Saved in:
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2408.00516 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911974625902592 |
|---|---|
| author | Vasilache, Alexandru Nitzsche, Sven Floegel, Daniel Schuermann, Tobias von Dosky, Stefan Bierweiler, Thomas Mußler, Marvin Kälber, Florian Hohmann, Soeren Becker, Juergen |
| author_facet | Vasilache, Alexandru Nitzsche, Sven Floegel, Daniel Schuermann, Tobias von Dosky, Stefan Bierweiler, Thomas Mußler, Marvin Kälber, Florian Hohmann, Soeren Becker, Juergen |
| contents | The advancements in smart sensors for Industry 4.0 offer ample opportunities for low-powered predictive maintenance and condition monitoring. However, traditional approaches in this field rely on processing in the cloud, which incurs high costs in energy and storage. This paper investigates the potential of neural networks for low-power on-device computation of vibration sensor data for predictive maintenance. We review the literature on Spiking Neural Networks (SNNs) and Artificial Neuronal Networks (ANNs) for vibration-based predictive maintenance by analyzing datasets, data preprocessing, network architectures, and hardware implementations. Our findings suggest that no satisfactory standard benchmark dataset exists for evaluating neural networks in predictive maintenance tasks. Furthermore frequency domain transformations are commonly employed for preprocessing. SNNs mainly use shallow feed forward architectures, whereas ANNs explore a wider range of models and deeper networks. Finally, we highlight the need for future research on hardware implementations of neural networks for low-power predictive maintenance applications and the development of a standardized benchmark dataset. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2408_00516 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Low-Power Vibration-Based Predictive Maintenance for Industry 4.0 using Neural Networks: A Survey Vasilache, Alexandru Nitzsche, Sven Floegel, Daniel Schuermann, Tobias von Dosky, Stefan Bierweiler, Thomas Mußler, Marvin Kälber, Florian Hohmann, Soeren Becker, Juergen Machine Learning The advancements in smart sensors for Industry 4.0 offer ample opportunities for low-powered predictive maintenance and condition monitoring. However, traditional approaches in this field rely on processing in the cloud, which incurs high costs in energy and storage. This paper investigates the potential of neural networks for low-power on-device computation of vibration sensor data for predictive maintenance. We review the literature on Spiking Neural Networks (SNNs) and Artificial Neuronal Networks (ANNs) for vibration-based predictive maintenance by analyzing datasets, data preprocessing, network architectures, and hardware implementations. Our findings suggest that no satisfactory standard benchmark dataset exists for evaluating neural networks in predictive maintenance tasks. Furthermore frequency domain transformations are commonly employed for preprocessing. SNNs mainly use shallow feed forward architectures, whereas ANNs explore a wider range of models and deeper networks. Finally, we highlight the need for future research on hardware implementations of neural networks for low-power predictive maintenance applications and the development of a standardized benchmark dataset. |
| title | Low-Power Vibration-Based Predictive Maintenance for Industry 4.0 using Neural Networks: A Survey |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2408.00516 |