TinyML Towards Industry 4.0: Resource-Efficient Process Monitoring of a Milling Machine
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866911117059555328 |
|---|---|
| author | Langer, Tim Widra, Matthias Beyer, Volkhard |
| author_facet | Langer, Tim Widra, Matthias Beyer, Volkhard |
| contents | In the context of industry 4.0, long-serving industrial machines can be retrofitted with process monitoring capabilities for future use in a smart factory. One possible approach is the deployment of wireless monitoring systems, which can benefit substantially from the TinyML paradigm. This work presents a complete TinyML flow from dataset generation, to machine learning model development, up to implementation and evaluation of a full preprocessing and classification pipeline on a microcontroller. After a short review on TinyML in industrial process monitoring, the creation of the novel MillingVibes dataset is described. The feasibility of a TinyML system for structure-integrated process quality monitoring could be shown by the development of an 8-bit-quantized convolutional neural network (CNN) model with 12.59kiB parameter storage. A test accuracy of 100.0% could be reached at 15.4ms inference time and 1.462mJ per quantized CNN inference on an ARM Cortex M4F microcontroller, serving as a reference for future TinyML process monitoring solutions. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2508_16553 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | TinyML Towards Industry 4.0: Resource-Efficient Process Monitoring of a Milling Machine Langer, Tim Widra, Matthias Beyer, Volkhard Machine Learning Computer Vision and Pattern Recognition Emerging Technologies Systems and Control Signal Processing I.2.1; I.5.4; C.5.3; C.3 In the context of industry 4.0, long-serving industrial machines can be retrofitted with process monitoring capabilities for future use in a smart factory. One possible approach is the deployment of wireless monitoring systems, which can benefit substantially from the TinyML paradigm. This work presents a complete TinyML flow from dataset generation, to machine learning model development, up to implementation and evaluation of a full preprocessing and classification pipeline on a microcontroller. After a short review on TinyML in industrial process monitoring, the creation of the novel MillingVibes dataset is described. The feasibility of a TinyML system for structure-integrated process quality monitoring could be shown by the development of an 8-bit-quantized convolutional neural network (CNN) model with 12.59kiB parameter storage. A test accuracy of 100.0% could be reached at 15.4ms inference time and 1.462mJ per quantized CNN inference on an ARM Cortex M4F microcontroller, serving as a reference for future TinyML process monitoring solutions. |
| title | TinyML Towards Industry 4.0: Resource-Efficient Process Monitoring of a Milling Machine |
| topic | Machine Learning Computer Vision and Pattern Recognition Emerging Technologies Systems and Control Signal Processing I.2.1; I.5.4; C.5.3; C.3 |
| url | https://arxiv.org/abs/2508.16553 |