An Expandable Yield Prediction Framework Using Explainable Artificial Intelligence for Semiconductor Manufacturing
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 devic...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-02-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/13/4/2660 |
| _version_ | 1797622515845038080 |
|---|---|
| author | Youjin Lee Yonghan Roh |
| author_facet | Youjin Lee Yonghan Roh |
| author_sort | Youjin Lee |
| collection | DOAJ |
| description | 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. |
| first_indexed | 2024-03-11T09:11:23Z |
| format | Article |
| id | doaj.art-cc5a67098d664e41902016cb6863d7ee |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-03-11T09:11:23Z |
| publishDate | 2023-02-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-cc5a67098d664e41902016cb6863d7ee2023-11-16T18:58:56ZengMDPI AGApplied Sciences2076-34172023-02-01134266010.3390/app13042660An Expandable Yield Prediction Framework Using Explainable Artificial Intelligence for Semiconductor ManufacturingYoujin Lee0Yonghan Roh1Department of Semiconductor and Display Engineering, Sungkyunkwan University, Suwon-si 16419, Republic of KoreaDepartment of Semiconductor and Display Engineering, Sungkyunkwan University, Suwon-si 16419, Republic of KoreaEnormous 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.https://www.mdpi.com/2076-3417/13/4/2660semiconductor manufacturingyield predictionXAISHAP value method |
| spellingShingle | Youjin Lee Yonghan Roh An Expandable Yield Prediction Framework Using Explainable Artificial Intelligence for Semiconductor Manufacturing Applied Sciences semiconductor manufacturing yield prediction XAI SHAP value method |
| title | An Expandable Yield Prediction Framework Using Explainable Artificial Intelligence for Semiconductor Manufacturing |
| title_full | An Expandable Yield Prediction Framework Using Explainable Artificial Intelligence for Semiconductor Manufacturing |
| title_fullStr | An Expandable Yield Prediction Framework Using Explainable Artificial Intelligence for Semiconductor Manufacturing |
| title_full_unstemmed | An Expandable Yield Prediction Framework Using Explainable Artificial Intelligence for Semiconductor Manufacturing |
| title_short | An Expandable Yield Prediction Framework Using Explainable Artificial Intelligence for Semiconductor Manufacturing |
| title_sort | expandable yield prediction framework using explainable artificial intelligence for semiconductor manufacturing |
| topic | semiconductor manufacturing yield prediction XAI SHAP value method |
| url | https://www.mdpi.com/2076-3417/13/4/2660 |
| work_keys_str_mv | AT youjinlee anexpandableyieldpredictionframeworkusingexplainableartificialintelligenceforsemiconductormanufacturing AT yonghanroh anexpandableyieldpredictionframeworkusingexplainableartificialintelligenceforsemiconductormanufacturing AT youjinlee expandableyieldpredictionframeworkusingexplainableartificialintelligenceforsemiconductormanufacturing AT yonghanroh expandableyieldpredictionframeworkusingexplainableartificialintelligenceforsemiconductormanufacturing |