Journal of Sensors and Sensor Systems
Journal of Sensors and Sensor Systems
JSSS
Articles | Volume 14, issue 2
Articles | Volume 14, issue 2
https://doi.org/10.5194/jsss-14-119-2025
© Author(s) 2025. This work is distributed under
the Creative Commons Attribution 4.0 License.
https://doi.org/10.5194/jsss-14-119-2025
© Author(s) 2025. This work is distributed under
the Creative Commons Attribution 4.0 License.
Articles | Volume 14, issue 2
Regular research article
 | 
04 Jul 2025
Regular research article |  | 04 Jul 2025

Domain shifts in industrial condition monitoring: a comparative analysis of automated machine learning models

Payman Goodarzi, Andreas Schütze, and Tizian Schneider

Data sets

CWRU Bearing Dataset (CWRU), Case Western Reserve University CWRU https://engineering.case.edu/bearingdatacenter/download-data-file

Condition monitoring of hydraulic systems Data Set at ZeMA T. Schneider et al. https://doi.org/10.5281/zenodo.1323611

Sensor data set, electromechanical cylinder at ZeMA testbed (2 kHz) S. Klein https://doi.org/10.5281/zenodo.3929384

Temperature Affected Guided Wave Propagation in a Composite Plate Complementing the Open Guided Waves Platform J. Moll et al. https://doi.org/10.6084/m9.figshare.9863465.v2

Paderborn University Bearing Dataset (PU) Paderborn University https://groups.uni-paderborn.de/kat/BearingDataCenter/

LMT-ML-Toolbox ZeMA-gGmbH https://github.com/ZeMA-gGmbH/LMT-ML-Toolbox/blob/main/naph.mat

Download
Short summary
Selecting the best model for monitoring industrial machines is challenging due to limited data and varying conditions. While deep learning (DL) is often considered ideal, it does not always perform well. We compared DL with traditional methods focused on feature extraction and classification. Our tests on seven datasets revealed that traditional methods are more reliable when machine conditions change, highlighting the importance of simpler, interpretable models for industrial monitoring.
Read more
Share