An Expandable Yield Prediction Framework Using Explainable Artificial Intelligence for Semiconductor Manufacturing
Source abstract
Abstract
Enormous amounts of data are generated and analyzed in the latest semiconductor industry. Established yield prediction studies have dealt with one type of data or a dataset from one procedure. However, semiconductor device fabrication comprises hundreds of processes, and various factors affect device yields. This challenge is addressed in this study by using an expandable input data-based framework to include divergent factors in the prediction and by adapting explainable artificial intelligence (XAI), which utilizes model interpretation to modify fabrication conditions. After preprocessing the data, the procedure of optimizing and comparing several machine learning models is followed to select the best performing model for the dataset, which is a random forest (RF) regression with a root mean square error (RMSE) value of 0.648. The prediction results enhance production management, and the explanations of the model deepen the understanding of yield-related factors with Shapley additive explanation (SHAP) values. This work provides evidence with an empirical case study of device production data. The framework improves prediction accuracy, and the relationships between yield and features are illustrated with the SHAP value. The proposed approach can potentially analyze expandable fields of fabrication conditions to interpret multifaceted semiconductor manufacturing.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Industrial Vision Systems and Defect Detection · Manufacturing Process and Optimization
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Department of Semiconductor and Display Engineering, Sungkyunkwan University, Suwon-si 16419, Republic of Korea
Semiconductor R&D Center, Samsung Electronics Co., Ltd., Hwaseong-si 18448, Republic of Korea
College of Information and Communication Engineering, Sungkyunkwan University, Suwon-si 16419, Republic of Korea
References (52)
Show source-provided references
1. A Novel Framework for Semiconductor Manufacturing Final Test Yield Classification Using Machine Learning Techniques10.1109/ACCESS.2020.3034680 ↗
2. Espadinha-Cruz, P., Godina, R., and Rodrigues, E.M.G. (2021). A Review of Data Mining Applications in Semiconductor Manufacturing. Processes, 9.10.3390/pr9020305 ↗
3. A Review of Yield Modelling Techniques for Semiconductor Manufacturing10.1080/00207540600596874 ↗
4. Defect Clustering Viewed through Generalized Poisson Distribution10.1109/66.149802 ↗
5. Statistical Process Control in Semiconductor Manufacturing10.1109/5.149445 ↗
6. A System for Semiconductor Process Specification10.1109/66.267639 ↗
7. Bouktif, S., Fiaz, A., Ouni, A., and Serhani, M.A. (2018). Optimal Deep Learning LSTM Model for Electric Load Forecasting using Feature Selection and Genetic Algorithm: Comparison with Machine Learning Approaches. Energies, 11.10.3390/en11071636 ↗
8. Zhang, Y., Ma, J., Liang, S., Li, X., and Li, M. (2020). An evaluation of eight machine learning regression algorithms for forest aboveground biomass estimation from multiple satellite data products. Remote Sens., 12.10.3390/rs12244015 ↗
9. Zhang, Y., Wang, G., Li, M., and Han, S. (2018). Automated Classification Analysis of Geological Structures Based on Images Data and Deep Learning Model. Appl. Sci., 8.10.3390/app8122493 ↗
10. Kammerer, K., Hoppenstedt, B., Pryss, R., Stökler, S., Allgaier, J., and Reichert, M. (2019). Anomaly Detections for Manufacturing Systems Based on Sensor Data—Insights into Two Challenging Real-World Production Settings. Sensors, 19.10.3390/s19245370 ↗
11. Li, Z., Rahman, S.M., Vega, R., and Dong, B. (2016). A Hierarchical Approach Using Machine Learning Methods in Solar Photovoltaic Energy Production Forecasting. Energies, 9.10.3390/en9010055 ↗
12. Dou, Z., Sun, Y., Zhang, Y., Wang, T., Wu, C., and Fan, S. (2021). Regional Manufacturing Industry Demand Forecasting: A Deep Learning Approach. Appl. Sci., 11.10.3390/app11136199 ↗
13. Semiconductor manufacturing process monitoring based on adaptive substatistical PCA10.1109/TSM.2009.2039188 ↗
14. Singgih, I.K. (2021). Production Flow Analysis in a Semiconductor Fab Using Machine Learning Techniques. Processes, 9.10.3390/pr9030407 ↗
15. Fault detection using the k-nearest neighbor rule for semiconductor manufacturing processes10.1109/TSM.2007.907607 ↗
16. López de la Rosa, F., Sánchez-Reolid, R., Gómez-Sirvent, J.L., Morales, R., and Fernández-Caballero, A. (2021). A Review on Machine and Deep Learning for Semiconductor Defect Classification in Scanning Electron Microscope Images. Appl. Sci., 11.10.3390/app11209508 ↗
17. Hung, Y.-H. (2021). Improved Ensemble-Learning Algorithm for Predictive Maintenance in the Manufacturing Process. Appl. Sci., 11.10.3390/app11156832 ↗
18. A comprehensive big-data-based monitoring system for yield enhancement in semiconductor manufacturing10.1109/TSM.2017.2753251 ↗
19. Kovacs, I., Ţopa, M., Buzo, A., and Pelz, G. (2017, January 12–15). An Accurate Yield Estimation Approach for Multivariate Non-Normal Data in Semiconductor Quality Analysis. Proceedings of the 2017 14th International Conference on Synthesis, Modeling, Analysis and Simulation Methods and Applications to Circuit Design (SMACD), IEEE, Giardini Naxos, Italy.10.1109/SMACD.2017.7981609 ↗
20. Jess, J.A., Kalafala, K., Naidu, S.R., Otten, R.H., and Visweswariah, C. (2003, January 2–6). Statistical Timing for Parametric Yield Prediction of Digital Integrated Circuits. Proceedings of the Proceedings of the 40th Annual Design Automation Conference, Anaheim, CA, USA.10.1145/775832.776066 ↗
21. –C. Data Mining for Yield Enhancement in Semiconductor Manufacturing and an Empirical Study10.1016/j.eswa.2006.04.014 ↗
22. A Data-Driven Approach to Selection of Critical Process Steps in the Semiconductor Manufacturing Process Considering Missing and Imbalanced Data10.1016/j.jmsy.2019.07.001 ↗
23. A Gaussian Mixture Model Clustering Ensemble Regressor for Semiconductor Manufacturing Final Test Yield Prediction10.1109/ACCESS.2021.3055433 ↗
24. Kim, S., Lee, K., Noh, H.-K., Shin, Y., Chang, K.-B., Jeong, J., Baek, S., Kang, M., Cho, K., and Kim, D.-W. (October, January 23). Automatic Modeling of Logic Device Performance Based on Machine Learning and Explainable AI. Proceedings of the 2020 International Conference on Simulation of Semiconductor Processes and Devices (SISPAD), IEEE, Kobe, Japan.10.23919/SISPAD49475.2020.9241681 ↗
25. Analysing Semiconductor Manufacturing Big Data for Root Cause Detection of Excursion for Yield Enhancement10.1080/00207543.2015.1109153 ↗
26. Sequential residual learning for multistep processes in semiconductor manufacturing10.1109/TSM.2022.3226716 ↗
27. Towards Better Process Management in Wastewater Treatment Plants: Process Analytics Based on SHAP Values for Tree-Based Machine Learning Methods10.1016/j.jenvman.2021.113941 ↗
28. Using Explainable Artificial Intelligence to Improve Process Quality: Evidence from Semiconductor Manufacturing10.1287/mnsc.2021.4190 ↗
29. Stochastic Games10.1073/pnas.39.10.1095 ↗
30. Lundberg, S.M., Erion, G.G., and Lee, S.-I. (2018). Consistent Individualized Feature Attribution for Tree Ensembles. arXiv, arXiv preprint.
31. Regression Shrinkage and Selection via the Lasso10.1111/j.2517-6161.1996.tb02080.x ↗
32. Drucker, H. (1997, January 8–12). Improving Regressors Using Boosting Techniques. Proceedings of the ICML, Nashville, TN, USA.
33. Chen, T., and Guestrin, C. (2016, January 13–17). Xgboost: A Scalable Tree Boosting System. Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, San Francisco, CA, USA.10.1145/2939672.2939785 ↗
34. Lightgbm: A Highly Efficient Gradient Boosting Decision Tree
35. Random Forests10.1023/A:1010933404324 ↗
36. Practical selection of SVM parameters and noise estimation for SVM regression10.1016/S0893-6080(03)00169-2 ↗
37. Rasmussen, C.E. (2023). Gaussian processes in machine learning. In Summer School on Machine Learning, Springer.
38. Rumelhart, D.E., Hinton, G.E., and Williams, R.J. (1985). Learning Internal Representations by Error Propagation, California Univ San Diego La Jolla Inst for Cognitive Science.10.21236/ADA164453 ↗
39. Application of k-nearest neighbor (knn) approach for predicting economic events: Theoretical background
40. Random sample consensus: A paradigm for model fitting with applications to image analysis and automated cartography10.1145/358669.358692 ↗
41. From local explanations to global understanding with explainable AI for trees10.1038/s42256-019-0138-9 ↗
42. Enhancing the explainability of regression-based polynomial chaos expansion by Shapley additive explanations10.1016/j.ress.2022.109045 ↗
43. Aydin, H.E., and Iban, M.C. (2022). Predicting and analyzing flood susceptibility using boosting-based ensemble machine learning algorithms with SHapley Additive exPlanations. Nat. Hazards, 1–35.10.1007/s11069-022-05793-y ↗
44. A machine learning model based on ultrasound image features to assess the risk of sentinel lymph node metastasis in breast cancer patients: Applications of scikit-learn and SHAP10.3389/fonc.2022.944569 ↗
45. A Virtual Metrology System for Semiconductor Manufacturing10.1016/j.eswa.2009.05.053 ↗
46. Lenz, B., Barak, B., Mührwald, J., and Leicht, C. (2013, January 4–7). Virtual metrology in semiconductor manufacturing by means of predictive machine learning models. Proceedings of the 2013 12th International Conference on Machine Learning and Applications, IEEE, Miami, FL, USA.10.1109/ICMLA.2013.186 ↗
47. Remaining useful life based maintenance policy for deteriorating systems subject to continuous degradation and shock10.1016/j.procir.2018.03.207 ↗
48. Textual analysis for online reviews: A polymerization topic sentiment model10.1109/ACCESS.2019.2920091 ↗
49. Ma, Y., Qiao, F., Zhao, F., and Sutherland, J.W. (2017). Dynamic Scheduling of a Semiconductor Production Line Based on a Composite Rule Set. Appl. Sci., 7.10.20944/preprints201710.0013.v1 ↗
50. Lee, G.M., and Gao, X. (2021). A Hybrid Approach Combining Fuzzy c-Means-Based Genetic Algorithm and Machine Learning for Predicting Job Cycle Times for Semiconductor Manufacturing. Appl. Sci., 11.10.3390/app11167428 ↗
51. Wafer edge yield prediction using a combined long short-term memory and feed-forward neural network model for semiconductor manufacturing10.1109/ACCESS.2020.3040426 ↗
52. A unified approach to interpreting model predictions