Wafer Defect Inspection via Unsupervised Anomaly Detection. Optimizations in Applied Machine Learning, 1(1). Retrieved from https://ojs.mri-pub.com/index.php/OAML/article/view/42
Creative Commons License

This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.

Abstract

Wafer defect inspection is crucial in ensuring the quality of semiconductor manufacturing. The current methods predominantly rely on supervised machine learning techniques, which require labeled training data and often struggle with detecting unforeseen defects. This limitation motivates the exploration of unsupervised anomaly detection methods in this research. This paper proposes a novel approach that leverages deep learning and anomaly detection algorithms to identify defects on wafers without the need for labeled data. By integrating different data sources and optimizing the anomaly detection process, our method aims to provide a more robust and efficient solution for wafer defect inspection. This work addresses the current challenges in defect detection and presents innovative strategies for improving inspection accuracy and reliability.

PDF

References

  1. C. Yan et al., "Innovative wafer defect inspection mode: self-adaptive pattern to pattern inspection," Advanced Lithography, 2024.
  2. R. Ding et al., "Structural Design and Simulation of a Multi-Channel and Dual Working Condition Wafer Defect Inspection Prototype," Micromachines, 2023.
  3. J. Zhu et al., "Optical wafer defect inspection at the 10 nm technology node and beyond," International Journal of Extreme Manufacturing, 2022.
  4. C. Liu et al., "Aperture design for a dark-field wafer defect inspection system," Applied Optics, 2021.
  5. M. Qin et al., "Wafer Defect Inspection Optimization With Partial Coverage—A Numerical Approach," IEEE Transactions on Automation Science and Engineering, 2021.
  6. Z. Shi et al., "Wafer Defect Inspection Optimization: Models, Analysis and Algorithms," Social Science Research Network, 2019.
  7. H. He et al., "MambaAD: Exploring State Space Models for Multi-class Unsupervised Anomaly Detection," arXiv.org, 2024.
  8. D. A. Gudovskiy et al., "CFLOW-AD: Real-Time Unsupervised Anomaly Detection with Localization via Conditional Normalizing Flows," IEEE Workshop/Winter Conference on Applications of Computer Vision, 2021.
  9. J. Yu1 et al., "FastFlow: Unsupervised Anomaly Detection and Localization via 2D Normalizing Flows," arXiv.org, 2021.
  10. M. Rahimi, Z. Wang, A. Shafieezadeh, D. Wood, and E. J. Kubatko, "Exploring passive and active metamodeling-based reliability analysis methods for soil slopes: a new approach to active training," International Journal of Geomechanics, 2020.
  11. X. Deng, L. Li, M. Enomoto, and Y. Kawano, ‘Continuously frequency-tuneable plasmonic structures for terahertz bio-sensing and spectroscopy’, Scientific reports, vol. 9, no. 1, p. 3498, 2019.
  12. X. Deng, M. Simanullang, and Y. Kawano, ‘Ge-core/a-si-shell nanowire-based field-effect transistor for sensitive terahertz detection’, in Photonics, MDPI, 2018, p. 13.
  13. X. Deng, S. Oda, and Y. Kawano, ‘Frequency selective, high transmission spiral terahertz plasmonic antennas’, Journal of Modeling and Simulation of Antennas and Propagation, vol. 2, pp. 1–6, 2016.
  14. Z. Wang and A. Shafieezadeh, ‘REAK: Reliability analysis through Error rate-based Adaptive Kriging’, Reliability Engineering & System Safety, vol. 182, pp. 33–45, Feb. 2019, doi: 10.1016/j.ress.2018.10.004.
  15. Z. Wang and A. Shafieezadeh, ‘ESC: an efficient error-based stopping criterion for kriging-based reliability analysis methods’, Struct Multidisc Optim, vol. 59, no. 5, Art. no. 5, May 2019, doi: 10.1007/s00158-018-2150-9.
  16. Z. Wang and A. Shafieezadeh, ‘Highly efficient Bayesian updating using metamodels: An adaptive Kriging-based approach’, Structural Safety, vol. 84, p. 101915, May 2020, doi: 10.1016/j.strusafe.2019.101915.
  17. Z. Wang and A. Shafieezadeh, ‘Confidence Intervals for Failure Probability Estimates in Adaptive Kriging-based Reliability Analysis’, Reliability Engineering & System Safety.
  18. Z. Wang and A. Shafieezadeh, ‘Real-time high-fidelity reliability updating with equality information using adaptive Kriging’, Reliability Engineering & System Safety, vol. 195, p. 106735, Mar. 2020, doi: 10.1016/j.ress.2019.106735.
  19. C. Zhang, Z. Wang, and A. Shafieezadeh, ‘Value of Information Analysis via Active Learning and Knowledge Sharing in Error-Controlled Adaptive Kriging’, IEEE Access, vol. 8, pp. 51021–51034, 2020, doi: 10.1109/ACCESS.2020.2980228.
  20. M. Rahimi, Z. Wang, A. Shafieezadeh, D. Wood, and E. J. Kubatko, ‘Exploring passive and active metamodeling-based reliability analysis methods for soil slopes: a new approach to active training’, International Journal of Geomechanics, vol. 20, no. 3, p. 04020009, 2020.