Operating condition invariant representation learning for machine prognostics

Minjung Kim, Yusuke Hioka, Michael Witbrock,
Operating condition invariant representation learning for machine prognostics,
Knowledge-Based Systems,
Volume 330, Part B,
2025,
114623,
ISSN 0950-7051,
https://doi.org/10.1016/j.knosys.2025.114623.
(https://www.sciencedirect.com/science/article/pii/S0950705125016624)
Abstract: Condition monitoring (CM) data can readily become complex as machines undergo continuous variations in operating conditions. This complexity poses a significant challenge to learning discriminative health-state representations. A standard solution to it is to incorporate operational parameters into learning framework, but doing so can be costly and often infeasible if such data are not available in practice. To this end, we propose a novel framework for learning health-state representations that are inherently invariant to changes in operating conditions-without relying on operational parameters. The core principle of our Operating Condition-Invariant Representation (OCIR) model is rooted in the intuition that learning to disentangle a factor of variation in data naturally leads to learning to encode representations that are invariant to the disentangled factor. We adopt an unsupervised generative model to disentangle operating condition factors at the observation level, thereby inducing invariance at the sequence level. Simultaneously, we leverage the generative model as a source of self-supervision and train a predictive model alongside it by enforcing cycle consistency in the transformation of knowledge between the two models. Experimental results demonstrate that the health-state representations learned through OCIR are highly competitive with those learned using operational parameters, while significantly outperforming methods that do not utilize such information. Additionally, we introduce a novel method for construction of virtually stationary trajectories directly from the raw CM data subject to varying operating conditions.
Keywords: Machine prognostics; Rul estimation; Varying operating condition; Invariant representation; Trajectory construction