Research

Paper

AI LLM March 24, 2026

MsFormer: Enabling Robust Predictive Maintenance Services for Industrial Devices

Authors

Jiahui Zhou, Dan Li, Ruibing Jin, Jian Lou, Yanran Zhao, Zhenghua Chen, Zigui Jiang, See-Kiong Ng

Abstract

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).

Metadata

arXiv ID: 2603.23076
Provider: ARXIV
Primary Category: cs.LG
Published: 2026-03-24
Fetched: 2026-03-25 06:02

Related papers

Raw Data (Debug)
{
  "raw_xml": "<entry>\n    <id>http://arxiv.org/abs/2603.23076v1</id>\n    <title>MsFormer: Enabling Robust Predictive Maintenance Services for Industrial Devices</title>\n    <updated>2026-03-24T11:12:50Z</updated>\n    <link href='https://arxiv.org/abs/2603.23076v1' rel='alternate' type='text/html'/>\n    <link href='https://arxiv.org/pdf/2603.23076v1' rel='related' title='pdf' type='application/pdf'/>\n    <summary>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).</summary>\n    <category scheme='http://arxiv.org/schemas/atom' term='cs.LG'/>\n    <published>2026-03-24T11:12:50Z</published>\n    <arxiv:primary_category term='cs.LG'/>\n    <author>\n      <name>Jiahui Zhou</name>\n    </author>\n    <author>\n      <name>Dan Li</name>\n    </author>\n    <author>\n      <name>Ruibing Jin</name>\n    </author>\n    <author>\n      <name>Jian Lou</name>\n    </author>\n    <author>\n      <name>Yanran Zhao</name>\n    </author>\n    <author>\n      <name>Zhenghua Chen</name>\n    </author>\n    <author>\n      <name>Zigui Jiang</name>\n    </author>\n    <author>\n      <name>See-Kiong Ng</name>\n    </author>\n  </entry>"
}