Topology-Guided Deep Clustering of Wafer Defect Patterns
Keywords:
Semiconductor wafer inspection; defect pattern clustering; development and manufacturing of integrated circuits; supervised learning; convolutional neural networks; topological data analysis; decisionsupport; structural heat-damping composite materials; lab-scale manufacture; controlled heat-damping properties.Abstract
Semiconductor wafers undergo regular pattern inspections that are essential for assessing production quality. Recent years have seen the rise of deep-learning techniques for automating pattern recognition. They remain underexplored, however, for specific inspection tasks such as clustering similar defect patterns. TDA-based methods have been proposed that utilize TDA to delimit defect patterns and a Gaussian mixture model to perform clustering. A deep neural network is leveraged for the underlying representation learning. A recent dataset of defect pattern images is explored to enable better recognition of such inspections. Results indicate that the method outperforms several baseline methods in clustering accuracy across multiple scenes.
Semiconductors perform information acquisition, processing, transmission, and control, and are called the “brain” of electronics. They experience regular pattern inspections at each phase of the manufacturing process, with the inspection results serving as important references for process evaluation and control. Take wafer patterns as an example: if a pattern has serious defects, it cannot be used in subsequent manufacturing processes and must be discarded. Therefore, fast and effective inspection of wafer patterns is important for determining product quality. Recently, deep-learning techniques have been introduced to automate the process of inspection pattern recognition. These tools have been successfully applied in many fields, but they have not yet been fully applied to specific semiconductor inspection tasks such as clustering the same type of defects. TDA-based methods have been proposed that first employ TDA to delimit defect patterns and then a Gaussian mixture model to perform clustering on the defect patterns for a given annealing result.
References
1. Wang, R., & Chen, N. (2020). Defect pattern recognition on wafers using convolutional neural networks. Quality and Reliability Engineering International, 36(4), 1245–1257.
2. Kang, S. (2020). Rotation-invariant wafer map pattern classification with convolutional neural networks. IEEE Access, 8, 170650–170658.
3. Mangalampalli, B. M., Bandi, V. D. V. K., Kolla, S. K., & Kumar, M. V. K. (2025). Towards Self-Evolving Healthcare Intelligence: Integrating Advanced Learning Systems with Real-Time Clinical Data Pipelines. Cultura: International Journal of Philosophy of Culture and Axiology, 22(12s), 464-486.
4. Jin, C. H., Kim, H.-J., Piao, Y., Li, M., & Piao, M. (2020). Wafer map defect pattern classification based on convolutional neural network features and error-correcting output codes. Journal of Intelligent Manufacturing, 31(8), 1861–1875.
5. Wang, J., Xu, C., Yang, Z., Zhang, J., & others. (2020). Deformable convolutional networks for efficient mixed-type wafer defect pattern recognition. IEEE Transactions on Semiconductor Manufacturing, 33(4), 587–596.
6. Mattaparthi, R. (2025). GenAI-Augmented Diagnostic Reasoning for Diesel Engine Fault Triage: A Large Language Model Framework for Technician Decision Support at Scale. Journal of Material Sciences & Manufacturing Research, 6(12), 1.
7. Batool, U., Shapiai, M. I., Fauzi, H., & Fong, S. (2020). Convolutional neural network for imbalanced data classification of silicon wafer defects. In Proceedings of the 2020 16th IEEE International Colloquium on Signal Processing & Its Applications, 230–235.
8. Koo, J., & Hwang, S. (2021). A unified defect pattern analysis of wafer maps using density-based clustering. IEEE Access, 9, 78873–78882.
9. Mahadevan, S. (2025). DRIVING SUSTAINABILITY IN AUTO & MANUFACTURING SECTORS: THE ROLE OF CLOUD-BASED SERVERLESS AUTOMATION FOR ERP SYSTEMS. International Journal of Applied Mathematics, 38(7s), 1813-1825.
10. Shim, J., Kang, S., & Cho, S. (2021). Active cluster annotation for wafer map pattern classification in semiconductor manufacturing. Expert Systems with Applications, 183, Article 115429.
11. Kang, H., & Kang, S. (2021). A stacking ensemble classifier with handcrafted and convolutional features for wafer map pattern classification. Computers in Industry, 129, Article 103450.
12. Wang, F.-K., Chou, J.-H., & Amogne, Z. E. (2022). A deep convolutional neural network with residual blocks for wafer map defect pattern recognition. Quality and Reliability Engineering International, 38(1), 343–357.
13. Loganathan, R. (2025). AGENTIC AI FRAMEWORKS FOR AUTONOMOUS RISK DETECTION AND COMPLIANCE REMEDIATION IN ENTERPRISE DATA CENTER OPERATIONS. Lex Localis-Journal of Local Self-Government, 23 (S6), 9672–9697.
14. Cha, J., & Jeong, J. (2022). Improved U-Net with residual attention block for mixed-defect wafer maps. Applied Sciences, 12(4), 2209.
15. Chen, S., Zhang, Y., Hou, X., Shang, Y., & Yang, P. (2022). Wafer map failure pattern recognition based on deep convolutional neural network. Expert Systems with Applications, 209, Article 118254.
16. Yu, N. (2022). Wafer map defect patterns classification based on a lightweight network and data augmentation. CAAI Transactions on Intelligence Technology.
17. Mangalampalli, B. M., Kolla, S. K., Bandi, V. D. V. K., Yandamuri, U. S., & Rani, P. S. (2025). Designing Intelligent Healthcare Ecosystems through Adaptive Data Integration and Autonomous Learning Systems. Vascular and Endovascular Review, 8(20s), 330-347.
18. Nag, S., et al. (2022). WaferSegClassNet: A light-weight network for classification and segmentation of semiconductor wafer defects. Computers in Industry, 140, Article 103720.
19. Kim, T., & Behdinan, K. (2022). Advances in machine learning and deep learning applications towards wafer map defect recognition and classification: A review. Journal of Intelligent Manufacturing.
20. Shim, J., & Kang, S. (2023). Learning from single-defect wafer maps to classify mixed-defect wafer maps. Expert Systems with Applications, 233, Article 120923.
21. Kolla, S. H., & Mangala, N. (2025). DESIGNING AUTONOMOUS LLM AGENT FRAMEWORKS USING GEN AI PIPELINES TO ENHANCE CUSTOMER SERVICE MANAGEMENT AND KNOWLEDGE WORKFLOWS. Lex Localis-Journal of Local Self-Government, 23, 9719-9733.
22. Ko, S., & Koo, D. (2023). A novel approach for wafer defect pattern classification based on topological data analysis. Expert Systems with Applications, 231, Article 120765.
23. Bae, Y., & Kang, S. (2023). Supervised contrastive learning for wafer map pattern classification. Engineering Applications of Artificial Intelligence, 126, Article 107154.
24. Kang, S., et al. (2023). Semi-supervised rotation-invariant representation learning for wafer map pattern analysis. Engineering Applications of Artificial Intelligence, 120, Article 105864.
25. Mahadevan, S. (2024). Intelligent Serverless Process Automation for Scalable Cloud Operations and Dynamic Resource Optimization. Journal of Computational Analysis and Applications (JoCAAA), 33(06), 4207-4221.
26. Chen, S., Liu, M., Hou, X., Zhu, Z., Huang, Z., & Wang, T. (2023). Wafer map defect pattern detection method based on improved attention mechanism. Expert Systems with Applications, 230, Article 120544.
27. Jeong, I., Lee, S. Y., Park, K., Kim, I., Huh, H., & Lee, S. (2023). Wafer map failure pattern classification using geometric transformation-invariant convolutional neural network. Scientific Reports, 13, Article 8127.
28. Kolla, S. K., & Reddy, V. A. R. (2024). Evaluating Cloud-Native vs. Hybrid Architectures for Health Benefit Administration Systems. International Journal of Medical Toxicology and Legal Medicine, 27(5), 1042-1053.
29. Choi, S.-H., Lee, D.-H., Kim, E.-S., Bae, Y.-M., Oh, Y.-C., & Kim, K.-J. (2024). Development of a spatial dimension-based taxonomy for classifying the defect patterns in a wafer bin map. Advanced Engineering Informatics, 60, Article 102540.
30. Uray, M., Giunti, B., Kerber, M., & Huber, S. (2024). Topological data analysis in smart manufacturing: State of the art and future directions. Journal of Manufacturing Systems, 76, 75–91.
31. Mangala, N., & Kolla, S. H. (2025). Real-Time Feature Engineering for Streaming AI Workloads Using PySpark and Azure Event Hubs. International Journal of Multidisciplinary Research in Science, Engineering, Technology & Management, 1(6), 93-105.
32. Yuan, W., Yan, J., & Piao, M. (2025). Position-aware self-supervised learning for wafer map defect pattern recognition. IEEE Transactions on Instrumentation and Measurement, 74, 1–11.
33. Tsai, T.-H., & Wang, C.-Y. (2025). Wafer map defect classification using deep learning framework with data augmentation on imbalance datasets. Journal on Image and Video Processing, 2025, Article 6.
34. Mangalampalli, B. M., & Kolla, S. K. (2025). Large Language Models for Automated Healthcare Data Dictionary Generation and Maintenance. Vascular and Endovascular Review, 8(20s), 363-375.
35. Yang, C.-J., Chen, Y.-H., & Hsieh, S.-Y. (2025). Enhanced wafer map defect pattern classification through stacking ensemble method and data augmentation integration. The Journal of Supercomputing, 81(5), Article 643.
Additional Files
Published
Data Availability Statement
None
Issue
Section
License
Copyright (c) 2026 Dhanaraj Sathiri (Author)
This work is licensed under a Creative Commons Attribution 4.0 International License.
This work is licensed under a Creative Commons Attribution 4.0 International License (CC BY 4.0), which permits unrestricted use, distribution, and reproduction in any medium, provided the original author(s) and source are credited.
