A Comprehensive Survey of Deep Transfer Learning for Anomaly Detection in Industrial Time Series: Methods, Applications, and Directions
Automating the monitoring of industrial processes has the potential to enhance efficiency and optimize quality by promptly detecting abnormal events and thus facilitating timely interventions. Deep learning, with its capacity to discern non-trivial patterns within large datasets, plays a pivotal rol...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2024-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10379639/ |
| _version_ | 1797360170636935168 |
|---|---|
| author | Peng Yan Ahmed Abdulkadir Paul-Philipp Luley Matthias Rosenthal Gerrit A. Schatte Benjamin F. Grewe Thilo Stadelmann |
| author_facet | Peng Yan Ahmed Abdulkadir Paul-Philipp Luley Matthias Rosenthal Gerrit A. Schatte Benjamin F. Grewe Thilo Stadelmann |
| author_sort | Peng Yan |
| collection | DOAJ |
| description | Automating the monitoring of industrial processes has the potential to enhance efficiency and optimize quality by promptly detecting abnormal events and thus facilitating timely interventions. Deep learning, with its capacity to discern non-trivial patterns within large datasets, plays a pivotal role in this process. Standard deep learning methods are suitable to solve a specific task given a specific type of data. During training, deep learning demands large volumes of labeled data. However, due to the dynamic nature of the industrial processes and environment, it is impractical to acquire large-scale labeled data for standard deep learning training for every slightly different case anew. Deep transfer learning offers a solution to this problem. By leveraging knowledge from related tasks and accounting for variations in data distributions, the transfer learning framework solves new tasks with little or even no additional labeled data. The approach bypasses the need to retrain a model from scratch for every new setup and dramatically reduces the labeled data requirement. This survey first provides an in-depth review of deep transfer learning, examining the problem settings of transfer learning and classifying the prevailing deep transfer learning methods. Moreover, we delve into applications of deep transfer learning in the context of a broad spectrum of time series anomaly detection tasks prevalent in primary industrial domains, e.g., manufacturing process monitoring, predictive maintenance, energy management, and infrastructure facility monitoring. We discuss the challenges and limitations of deep transfer learning in industrial contexts and conclude the survey with practical directions and actionable suggestions to address the need to leverage diverse time series data for anomaly detection in an increasingly dynamic production environment. |
| first_indexed | 2024-03-08T15:35:24Z |
| format | Article |
| id | doaj.art-3b29133470184c76b191415a2d519127 |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-03-08T15:35:24Z |
| publishDate | 2024-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-3b29133470184c76b191415a2d5191272024-01-10T00:05:50ZengIEEEIEEE Access2169-35362024-01-01123768378910.1109/ACCESS.2023.334913210379639A Comprehensive Survey of Deep Transfer Learning for Anomaly Detection in Industrial Time Series: Methods, Applications, and DirectionsPeng Yan0https://orcid.org/0009-0006-0236-4707Ahmed Abdulkadir1Paul-Philipp Luley2https://orcid.org/0009-0007-0851-665XMatthias Rosenthal3https://orcid.org/0000-0002-7577-783XGerrit A. Schatte4https://orcid.org/0009-0002-5760-9346Benjamin F. Grewe5Thilo Stadelmann6https://orcid.org/0000-0002-3784-0420Centre for Artificial Intelligence, ZHAW School of Engineering, Winterthur, SwitzerlandCentre for Artificial Intelligence, ZHAW School of Engineering, Winterthur, SwitzerlandCentre for Artificial Intelligence, ZHAW School of Engineering, Winterthur, SwitzerlandInstitute of Embedded Systems, ZHAW School of Engineering, Winterthur, SwitzerlandInnovation Lab, Kistler Instrumente AG, Winterthur, SwitzerlandFaculty of Science, University of Zurich, Zürich, SwitzerlandCentre for Artificial Intelligence, ZHAW School of Engineering, Winterthur, SwitzerlandAutomating the monitoring of industrial processes has the potential to enhance efficiency and optimize quality by promptly detecting abnormal events and thus facilitating timely interventions. Deep learning, with its capacity to discern non-trivial patterns within large datasets, plays a pivotal role in this process. Standard deep learning methods are suitable to solve a specific task given a specific type of data. During training, deep learning demands large volumes of labeled data. However, due to the dynamic nature of the industrial processes and environment, it is impractical to acquire large-scale labeled data for standard deep learning training for every slightly different case anew. Deep transfer learning offers a solution to this problem. By leveraging knowledge from related tasks and accounting for variations in data distributions, the transfer learning framework solves new tasks with little or even no additional labeled data. The approach bypasses the need to retrain a model from scratch for every new setup and dramatically reduces the labeled data requirement. This survey first provides an in-depth review of deep transfer learning, examining the problem settings of transfer learning and classifying the prevailing deep transfer learning methods. Moreover, we delve into applications of deep transfer learning in the context of a broad spectrum of time series anomaly detection tasks prevalent in primary industrial domains, e.g., manufacturing process monitoring, predictive maintenance, energy management, and infrastructure facility monitoring. We discuss the challenges and limitations of deep transfer learning in industrial contexts and conclude the survey with practical directions and actionable suggestions to address the need to leverage diverse time series data for anomaly detection in an increasingly dynamic production environment.https://ieeexplore.ieee.org/document/10379639/Deep transfer learningtime series analysisanomaly detectionmanufacturing process monitoringpredictive maintenance |
| spellingShingle | Peng Yan Ahmed Abdulkadir Paul-Philipp Luley Matthias Rosenthal Gerrit A. Schatte Benjamin F. Grewe Thilo Stadelmann A Comprehensive Survey of Deep Transfer Learning for Anomaly Detection in Industrial Time Series: Methods, Applications, and Directions IEEE Access Deep transfer learning time series analysis anomaly detection manufacturing process monitoring predictive maintenance |
| title | A Comprehensive Survey of Deep Transfer Learning for Anomaly Detection in Industrial Time Series: Methods, Applications, and Directions |
| title_full | A Comprehensive Survey of Deep Transfer Learning for Anomaly Detection in Industrial Time Series: Methods, Applications, and Directions |
| title_fullStr | A Comprehensive Survey of Deep Transfer Learning for Anomaly Detection in Industrial Time Series: Methods, Applications, and Directions |
| title_full_unstemmed | A Comprehensive Survey of Deep Transfer Learning for Anomaly Detection in Industrial Time Series: Methods, Applications, and Directions |
| title_short | A Comprehensive Survey of Deep Transfer Learning for Anomaly Detection in Industrial Time Series: Methods, Applications, and Directions |
| title_sort | comprehensive survey of deep transfer learning for anomaly detection in industrial time series methods applications and directions |
| topic | Deep transfer learning time series analysis anomaly detection manufacturing process monitoring predictive maintenance |
| url | https://ieeexplore.ieee.org/document/10379639/ |
| work_keys_str_mv | AT pengyan acomprehensivesurveyofdeeptransferlearningforanomalydetectioninindustrialtimeseriesmethodsapplicationsanddirections AT ahmedabdulkadir acomprehensivesurveyofdeeptransferlearningforanomalydetectioninindustrialtimeseriesmethodsapplicationsanddirections AT paulphilippluley acomprehensivesurveyofdeeptransferlearningforanomalydetectioninindustrialtimeseriesmethodsapplicationsanddirections AT matthiasrosenthal acomprehensivesurveyofdeeptransferlearningforanomalydetectioninindustrialtimeseriesmethodsapplicationsanddirections AT gerritaschatte acomprehensivesurveyofdeeptransferlearningforanomalydetectioninindustrialtimeseriesmethodsapplicationsanddirections AT benjaminfgrewe acomprehensivesurveyofdeeptransferlearningforanomalydetectioninindustrialtimeseriesmethodsapplicationsanddirections AT thilostadelmann acomprehensivesurveyofdeeptransferlearningforanomalydetectioninindustrialtimeseriesmethodsapplicationsanddirections AT pengyan comprehensivesurveyofdeeptransferlearningforanomalydetectioninindustrialtimeseriesmethodsapplicationsanddirections AT ahmedabdulkadir comprehensivesurveyofdeeptransferlearningforanomalydetectioninindustrialtimeseriesmethodsapplicationsanddirections AT paulphilippluley comprehensivesurveyofdeeptransferlearningforanomalydetectioninindustrialtimeseriesmethodsapplicationsanddirections AT matthiasrosenthal comprehensivesurveyofdeeptransferlearningforanomalydetectioninindustrialtimeseriesmethodsapplicationsanddirections AT gerritaschatte comprehensivesurveyofdeeptransferlearningforanomalydetectioninindustrialtimeseriesmethodsapplicationsanddirections AT benjaminfgrewe comprehensivesurveyofdeeptransferlearningforanomalydetectioninindustrialtimeseriesmethodsapplicationsanddirections AT thilostadelmann comprehensivesurveyofdeeptransferlearningforanomalydetectioninindustrialtimeseriesmethodsapplicationsanddirections |