DOI QR코드

DOI QR Code

Detection of Defect Patterns on Wafer Bin Map Using Fully Convolutional Data Description (FCDD)

FCDD 기반 웨이퍼 빈 맵 상의 결함패턴 탐지

  • Seung-Jun Jang (Department of Industrial Engineering, Hanyang University) ;
  • Suk Joo Bae (Department of Industrial Engineering, Hanyang University)
  • Received : 2023.05.17
  • Accepted : 2023.06.22
  • Published : 2023.06.30

Abstract

To make semiconductor chips, a number of complex semiconductor manufacturing processes are required. Semiconductor chips that have undergone complex processes are subjected to EDS(Electrical Die Sorting) tests to check product quality, and a wafer bin map reflecting the information about the normal and defective chips is created. Defective chips found in the wafer bin map form various patterns, which are called defective patterns, and the defective patterns are a very important clue in determining the cause of defects in the process and design of semiconductors. Therefore, it is desired to automatically and quickly detect defective patterns in the field, and various methods have been proposed to detect defective patterns. Existing methods have considered simple, complex, and new defect patterns, but they had the disadvantage of being unable to provide field engineers the evidence of classification results through deep learning. It is necessary to supplement this and provide detailed information on the size, location, and patterns of the defects. In this paper, we propose an anomaly detection framework that can be explained through FCDD(Fully Convolutional Data Description) trained only with normal data to provide field engineers with details such as detection results of abnormal defect patterns, defect size, and location of defect patterns on wafer bin map. The results are analyzed using open dataset, providing prominent results of the proposed anomaly detection framework.

Keywords

Acknowledgement

This study is a research project conducted with the support of the Ministry of Trade, Industry and Energy (MOTIE) and the Korea Energy Technology Evaluation Institute (KETEP). (No. 2021202090056C, 20213030030190)

References

  1. Amari, S.-I., Backpropagation and stochastic gradient descent method, Neurocomputing, 1993, Vol. 5, pp. 185-196. https://doi.org/10.1016/0925-2312(93)90006-O
  2. Baek, S.H., Lee, C.H., and KIM, S.B., New Pattern Detection of Wafer Bin Map Using Deep-Learning, KIIE, 2021, Vol. 46, pp. 326-337. https://doi.org/10.7232/JKIIE.2020.46.3.326
  3. Buades, A., Coll, B. and Morel, J.-M., A non-local algorithm for image denoising, IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05), 2005, Vol. 2, pp. 60-65.
  4. Clevert, D.-A., Unterthiner, T., and Hochreiter, S., Fast and Accurate Deep Network Learning by Exponential Linear Units (ELUs), ICLR, 2016.
  5. Do, H., Lee, C., and Kim, S.B., A Hierarchical Spatial-Test Attention Network for Explainable Multiple Wafer Bin Maps Classification, IEEE Transactions on Semiconductor Manufacturing, 2022, Vol. 35, pp. 78-86. https://doi.org/10.1109/TSM.2021.3121006
  6. Huang, C.-J., Wu, C.-F., and Wang, C.-C., Image Processing Techniques for Wafer Defect Cluster Identification, IEEE Design & Test of Computers, 2002, Vol. 19, pp. 44-48. https://doi.org/10.1109/54.990441
  7. Hubel, D.H. and Wiesel, T.N., Receptive fields of single neurones in the cat's striate cortex, PHYSIOLOGY, 1959, Vol. 148, pp. 574-591. https://doi.org/10.1113/jphysiol.1959.sp006308
  8. Ji, Y.J., Decomposition of mixed defect pattern in wafer bin map via Grad-CAM (Gradient-Class Activation Map) [master's thesis], [Seoul, Korea]: Hanyang University, 2021.
  9. Jin, C.H., Na, H.J., Piao, M., and Pok, G., A Novel DBSCAN-Based Defect Pattern Detection and Classification Framework for Wafer Bin Map, IEEE Transactions on Semiconductor Manufacturing, 2019, Vol. 32, pp. 286-292. https://doi.org/10.1109/TSM.2019.2916835
  10. Kingma, D.P. and Ba, J.L., ADAM: A METHOD FOR STOCHASTIC OPTIMIZA TION, ICLR, 2015.
  11. Krizhevsky, A., Sutskever, I., Hinton, G.E., ImageNet Classification with Deep Convolutional Neural Networks, Neural Information Processing Systems 25 (NIPS 2012), 2012, Vol. 60, pp. 84-90. https://doi.org/10.1145/3065386
  12. LeCun, Y., Boser, B., Denker, J.S., Henderson, D., Howard, R.E., Hubbard, W., and Jackel, L.D., Backpropagation Applied to Handwritten Zip Code Recognition, Neural Computation, 1989, Vol. 1, pp. 541-551. https://doi.org/10.1162/neco.1989.1.4.541
  13. Liu, C.-W. and Chien, C.-F., An intelligent system for wafer bin map defect diagnosis: An empirical study for semiconductor manufacturing, In Engineering Applications of Artificial Intelligence, 2013, Vol. 26, pp. 1479-1486. https://doi.org/10.1016/j.engappai.2012.11.009
  14. Liznerski, P., Ruff, L., Vandermeulen, R.A., Franks, B.J., Kloft, M., and Muller, K.-R., Explainable Deep One-Class Classification, ICLR, 2021.
  15. Long, J., Shelhamer, E. and Darrell, T., Fully Convolutional Networks for Semantic Segmentation, CVPR, 2015, pp. 3431-3440.
  16. Loshchilov, I. and Hutter, F., Decoupled Weight Decay Regularization, ICLR, 2019.
  17. Luo, W., Li, Y., Urtasun, R. and Zemel, R., Understanding the Effective Receptive Field in Deep Convolutional Neural Networks, NIPS, 2016.
  18. Nair, V. and Hinton, G.E., Rectified Linear Units Improve Restricted Boltzmann Machines, ICML, 2010, pp. 807-814.
  19. Nakazawa, T. and Kulkarni, D.V., Wafer Map Defect Pattern Classification and Image Retrieval Using Convolutional Neural Network, IEEE Transactions on Semiconductor Manufacturing, 2018, Vol. 31, pp. 309-314. https://doi.org/10.1109/TSM.2018.2795466
  20. Ruff, L., Vandermeulen, R.A., Gornitz, N., Deecke, L., Siddiqui, S.A., Binder, A., Muller, E., and Kloft, M., Deep One-Class Classification, 35th International Conference on Machine Learning ICML, 2018, pp. 4393-4402.
  21. Ruff, L., Vandermeulen, R.A., Gornitz, Binder, N., A., Muiiller, E., Muller, K.-R., and Kloft, M., Deep SemiSupervised Anomaly Detection, ICLR, 2020.
  22. Ruff, L., Vandermeulen, R.A., Franks, B.J., Muller, K.-R., and Kloft, M., Rethinking Assumptions in Deep Anomaly Detection, ICML, 2021.
  23. Tax, D.M.J. and Duin, R.P.W., Support Vector Data Description, Machine Learning, 2004, pp. 45-66.
  24. Tomasi, C., Manduchi, R., Bilateral Filtering for Gray and Color Images, IEEE 6th International Conference on Computer Vision, 1998, pp. 839-846.
  25. Wang, C.-H., Separation of Composite Defect Patterns on Wafer Bin Map Using Support Vector Clustering, Expert Systems with Applications, 2009, Vol.36, pp. 2554-2561. https://doi.org/10.1016/j.eswa.2008.01.057
  26. Wang, J., Xu, C., Yang, Z., Zhang, J., and Li, X., Deformable Convolutional Networks for Efficient Mixed-Type Wafer Defect Pattern Recognition, IEEE Transactions on Semiconductor Manufacturing, 2020, Vol.33, pp. 587-596. https://doi.org/10.1109/TSM.2020.3020985
  27. Wu, M.-J., Jang, J.-S.R., Chen, J.-L., Wafer Map Failure Pattern Recognition and Similarity Ranking for Large-Scale Data Sets, IEEE Transactions on Semiconductor Manufacturing, 2015, Vol. 28, pp. 1-12. https://doi.org/10.1109/TSM.2014.2364237
  28. Xu, B., Wang, N., Chen, T. and Li, M., Empirical Evaluation of Rectified Activations in Convolution Network, arXiv:1505.