Reliability-Calibrated Edge-IoT Early Fault Warning for Rotating Machinery with a Physics-Guided Tiny-Mamba Transformer
arXiv:2601.21293v3 Announce Type: replace Abstract: Industrial Internet of Things (IIoT) systems increasingly rely on distributed vibration sensing to support predictive maintenance of rotating machinery. In practical deployments, however, raw signal upload is costly and alarm decisions must be made locally under limited computation, changing operating conditions, and strict nuisance-alarm budgets. This paper presents a reliability-calibrated edge-IoT early-warning framework, in which a compact Physics-Guided Tiny-Mamba Transformer (PG-TMT) acts as the representation module and an extreme valu
The increasing reliance on IIoT systems for predictive maintenance necessitates efficient and reliable edge computing solutions for real-time fault detection.
This development allows for more effective and cost-efficient predictive maintenance in industrial settings, reducing downtime and operational costs.
The ability to perform sophisticated fault detection directly at the edge with high reliability reduces bandwidth needs and enables faster responses in critical machinery.
- · Industrial IoT hardware manufacturers
- · Predictive maintenance startups
- · Manufacturing sector
- · AI model developers for edge devices
- · Legacy central cloud-based analytics providers
- · Traditional preventative maintenance services
Widespread adoption of edge-based AI for industrial anomaly detection.
Increased efficiency and reduced operational overhead in heavy industries globally.
Shift in industrial workforce toward AI-driven maintenance oversight rather than manual diagnostics.
This signal links to a primary source. Continuum Brief monitors and indexes it as part of the live intelligence stream — we do not republish source content.
Read at arXiv cs.LG