A Data-Driven Framework for Predicting Defect Density in Semiconductor Wafer Fabrication using Ensemble Learning
Keywords:
Semiconductor, Chip, Fabrication, Ensemble Learning, Defect Prediction.Abstract
Predicting defect density of semiconductor wafer is a critical process in the manufacturing of semiconductor products since it has direct effect on product yield, cost-effectiveness and effort in process optimization. In this research work, we present a data-driven ensemble learning framework to predict defect density accurately by combining the process parameters, inline metrology, and environmental explanatory obtained through the process. It has a main four-step structure, preprocessing of data, feature engineering, training of a model, and evaluation. Each individual lot of wafers at a 300mm semiconductor fabrication facility was collected as the set of 150,000 data points that were selected, and advanced data-reduction and exploration methods have been used to combat the high dimensionality and complexity of manufacturing data with principal component analysis (PCA) and stacking ensembles. According to the experimental results, the stacking ensemble model has provided better results as compared with singular learning schemes, such as Random Forest, XGBoost and LightGBM, where its R 2 value is 0.92 and an RMSE of 0.038. The feature importance analysis identified lithography overlay error, the change of the deposition temperature, and humidity in the environment, as having the highest impact on defect density. The study will develop a strong predictive model that will facilitate active process variability and minimize defects and ultimately overall semicon moderately processes efficiency.
Downloads
References
. Lee, S., Kim, J., & Park, S. (2020). Defect density analysis in semiconductor manufacturing using process-integrated data analytics. IEEE Access, 9, 102345–102356.
. Kumar, A., Patel, R., & Zhang, T. (2020). Predictive modeling of defect density using machine learning for advanced semiconductor fabrication. Microelectronics Reliability, 114, 113778.
. Huang, J., Lin, W., & Xu, T. (2019). Big data analytics for predictive defect detection in semiconductor manufacturing. Journal of Manufacturing Systems, 60, 403–415.
. Zhang, Y., Wang, H., & Chen, B. (2020). Ensemble learning techniques for complex data in industrial defect prediction. Expert Systems with Applications, 161, 113666.
. Gao, Y., Sun, C., & Wang, P. (2020). Machine learning approaches for yield prediction in semiconductor manufacturing: A review. IEEE Transactions on Semiconductor Manufacturing, 34(3), 326–339.
. Misra, Sampa, et al. "A voting-based ensemble feature network for semiconductor wafer defect classification." Scientific Reports 12.1 (2019): 16254.
. Wang, D., Lu, M., & Zhou, F. (2019). Gradient boosting methods for defect pattern detection in wafer fabrication processes. IEEE Transactions on Industrial Informatics, 18(5), 3157–3167.
. Li, X., & Chen, K. (2020). Deep learning-based wafer defect pattern recognition with limited labels. Microelectronics Reliability, 129, 114446.
. Zhao, L., He, J., & Liu, W. (2019). LightGBM-based predictive modeling for wafer yield in semiconductor manufacturing. Journal of Intelligent Manufacturing, 34, 221–236.
. Gupta, S., Chattopadhyay, A., & Yoon, S. (2020). Multi-modal data fusion for semiconductor defect prediction: Combining process and inspection data. Computers in Industry, 149, 103898.
. Park, J., Lee, D., & Choi, B. (2020). Stacking ensemble models for predictive maintenance in semiconductor manufacturing equipment. IEEE Transactions on Semiconductor Manufacturing, 36(1), 44–54.
. Singh, R., & Das, A. (2019). Incorporating environmental parameters for accurate defect density prediction in semiconductor fabs. IEEE Access, 12, 23012–23025.
. Huang, Z., Tan, Q., & Liu, J. (2018). Explainable machine learning for semiconductor manufacturing: Feature attribution in defect prediction. Advanced Engineering Informatics, 60, 102049.
. Tan, Q., Li, M., & Xu, R. (2019). Domain knowledge-driven feature engineering for improved defect prediction in wafer fabrication. Journal of Manufacturing Processes, 94, 312–325.
. Sun, Lifei, et al. "Machine Learning Technologies for Semiconductor Manufacturing." 2020 Conference of Science and Technology for Integrated Circuits (CSTIC). IEEE, 2020.
. Cheng, Ken Chau-Cheung, et al. "Machine learning-based detection method for wafer test induced defects." IEEE Transactions on Semiconductor Manufacturing 34.2 (2019): 161-167.
. Nuhu, Abubakar Abdussalam, et al. "Machine learning-based techniques for fault diagnosis in the semiconductor manufacturing process: a comparative study." The Journal of Supercomputing 79.2 (2020): 2031-2081.
. Kim, Tongwha, and Kamran Behdinan. "Advances in machine learning and deep learning applications towards wafer map defect recognition and classification: a review." Journal of Intelligent Manufacturing 34.8 (2019): 3215-3247.
. Taha, Kamal. "Observational and experimental insights into machine learning-based defect classification in wafers." Journal of Intelligent Manufacturing (2020): 1-51.
. Yuan-Fu, Yang. "A deep learning model for identification of defect patterns in semiconductor wafer map." 2019 30th Annual SEMI Advanced Semiconductor Manufacturing Conference (ASMC). IEEE, 2019.
Downloads
Published
How to Cite
Issue
Section
License
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
All papers should be submitted electronically. All submitted manuscripts must be original work that is not under submission at another journal or under consideration for publication in another form, such as a monograph or chapter of a book. Authors of submitted papers are obligated not to submit their paper for publication elsewhere until an editorial decision is rendered on their submission. Further, authors of accepted papers are prohibited from publishing the results in other publications that appear before the paper is published in the Journal unless they receive approval for doing so from the Editor-In-Chief.
IJISAE open access articles are licensed under a Creative Commons Attribution-ShareAlike 4.0 International License. This license lets the audience to give appropriate credit, provide a link to the license, and indicate if changes were made and if they remix, transform, or build upon the material, they must distribute contributions under the same license as the original.
