Anomaly Detection in Time Series Data and its Application to Semiconductor Manufacturing
Anomaly detection is essential for the monitoring and improvement of product quality in manufacturing processes. In the case of semiconductor manufacturing, where large amounts of time series data from equipment sensors are rapidly accumulated, identifying anomalous signals within this data presents...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2023-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10318085/ |
| _version_ | 1797473499631058944 |
|---|---|
| author | Rakhoon Hwang Seungtae Park Youngwook Bin Hyung Ju Hwang |
| author_facet | Rakhoon Hwang Seungtae Park Youngwook Bin Hyung Ju Hwang |
| author_sort | Rakhoon Hwang |
| collection | DOAJ |
| description | Anomaly detection is essential for the monitoring and improvement of product quality in manufacturing processes. In the case of semiconductor manufacturing, where large amounts of time series data from equipment sensors are rapidly accumulated, identifying anomalous signals within this data presents a significant challenge. The data in question is multivariate and of varying lengths, with an often highly imbalanced ratio of normal to abnormal signals. Given the nature of this data, traditional data-driven methods may not be appropriate for its analysis. This paper proposes a novel unsupervised anomaly detection model for the analysis of multivariate time series data. The model utilizes a unique recurrent neural network architecture and a special objective function to detect anomalies. Furthermore, a relevance analysis method is introduced to facilitate the interpretation and analysis of the detected anomalous signals. Our experimental results indicate that this deep anomaly detection model, which summarizes sensor data of different lengths into a low-dimensional latent space, enabling the easy visualization and distinction of anomalous signals, can be applied in real-world semiconductor manufacturing factories and used by on-site engineers for both analysis and execution purposes. |
| first_indexed | 2024-03-09T20:15:22Z |
| format | Article |
| id | doaj.art-44c08680b9934779ba5559bf4486ab6d |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-03-09T20:15:22Z |
| publishDate | 2023-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-44c08680b9934779ba5559bf4486ab6d2023-11-24T00:01:38ZengIEEEIEEE Access2169-35362023-01-011113048313049010.1109/ACCESS.2023.333324710318085Anomaly Detection in Time Series Data and its Application to Semiconductor ManufacturingRakhoon Hwang0https://orcid.org/0000-0001-9220-5027Seungtae Park1https://orcid.org/0000-0002-8776-8375Youngwook Bin2Hyung Ju Hwang3https://orcid.org/0000-0002-3678-2687Institute of Advanced Technology Development, Hyundai Motor Company, Seongnam-si, Republic of KoreaDepartment of Mechanical Engineering, POSTECH, Pohang, Republic of KoreaInnovation Center, Manufacturing Execution System Team, Samsung Electronics, Hwaseong-si, Republic of KoreaDepartment of Mathematics, POSTECH, Pohang, Republic of KoreaAnomaly detection is essential for the monitoring and improvement of product quality in manufacturing processes. In the case of semiconductor manufacturing, where large amounts of time series data from equipment sensors are rapidly accumulated, identifying anomalous signals within this data presents a significant challenge. The data in question is multivariate and of varying lengths, with an often highly imbalanced ratio of normal to abnormal signals. Given the nature of this data, traditional data-driven methods may not be appropriate for its analysis. This paper proposes a novel unsupervised anomaly detection model for the analysis of multivariate time series data. The model utilizes a unique recurrent neural network architecture and a special objective function to detect anomalies. Furthermore, a relevance analysis method is introduced to facilitate the interpretation and analysis of the detected anomalous signals. Our experimental results indicate that this deep anomaly detection model, which summarizes sensor data of different lengths into a low-dimensional latent space, enabling the easy visualization and distinction of anomalous signals, can be applied in real-world semiconductor manufacturing factories and used by on-site engineers for both analysis and execution purposes.https://ieeexplore.ieee.org/document/10318085/Anomaly detectionfault detection and diagnosismultivariate time series datasemiconductor manufacturingunsupervised learning |
| spellingShingle | Rakhoon Hwang Seungtae Park Youngwook Bin Hyung Ju Hwang Anomaly Detection in Time Series Data and its Application to Semiconductor Manufacturing IEEE Access Anomaly detection fault detection and diagnosis multivariate time series data semiconductor manufacturing unsupervised learning |
| title | Anomaly Detection in Time Series Data and its Application to Semiconductor Manufacturing |
| title_full | Anomaly Detection in Time Series Data and its Application to Semiconductor Manufacturing |
| title_fullStr | Anomaly Detection in Time Series Data and its Application to Semiconductor Manufacturing |
| title_full_unstemmed | Anomaly Detection in Time Series Data and its Application to Semiconductor Manufacturing |
| title_short | Anomaly Detection in Time Series Data and its Application to Semiconductor Manufacturing |
| title_sort | anomaly detection in time series data and its application to semiconductor manufacturing |
| topic | Anomaly detection fault detection and diagnosis multivariate time series data semiconductor manufacturing unsupervised learning |
| url | https://ieeexplore.ieee.org/document/10318085/ |
| work_keys_str_mv | AT rakhoonhwang anomalydetectionintimeseriesdataanditsapplicationtosemiconductormanufacturing AT seungtaepark anomalydetectionintimeseriesdataanditsapplicationtosemiconductormanufacturing AT youngwookbin anomalydetectionintimeseriesdataanditsapplicationtosemiconductormanufacturing AT hyungjuhwang anomalydetectionintimeseriesdataanditsapplicationtosemiconductormanufacturing |