Application of 1D ResNet for Multivariate Fault Detection on Semiconductor Manufacturing Equipment
Amid the ongoing emphasis on reducing manufacturing costs and enhancing productivity, one of the crucial objectives when manufacturing is to maintain process tools in optimal operating conditions. With advancements in sensing technologies, large amounts of data are collected during manufacturing pro...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-11-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/23/22/9099 |
| _version_ | 1797457848799592448 |
|---|---|
| author | Philip Tchatchoua Guillaume Graton Mustapha Ouladsine Jean-François Christaud |
| author_facet | Philip Tchatchoua Guillaume Graton Mustapha Ouladsine Jean-François Christaud |
| author_sort | Philip Tchatchoua |
| collection | DOAJ |
| description | Amid the ongoing emphasis on reducing manufacturing costs and enhancing productivity, one of the crucial objectives when manufacturing is to maintain process tools in optimal operating conditions. With advancements in sensing technologies, large amounts of data are collected during manufacturing processes, and the challenge today is to utilize these massive data efficiently. Some of these data are used for fault detection and classification (FDC) to evaluate the general condition of production machinery. The distinctive characteristics of semiconductor manufacturing, such as interdependent parameters, fluctuating behaviors over time, and frequently changing operating conditions, pose a major challenge in identifying defective wafers during the manufacturing process. To address this challenge, a multivariate fault detection method based on a 1D ResNet algorithm is introduced in this study. The aim is to identify anomalous wafers by analyzing the raw time-series data collected from multiple sensors throughout the semiconductor manufacturing process. To achieve this objective, a set of features is chosen from specified tools in the process chain to characterize the status of the wafers. Tests on the available data confirm that the gradient vanishing problem faced by very deep networks starts to occur with the plain 1D Convolutional Neural Network (CNN)-based method when the size of the network is deeper than 11 layers. To address this, a 1D Residual Network (ResNet)-based method is used. The experimental results show that the proposed method works more effectively and accurately compared to techniques using a plain 1D CNN and can thus be used for detecting abnormal wafers in the semiconductor manufacturing industry. |
| first_indexed | 2024-03-09T16:28:40Z |
| format | Article |
| id | doaj.art-a762cf061da7449bbda898dad129dd64 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-09T16:28:40Z |
| publishDate | 2023-11-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-a762cf061da7449bbda898dad129dd642023-11-24T15:05:20ZengMDPI AGSensors1424-82202023-11-012322909910.3390/s23229099Application of 1D ResNet for Multivariate Fault Detection on Semiconductor Manufacturing EquipmentPhilip Tchatchoua0Guillaume Graton1Mustapha Ouladsine2Jean-François Christaud3LIS, CNRS, Aix Marseille University, University of Toulon, 13007 Marseille, FranceLIS, CNRS, Aix Marseille University, University of Toulon, 13007 Marseille, FranceLIS, CNRS, Aix Marseille University, University of Toulon, 13007 Marseille, FranceSTMicroelectronics, 13106 Rousset, FranceAmid the ongoing emphasis on reducing manufacturing costs and enhancing productivity, one of the crucial objectives when manufacturing is to maintain process tools in optimal operating conditions. With advancements in sensing technologies, large amounts of data are collected during manufacturing processes, and the challenge today is to utilize these massive data efficiently. Some of these data are used for fault detection and classification (FDC) to evaluate the general condition of production machinery. The distinctive characteristics of semiconductor manufacturing, such as interdependent parameters, fluctuating behaviors over time, and frequently changing operating conditions, pose a major challenge in identifying defective wafers during the manufacturing process. To address this challenge, a multivariate fault detection method based on a 1D ResNet algorithm is introduced in this study. The aim is to identify anomalous wafers by analyzing the raw time-series data collected from multiple sensors throughout the semiconductor manufacturing process. To achieve this objective, a set of features is chosen from specified tools in the process chain to characterize the status of the wafers. Tests on the available data confirm that the gradient vanishing problem faced by very deep networks starts to occur with the plain 1D Convolutional Neural Network (CNN)-based method when the size of the network is deeper than 11 layers. To address this, a 1D Residual Network (ResNet)-based method is used. The experimental results show that the proposed method works more effectively and accurately compared to techniques using a plain 1D CNN and can thus be used for detecting abnormal wafers in the semiconductor manufacturing industry.https://www.mdpi.com/1424-8220/23/22/9099fault detectionraw sensor datamultivariate time seriessemiconductor manufacturingdeep learning |
| spellingShingle | Philip Tchatchoua Guillaume Graton Mustapha Ouladsine Jean-François Christaud Application of 1D ResNet for Multivariate Fault Detection on Semiconductor Manufacturing Equipment Sensors fault detection raw sensor data multivariate time series semiconductor manufacturing deep learning |
| title | Application of 1D ResNet for Multivariate Fault Detection on Semiconductor Manufacturing Equipment |
| title_full | Application of 1D ResNet for Multivariate Fault Detection on Semiconductor Manufacturing Equipment |
| title_fullStr | Application of 1D ResNet for Multivariate Fault Detection on Semiconductor Manufacturing Equipment |
| title_full_unstemmed | Application of 1D ResNet for Multivariate Fault Detection on Semiconductor Manufacturing Equipment |
| title_short | Application of 1D ResNet for Multivariate Fault Detection on Semiconductor Manufacturing Equipment |
| title_sort | application of 1d resnet for multivariate fault detection on semiconductor manufacturing equipment |
| topic | fault detection raw sensor data multivariate time series semiconductor manufacturing deep learning |
| url | https://www.mdpi.com/1424-8220/23/22/9099 |
| work_keys_str_mv | AT philiptchatchoua applicationof1dresnetformultivariatefaultdetectiononsemiconductormanufacturingequipment AT guillaumegraton applicationof1dresnetformultivariatefaultdetectiononsemiconductormanufacturingequipment AT mustaphaouladsine applicationof1dresnetformultivariatefaultdetectiononsemiconductormanufacturingequipment AT jeanfrancoischristaud applicationof1dresnetformultivariatefaultdetectiononsemiconductormanufacturingequipment |