Fault Diagnosis of Rotating Machinery Using Supervised Machine Learning Algorithms with Integrated Data-Driven and Physics-Informed Feature Sets
Journal
Sensors
Date Issued
2026-03-17
Author(s)
Ignjatovska, Anastasija Angjusheva
Shishkovski, Dejan
Domazetovska Markovska, Simona
Pecioski, Damjan
DOI
10.3390/s26061876
Abstract
This study proposes a supervised machine learning framework for vibration-based fault diagnosis of rotating machinery using integrated data-driven and physics-informed fea-ture 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 analy-sis, frequency-domain analysis, baseband analysis, and envelope analysis. From the cor-responding signal representations, statistical, spectral, and physics-based features associ-ated with characteristic fault frequencies were extracted and combined into integrated feature sets. The diagnostic performance of models trained using purely data-driven fea-tures 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 con-ditions confirmed the robustness and generalization capability of the proposed diagnostic framework.
File(s)![Thumbnail Image]()
Loading...
Name
sensors-26-01876.pdf
Size
4.65 MB
Format
Adobe PDF
Checksum
(MD5):b6a73287edb49052314283ba96497a2b