EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Fault Diagnosis of Rotating Machinery Using Supervised Machine Learning Algorithms with Integrated Data-Driven and Physics-Informed Feature Sets

Anastasija Angjusheva Ignjatovska iD, Zlatko Petreski, Viktor Gavriloski, Dejan Shishkovski iD, Simona Domazetovska Markovska iD, Maja Anachkova, Damjan Pecioski

Sensors · 17.03.2026 · 26 (6) · 1876

DOI: 10.3390/s26061876 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 17.03.2026. Verfasst von Anastasija Angjusheva Ignjatovska und 6 weiteren Autor:innen. Beteiligte Einrichtung: Faculty of Mechanical Engineering Skopje, Ss. Cyril and Methodius University in Skopje, 1000 Skopje, North Macedonia. Die Arbeit wurde bisher 8-mal zitiert (Crossref) und nennt 82 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Ministry of Education of North Macedonia.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

This study proposes a supervised machine learning framework for vibration-based fault diagnosis of rotating machinery using integrated data-driven and physics-informed feature sets. A dataset acquired under variable load and multiple operating conditions was used for model training. Parallel signal processing techniques were applied to capture fault-related information across multiple frequency bands including time-domain analysis, frequency-domain analysis, baseband analysis, and envelope analysis. From the corresponding signal representations, statistical, spectral, and physics-based features associated with characteristic fault frequencies were extracted and combined into integrated feature sets. The diagnostic performance of models trained using purely data-driven features was systematically compared with models incorporating integrated data-driven and physics-informed features. Support Vector Machine, Random Forests, Gradient Boosting, and an ensemble classifier were evaluated using accuracy, precision, recall, and F1-score metrics. The proposed framework employs a two-layer classification strategy, where the first layer performs multiclass fault identification, while the second layer evaluates the presence of imbalance as a coexisting fault. In addition, the influence of different feature groups as well as individual measurement axes and their combinations on diagnostic performance were analyzed. Validation using a new dataset measured in laboratory conditions confirmed the robustness and generalization capability of the proposed diagnostic framework.

Schlagwörter

Stichwörter der Autor:innen

data-driven featuresfault diagnosisphysics-informed featuresrotating machinerysupervised machine learningvibration analysis

Autor:innen und Institutionen

  • Faculty of Mechanical Engineering Skopje, Ss. Cyril and Methodius University in Skopje, 1000 Skopje, North Macedonia.

ORCID-Profile: Anastasija Angjusheva Ignjatovska, Dejan Shishkovski, Simona Domazetovska Markovska

Förderung

  • Ministry of Education of North Macedonia

Zitieren

APA

Ignjatovska, A. A., Petreski, Z., Gavriloski, V., Shishkovski, D., Domazetovska Markovska, S., Anachkova, M., & Pecioski, D. (2026). Fault Diagnosis of Rotating Machinery Using Supervised Machine Learning Algorithms with Integrated Data-Driven and Physics-Informed Feature Sets. Sensors, 26(6), 1876. https://doi.org/10.3390/s26061876

Vancouver

Ignjatovska AA, Petreski Z, Gavriloski V, Shishkovski D, Domazetovska Markovska S, Anachkova M, et al. Fault Diagnosis of Rotating Machinery Using Supervised Machine Learning Algorithms with Integrated Data-Driven and Physics-Informed Feature Sets. Sensors. 2026;26(6):1876. doi:10.3390/s26061876

BibTeX
@article{Ignjatovska2026,
  author = {Ignjatovska, Anastasija Angjusheva and Petreski, Zlatko and Gavriloski, Viktor and Shishkovski, Dejan and Domazetovska Markovska, Simona and Anachkova, Maja and Pecioski, Damjan},
  title = {Fault Diagnosis of Rotating Machinery Using Supervised Machine Learning Algorithms with Integrated Data-Driven and Physics-Informed Feature Sets},
  journal = {Sensors},
  year = {2026},
  volume = {26},
  number = {6},
  pages = {1876},
  doi = {10.3390/s26061876}
}
Kostenlos starten →