Generative Adversarial Network-Based Fault Detection in Semiconductor Equipment with Class-Imbalanced Data
This research proposes an application of generative adversarial networks (GANs) to solve the class imbalance problem in the fault detection and classification study of a plasma etching process. Small changes in the equipment part condition of the plasma equipment may cause an equipment fault, result...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-02-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/23/4/1889 |
| _version_ | 1797618284190760960 |
|---|---|
| author | Jeong Eun Choi Da Hoon Seol Chan Young Kim Sang Jeen Hong |
| author_facet | Jeong Eun Choi Da Hoon Seol Chan Young Kim Sang Jeen Hong |
| author_sort | Jeong Eun Choi |
| collection | DOAJ |
| description | This research proposes an application of generative adversarial networks (GANs) to solve the class imbalance problem in the fault detection and classification study of a plasma etching process. Small changes in the equipment part condition of the plasma equipment may cause an equipment fault, resulting in a process anomaly. Thus, fault detection in the semiconductor process is essential for success in advanced process control. Two datasets that assume faults of the mass flow controller (MFC) in equipment components were acquired using optical emission spectroscopy (OES) in the plasma etching process of a silicon trench: The abnormal process changed by the MFC is assumed to be faults, and the minority class of Case 1 is the normal class, and that of Case 2 is the abnormal class. In each case, additional minority class data were generated using GANs to compensate for the degradation of model training due to class-imbalanced data. Comparisons of five existing fault detection algorithms with the augmented datasets showed improved modeling performances. Generating a dataset for the minority group using GANs is beneficial for class imbalance problems of OES datasets in fault detection for the semiconductor plasma equipment. |
| first_indexed | 2024-03-11T08:10:54Z |
| format | Article |
| id | doaj.art-77a93b3851604ea7a894065fb29be4ac |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-11T08:10:54Z |
| publishDate | 2023-02-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-77a93b3851604ea7a894065fb29be4ac2023-11-16T23:07:31ZengMDPI AGSensors1424-82202023-02-01234188910.3390/s23041889Generative Adversarial Network-Based Fault Detection in Semiconductor Equipment with Class-Imbalanced DataJeong Eun Choi0Da Hoon Seol1Chan Young Kim2Sang Jeen Hong3Department of Electronics Engineering, Myongji University, 116 Myongji-ro, Yongin-si 17058, Gyeonggi-do, Republic of KoreaDepartment of Electronics Engineering, Myongji University, 116 Myongji-ro, Yongin-si 17058, Gyeonggi-do, Republic of KoreaDepartment of Electronics Engineering, Myongji University, 116 Myongji-ro, Yongin-si 17058, Gyeonggi-do, Republic of KoreaDepartment of Electronics Engineering, Myongji University, 116 Myongji-ro, Yongin-si 17058, Gyeonggi-do, Republic of KoreaThis research proposes an application of generative adversarial networks (GANs) to solve the class imbalance problem in the fault detection and classification study of a plasma etching process. Small changes in the equipment part condition of the plasma equipment may cause an equipment fault, resulting in a process anomaly. Thus, fault detection in the semiconductor process is essential for success in advanced process control. Two datasets that assume faults of the mass flow controller (MFC) in equipment components were acquired using optical emission spectroscopy (OES) in the plasma etching process of a silicon trench: The abnormal process changed by the MFC is assumed to be faults, and the minority class of Case 1 is the normal class, and that of Case 2 is the abnormal class. In each case, additional minority class data were generated using GANs to compensate for the degradation of model training due to class-imbalanced data. Comparisons of five existing fault detection algorithms with the augmented datasets showed improved modeling performances. Generating a dataset for the minority group using GANs is beneficial for class imbalance problems of OES datasets in fault detection for the semiconductor plasma equipment.https://www.mdpi.com/1424-8220/23/4/1889fault detectiongenerative adversarial networksmachine learningoptical emission spectroscopyplasma etch |
| spellingShingle | Jeong Eun Choi Da Hoon Seol Chan Young Kim Sang Jeen Hong Generative Adversarial Network-Based Fault Detection in Semiconductor Equipment with Class-Imbalanced Data Sensors fault detection generative adversarial networks machine learning optical emission spectroscopy plasma etch |
| title | Generative Adversarial Network-Based Fault Detection in Semiconductor Equipment with Class-Imbalanced Data |
| title_full | Generative Adversarial Network-Based Fault Detection in Semiconductor Equipment with Class-Imbalanced Data |
| title_fullStr | Generative Adversarial Network-Based Fault Detection in Semiconductor Equipment with Class-Imbalanced Data |
| title_full_unstemmed | Generative Adversarial Network-Based Fault Detection in Semiconductor Equipment with Class-Imbalanced Data |
| title_short | Generative Adversarial Network-Based Fault Detection in Semiconductor Equipment with Class-Imbalanced Data |
| title_sort | generative adversarial network based fault detection in semiconductor equipment with class imbalanced data |
| topic | fault detection generative adversarial networks machine learning optical emission spectroscopy plasma etch |
| url | https://www.mdpi.com/1424-8220/23/4/1889 |
| work_keys_str_mv | AT jeongeunchoi generativeadversarialnetworkbasedfaultdetectioninsemiconductorequipmentwithclassimbalanceddata AT dahoonseol generativeadversarialnetworkbasedfaultdetectioninsemiconductorequipmentwithclassimbalanceddata AT chanyoungkim generativeadversarialnetworkbasedfaultdetectioninsemiconductorequipmentwithclassimbalanceddata AT sangjeenhong generativeadversarialnetworkbasedfaultdetectioninsemiconductorequipmentwithclassimbalanceddata |