Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2603.23076 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914417453563904 |
|---|---|
| author | Zhou, Jiahui Li, Dan Jin, Ruibing Lou, Jian Zhao, Yanran Chen, Zhenghua Jiang, Zigui Ng, See-Kiong |
| author_facet | Zhou, Jiahui Li, Dan Jin, Ruibing Lou, Jian Zhao, Yanran Chen, Zhenghua Jiang, Zigui Ng, See-Kiong |
| contents | Providing reliable predictive maintenance is a critical industrial AI service essential for ensuring the high availability of manufacturing devices. Existing deep-learning methods present competitive results on such tasks but lack a general service-oriented framework to capture complex dependencies in industrial IoT sensor data. While Transformer-based models show strong sequence modeling capabilities, their direct deployment as robust AI services faces significant bottlenecks. Specifically, streaming sensor data collected in real-world service environments often exhibits multi-scale temporal correlations driven by machine working principles. Besides, the datasets available for training time-to-failure predictive services are typically limited in size. These issues pose significant challenges for directly applying existing models as robust predictive services. To address these challenges, we propose MsFormer, a lightweight Multi-scale Transformer designed as a unified AI service model for reliable industrial predictive maintenance. MsFormer incorporates a Multi-scale Sampling (MS) module and a tailored position encoding mechanism to capture sequential correlations across multi-streaming service data. Additionally, to accommodate data-scarce service environments, MsFormer adopts a lightweight attention mechanism with straightforward pooling operations instead of self-attention. Extensive experiments on real-world datasets demonstrate that the proposed framework achieves significant performance improvements over state-of-the-art methods. Furthermore, MsFormer outperforms across industrial devices and operating conditions, demonstrating strong generalizability while maintaining a highly reliable Quality of Service (QoS). |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_23076 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | MsFormer: Enabling Robust Predictive Maintenance Services for Industrial Devices Zhou, Jiahui Li, Dan Jin, Ruibing Lou, Jian Zhao, Yanran Chen, Zhenghua Jiang, Zigui Ng, See-Kiong Machine Learning Providing reliable predictive maintenance is a critical industrial AI service essential for ensuring the high availability of manufacturing devices. Existing deep-learning methods present competitive results on such tasks but lack a general service-oriented framework to capture complex dependencies in industrial IoT sensor data. While Transformer-based models show strong sequence modeling capabilities, their direct deployment as robust AI services faces significant bottlenecks. Specifically, streaming sensor data collected in real-world service environments often exhibits multi-scale temporal correlations driven by machine working principles. Besides, the datasets available for training time-to-failure predictive services are typically limited in size. These issues pose significant challenges for directly applying existing models as robust predictive services. To address these challenges, we propose MsFormer, a lightweight Multi-scale Transformer designed as a unified AI service model for reliable industrial predictive maintenance. MsFormer incorporates a Multi-scale Sampling (MS) module and a tailored position encoding mechanism to capture sequential correlations across multi-streaming service data. Additionally, to accommodate data-scarce service environments, MsFormer adopts a lightweight attention mechanism with straightforward pooling operations instead of self-attention. Extensive experiments on real-world datasets demonstrate that the proposed framework achieves significant performance improvements over state-of-the-art methods. Furthermore, MsFormer outperforms across industrial devices and operating conditions, demonstrating strong generalizability while maintaining a highly reliable Quality of Service (QoS). |
| title | MsFormer: Enabling Robust Predictive Maintenance Services for Industrial Devices |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2603.23076 |