Progressive Physics-AI Hybrid Methodology for Unsupervised Anomaly Detection in Electromechanical Systems
##plugins.themes.bootstrap3.article.main##
##plugins.themes.bootstrap3.article.sidebar##
Abstract
Physics-informed machine learning has emerged as a promising
paradigm for industrial health monitoring, yet practical
guidance on when and how to integrate domain knowledge
into detection pipelines remains limited. This paper proposes
a structured methodology for progressive physics integration
in unsupervised anomaly detection, organised into three levels
of increasing depth: data-driven baselines (Level 0), operational
conditioning (Level 1), and structural physics injection
(Level 2). The methodology is designed for systems
where qualitative expert knowledge is available but no quantitative
degradation model exists. It is applied systematically
across three method families—statistical envelopes, principal
component analysis, isolation forests, deterministic autoencoders,
and variational autoencoders—for the monitoring of
medium-voltage circuit breaker coil currents. At the highest integration
level, a physics-informed conditional variational autoencoder
(PicVAE) incorporates domain knowledge through
phase-segmented inputs, FiLM-conditioned architecture, and
a phase-weighted reconstruction loss. Validated on real operational
data with expert-labelled anomalies, the results reveal
two findings: operational conditioning at Level 1 consistently
improves detection across all method families, while structural
physics injection at Level 2 has a method-dependent impact,
yielding clear gains for phase-aware representation learning
while introducing trade-offs for simpler models. The PhD
plan extends this work along three axes: quantitative physics
integration on a second use case, cross-domain validation on
public benchmarks through a human-in-the-loop knowledge
acquisition protocol, and consolidation of the methodology
[Melvin Fernandes Novo] et al. This is an open-access article distributed under
the terms of the Creative Commons Attribution 3.0 United States License,
which permits unrestricted use, distribution, and reproduction in any medium,
provided the original author and source are credited.
into a transferable deployment framework.
How to Cite
##plugins.themes.bootstrap3.article.details##
electromechanical, hybridization, health monitoring, deep learning, physics, prognostic, coil current, circuit breaker
This work is licensed under a Creative Commons Attribution 3.0 Unported License.
The Prognostic and Health Management Society advocates open-access to scientific data and uses a Creative Commons license for publishing and distributing any papers. A Creative Commons license does not relinquish the author’s copyright; rather it allows them to share some of their rights with any member of the public under certain conditions whilst enjoying full legal protection. By submitting an article to the International Conference of the Prognostics and Health Management Society, the authors agree to be bound by the associated terms and conditions including the following:
As the author, you retain the copyright to your Work. By submitting your Work, you are granting anybody the right to copy, distribute and transmit your Work and to adapt your Work with proper attribution under the terms of the Creative Commons Attribution 3.0 United States license. You assign rights to the Prognostics and Health Management Society to publish and disseminate your Work through electronic and print media if it is accepted for publication. A license note citing the Creative Commons Attribution 3.0 United States License as shown below needs to be placed in the footnote on the first page of the article.
First Author et al. This is an open-access article distributed under the terms of the Creative Commons Attribution 3.0 United States License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.