Leveraging systems' non-linearity to tackle the scarcity of data in the design of Intelligent Fault Diagnosis Systems
arXiv:2606.20323v1 Announce Type: new Abstract: Deep Transfer Learning (DTL) allows for the efficient building of Intelligent Fault Diagnosis Systems (IFDS). On the other hand, DTL methods still heavily rely on large amounts of labelled data. Obtaining such an amount of data can be challenging when dealing with machines or structures faults. This document proposes a novel approach to the design of vibration-based IFDS using DTL in condition of strong data scarcity. A periodic multi-excitation level procedure leveraging intrinsic non-linearities of real-world systems is used to produce images t
The increasing complexity and autonomy of systems necessitates robust fault diagnosis, while the challenges of data scarcity in specialized domains remain a critical barrier for AI adoption.
This development addresses a fundamental limitation in applying advanced AI techniques to real-world industrial and critical infrastructure, where data collection is often difficult or expensive.
The ability to develop Intelligent Fault Diagnosis Systems with limited data using intrinsic system non-linearities could significantly broaden AI's application in high-stakes environments.
- · Industrial automation sector
- · Predictive maintenance companies
- · Deep Transfer Learning researchers
- · Traditional fault diagnosis methods
- · Companies reliant on massive datasets
More efficient and reliable maintenance systems in critical infrastructure and manufacturing.
Reduced operational downtime and increased safety in industries like aerospace, energy, and transportation.
Acceleration of autonomous system deployment due to enhanced self-diagnosis capabilities, reducing human intervention costs.
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.AI