Distinctive Contribution of Sound Spectral Features in Enhancing Vibration-Based Multi-Component Fault Classification Under Non-Stationary Speed Conditions

• Published in: IEEE access Vol. 13; pp. 126261 - 126278
• Main Authors: Sowmya, S., Saimurugan, M., Venkatesh, Naveen
• Format: Journal Article
• Language: English
• Published: IEEE 2025
• Subjects: Accuracy; Artificial neural networks; Drift och underhållsteknik; Fault diagnosis; Feature extraction; Gears; machine learning; Mathematical models; Mel frequency cepstral coefficient; multi-component; Operation and Maintenance Engineering; Shafts; soundsignals; Time-frequency analysis; variable speed condition monitoring; vibration signals; Vibrations
• ISSN: 2169-3536; 2169-3536
• DOI: 10.1109/ACCESS.2025.3587652

Rotational machines under variable speed conditions often confront challenges to diagnose various component faults as an existing problem with less exploration of sound signals in this subject area. This premise motivates the paper to contribute the prodigious sound signal features to the vibration-based multi-component fault recognition at speeds ranging from 200 to 2200 rpm. With this novelty, as an added innovation, how each signal-based metric is influencing the classification of different faults in each component is examined. To begin with, speed synchronizing instantaneous frequency (IF) with two signal envelopes of vibration signals are individually fed to the machine learning (ML) classifier, such as Decision Tree (DT), Support Vector Machine-Radial Basis Function (SVM-RBF), and Artificial Neural Network (ANN), to verify the model performance. It is realized that the shaft is highly misclassified by fusing these vibration signal features. To enhance the ML effects and also to reduce the shaft's misclassification, sound signal features such as Mel Frequency Cepstral Coefficients (MFCCs), spectral centroid, and zero-crossing rate are incorporated to evidence its significance. Besides this feature fusion, the comparison of vibration and sound data properties for bearing, gear, and shaft proves the effectiveness of sound-based parameters towards shaft and gear classification but less impact on bearings. Further reassessment of sound spectral attributes in differentiating gear faults clarifies its utility through SHAP, cross-domain adaptation, covariance, and correlation analysis. This imparts an interpretation of integrating vibration- and sound-based features, which attains 83.84% classification accuracy for ANN with a better F1 score than vibration-based features. Thus, distinctively integrating the sound spectral attributes to the vibration signal features under varying speeds demonstrates an improvement in multi-component fault prediction.