Industrial Transfer Learning for Multivariate Time Series Segmentation: A Case Study on Hydraulic Pump Testing Cycles
Industrial data scarcity is one of the largest factors holding back the widespread use of machine learning in manufacturing. To overcome this problem, the concept of transfer learning was developed and has received much attention in recent industrial research. This paper focuses on the problem of ti...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-03-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/23/7/3636 |
| _version_ | 1797607002914947072 |
|---|---|
| author | Stefan Gaugel Manfred Reichert |
| author_facet | Stefan Gaugel Manfred Reichert |
| author_sort | Stefan Gaugel |
| collection | DOAJ |
| description | Industrial data scarcity is one of the largest factors holding back the widespread use of machine learning in manufacturing. To overcome this problem, the concept of transfer learning was developed and has received much attention in recent industrial research. This paper focuses on the problem of time series segmentation and presents the first in-depth research on transfer learning for deep learning-based time series segmentation on the industrial use case of end-of-line pump testing. In particular, we investigate whether the performance of deep learning models can be increased by pretraining the network with data from other domains. Three different scenarios are analyzed: source and target data being closely related, source and target data being distantly related, and source and target data being non-related. The results demonstrate that transfer learning can enhance the performance of time series segmentation models with respect to accuracy and training speed. The benefit can be most clearly seen in scenarios where source and training data are closely related and the number of target training data samples is lowest. However, in the scenario of non-related datasets, cases of negative transfer learning were observed as well. Thus, the research emphasizes the potential, but also the challenges, of industrial transfer learning. |
| first_indexed | 2024-03-11T05:25:11Z |
| format | Article |
| id | doaj.art-c68cbd1b1c7941fdad06741dcafae39c |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-11T05:25:11Z |
| publishDate | 2023-03-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-c68cbd1b1c7941fdad06741dcafae39c2023-11-17T17:35:28ZengMDPI AGSensors1424-82202023-03-01237363610.3390/s23073636Industrial Transfer Learning for Multivariate Time Series Segmentation: A Case Study on Hydraulic Pump Testing CyclesStefan Gaugel0Manfred Reichert1Bosch Rexroth AG, 89081 Ulm, GermanyInstitute of Databases and Information Systems, Ulm University, 89081 Ulm, GermanyIndustrial data scarcity is one of the largest factors holding back the widespread use of machine learning in manufacturing. To overcome this problem, the concept of transfer learning was developed and has received much attention in recent industrial research. This paper focuses on the problem of time series segmentation and presents the first in-depth research on transfer learning for deep learning-based time series segmentation on the industrial use case of end-of-line pump testing. In particular, we investigate whether the performance of deep learning models can be increased by pretraining the network with data from other domains. Three different scenarios are analyzed: source and target data being closely related, source and target data being distantly related, and source and target data being non-related. The results demonstrate that transfer learning can enhance the performance of time series segmentation models with respect to accuracy and training speed. The benefit can be most clearly seen in scenarios where source and training data are closely related and the number of target training data samples is lowest. However, in the scenario of non-related datasets, cases of negative transfer learning were observed as well. Thus, the research emphasizes the potential, but also the challenges, of industrial transfer learning.https://www.mdpi.com/1424-8220/23/7/3636time series segmentationdeep learningmultivariate time seriestransfer learningend-of-line testing |
| spellingShingle | Stefan Gaugel Manfred Reichert Industrial Transfer Learning for Multivariate Time Series Segmentation: A Case Study on Hydraulic Pump Testing Cycles Sensors time series segmentation deep learning multivariate time series transfer learning end-of-line testing |
| title | Industrial Transfer Learning for Multivariate Time Series Segmentation: A Case Study on Hydraulic Pump Testing Cycles |
| title_full | Industrial Transfer Learning for Multivariate Time Series Segmentation: A Case Study on Hydraulic Pump Testing Cycles |
| title_fullStr | Industrial Transfer Learning for Multivariate Time Series Segmentation: A Case Study on Hydraulic Pump Testing Cycles |
| title_full_unstemmed | Industrial Transfer Learning for Multivariate Time Series Segmentation: A Case Study on Hydraulic Pump Testing Cycles |
| title_short | Industrial Transfer Learning for Multivariate Time Series Segmentation: A Case Study on Hydraulic Pump Testing Cycles |
| title_sort | industrial transfer learning for multivariate time series segmentation a case study on hydraulic pump testing cycles |
| topic | time series segmentation deep learning multivariate time series transfer learning end-of-line testing |
| url | https://www.mdpi.com/1424-8220/23/7/3636 |
| work_keys_str_mv | AT stefangaugel industrialtransferlearningformultivariatetimeseriessegmentationacasestudyonhydraulicpumptestingcycles AT manfredreichert industrialtransferlearningformultivariatetimeseriessegmentationacasestudyonhydraulicpumptestingcycles |