Inspection and Classification of Semiconductor Wafer Surface Defects Using CNN Deep Learning Networks
Source abstract
Abstract
Due to advances in semiconductor processing technologies, each slice of a semiconductor is becoming denser and more complex, which can increase the number of surface defects. These defects should be caught early and correctly classified in order help identify the causes of these defects in the process and eventually help to improve the yield. In today’s semiconductor industry, visible surface defects are still being inspected manually, which may result in erroneous classification when the inspectors become tired or lose objectivity. This paper presents a vision-based machine-learning-based method to classify visible surface defects on semiconductor wafers. The proposed method uses deep learning convolutional neural networks to identify and classify four types of surface defects: center, local, random, and scrape. Experiments were performed to determine its accuracy. The experimental results showed that this method alone, without additional refinement, could reach a top accuracy in the range of 98% to 99%. Its performance in wafer-defect classification shows superior performance compared to other machine-learning methods investigated in the experiments.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Industrial Vision Systems and Defect Detection · Advanced Surface Polishing Techniques · Integrated Circuits and Semiconductor Failure Analysis
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Degree Program of Digital Space and Product Design, Kainan University, Taoyuan 33587, Taiwan
Department of Electrial Engineering, Chang Gung University, Taoyuan 33302, Taiwan
Department of Neurosurgery, Chang Gung Memorial Hospital at Linkou, Taoyuan 33305, Taiwan
Department of Electrical Engineering, Ming Chi University of Technology, New Taipei City 24301, Taiwan
Funding
Ministry of Science and Technology (MOST) , Taiwan, Republic of China
References (24)
Show source-provided references
1. Chandrasekar, K., Goossens, S., Weis, C., Koedam, M., Akesson, B., Wehn, N., and Goossens, K. (2014, January 24–28). Exploiting expendable process-margins in DRAMs for run-time performance optimization. Proceedings of the Desig, Automation & Test in Europe Conference & Exhibition, Dresden, Germany.10.7873/DATE2014.186 ↗
2. Huang, P.S., Tsai, M.Y., Huang, C.Y., Lin, P.C., Huang, L., Chang, M., Shih, S., and Lin, J. (2012, January 13–16). Warpage, stresses and KOZ of 3D TSV DRAM package during manufacturing processes. Proceedings of the 14th International Conference on Electronic Materials and Packaging (EMAP), Lantau Island, Hong Kong, China.10.1109/EMAP.2012.6507849 ↗
3. Testing Open Defects in Memristor-Based Memories10.1109/TC.2013.206 ↗
4. Guldi, R., Watts, J., Paparao, S., Catlett, D., Montgomery, J., and Saeki, T. (1998, January 23–25). Analysis and modeling of systematic and defect related yield issues during early development of a new technology. Proceedings of the Advanced Semiconductor Manufacturing Conference and Workshop, Boston, MA, USA.
5. Shen, L., and Cockburn, B. (1993, January 9–10). An optimal march test for locating faults in DRAMs. Proceedings of the 1993 IEEE International Workshop on Memory Testing, San Jose, CA, USA.
6. The binomial test: A simple tool to identify process problems10.1109/66.382280 ↗
7. Wafer Classification Using Support Vector Machines10.1109/TSM.2012.2196058 ↗
8. Wafer yield prediction using derived spatial variables10.1002/qre.2192 ↗
9. Fault Detection using Random Forest Similarity Distance10.1016/j.ifacol.2015.09.589 ↗
10. A Voting Ensemble Classifier for Wafer Map Defect Patterns Identification in Semiconductor Manufacturing10.1109/TSM.2019.2904306 ↗
11. A Light-Weighted CNN Model for Wafer Structural Defect Detection10.1109/ACCESS.2020.2970461 ↗
12. Object Detection with Deep Learning: A Review10.1109/TNNLS.2018.2876865 ↗
13. (2019, February 14). Kaggle SM-811K Wafer Map. WM-811K Wafer Map. Available online: https://www.kaggle.com/qingyi/wm811k-wafer-map.
14. A Threshold Selection Method from Gray-Level Histograms10.1109/TSMC.1979.4310076 ↗
15. Al-Saffar, A.A.M., Tao, H., and Talab, M.A. (2017, January 23–24). Review of deep convolution neural network in image classification. Proceedings of the 2017 International Conference on Radar, Antenna, Microwave, Electronics, and Telecommunications (ICRAMET), Jakarta, Indian.10.1109/ICRAMET.2017.8253139 ↗
16. A Mathematical Theory of Deep Convolutional Neural Networks for Feature Extraction10.1109/TIT.2017.2776228 ↗
17. Conceptual Understanding of Convolutional Neural Network- A Deep Learning Approach10.1016/j.procs.2018.05.069 ↗
18. Ren, S., He, K., Girshick, R., and Sun, J. (2015, January 7–12). Faster R-CNN: Towards real-time object detection with region proposal network. Proceedings of the Neural Information Processing Systems, Montreal, QC, Canada.
19. Gyanendra, V., and Anamika, D. (2017, January 24–26). A Handheld Gun Detection using Faster R-CNN Deep Learnin. Proceedings of the 7th International Conference on Computer and Communication Technology, Allahabad, India.
20. Wang, Z. (2018). Theoretical Guarantees of Transfer Learning. arXiv.
21. Coco dataset (2020, February 14). COCO-Common Objects in Context. Available online: https://cocodataset.org/.
22. Vision meets robotics: The KITTI dataset10.1177/0278364913491297 ↗
23. Tensorflow (2019, October 12). TensorFlow. Available online: https://www.tensorflow.org/.
24. He, K., Gkioxari, G., Dollár, P., and Girshick, R. (2017, January 22–29). Mask R-CNN. Proceedings of the 2017 IEEE International Conference on Computer Vision (ICCV), Venice, Italy.10.1109/ICCV.2017.322 ↗