Unsupervised Hybrid Deep Learning for Unknown Bearing Fault Diagnosis and Severity Assessment

Edris Shamsulhaq, Fikri Arif Wicaksana

Abstract


This paper presents an unsupervised hybrid deep learning framework for unknown bearing fault diagnosis and severity assessment using vibration signals. The proposed framework combines Continuous Wavelet Transform (CWT), Convolutional Neural Networks (CNN), and Long Short-Term Memory (LSTM) autoencoders. Trained exclusively on 3,779 healthy data segments, the model detects anomalies via reconstruction error analysis evaluated across a total of 7,585 test segments. Experiments on the CWRU dataset show that the proposed hybrid model achieves competitive performance (AUC 0.990, accuracy 90.42%, and F1-score 89.57%) compared to spectral baselines, while uniquely preserving temporal dynamics—a critical advantage for non-stationary industrial environments. However, outer race faults were not reliably detected under the global threshold, which we report as a key limitation. A severity assessment and Health Index are also introduced for interpretable predictive maintenance.

Keywords


Unsupervised learning; bearing fault diagnosis; continuous wavelet transform; CNN-LSTM autoencoder; anomaly detection.

Full Text:

PDF

References


R. B. Randall, “Vibration-Based Condition Monitoring: Industrial, Aerospace and Automotive Applications,” Wiley, 2010, doi: 10.1002/9780470977668.

E. T. Chelmiah and D. F. Kavanagh, “Hilbert Marginal Spectrum for Failure Mode Diagnosis of Rotating Machines,” IECON 2021, doi: 10.1109/IECON48115.2021.9589472.

A. Nejadpak and C. X. Yang, “A vibration-based diagnostic tool for analysis of superimposed failures in electric machines,” IEEE EIT 2016, pp. 324–329, doi: 10.1109/EIT.2016.7535260.

M. R. Islam et al., “Explainable Multi-Stage Self-Supervised Learning Framework for Intelligent Fault Diagnosis,” AIACT 2026, doi: 10.1145/3795496.3795710.

M. Xia et al., “Intelligent fault diagnosis approach with unsupervised feature learning by stacked denoising autoencoder,” IET Sci., Meas. Technol., vol. 11, no. 6, pp. 687–695, 2017.

D. Li et al., “Identifying Unseen Faults for Smart Buildings by Incorporating Expert Knowledge With Data,” IEEE Trans. Autom. Sci. Eng., vol. 16, no. 3, pp. 1412–1425, 2019.

K. Jaskie et al., “PV Fault Detection Using Positive Unlabeled Learning,” Applied Sciences, vol. 11, no. 12, p. 5599, 2021.

R. Boudiaf et al., “Bearing fault diagnosis in induction motor using CWT and CNN,” IJPEDS, vol. 15, no. 1, pp. 591–602, 2024.

M. F. Siddique et al., “A Hybrid Deep Learning Approach for Bearing Fault Diagnosis Using CWT and Attention-Enhanced Spatiotemporal Feature Extraction,” Sensors, vol. 25, no. 9, p. 2712, 2025.

D. Lee et al., “GCN-Based LSTM Autoencoder with Self-Attention for Bearing Fault Diagnosis,” Sensors, vol. 24, no. 15, p. 4855, 2024.

B. Yuan et al., “Efficient Gearbox Fault Diagnosis Based on Improved Multi-Scale CNN with Lightweight Convolutional Attention,” Sensors, vol. 25, no. 9, p. 2636, 2025.

K. H. Park et al., “Unsupervised Fault Detection on UAVs: Encoding and Thresholding Approach,” Sensors, vol. 21, no. 6, p. 2208, 2021.

B. Zhang et al., “A hybrid approach combining deep learning and signal processing for bearing fault diagnosis under imbalanced samples,” Scientific Reports, vol. 15, p. 13606, 2025.

CWRU Bearing Data Center, "Ball bearing test data for normal and faulty bearings," Case Western Reserve University, 2015. [Online]. Available: https://engineering.case.edu/bearingdatacenter

N. G. Nikolaou and I. A. Antoniadis, “Demodulation of vibration signals from defects in rolling element bearings using complex shifted Morlet wavelets,” Mech. Syst. Signal Process., vol. 16, no. 4, pp. 677–694, 2002.

S. Mallat, A Wavelet Tour of Signal Processing: The Sparse Way. Academic Press, 2008.

F. Pukelsheim, “The Three Sigma Rule,” The American Statistician, vol. 48, no. 2, p. 88, 1994.

G. E. Ophel et al., “An Analysis of Hertzian Contact and Inner Race Crack-Induced Vibrations,” Engineering, Technology & Applied Science Research, vol. 15, no. 6, pp. 28680–28686, 2025.

P. Bordush, “Maintenance, Engineering, and Operational Decision-Making Metrics Derived from Simple Maintenance Datasets,” Annual Conf. PHM Society, vol. 17, no. 1, 2025.




DOI: https://doi.org/10.37905/jjeee.v8i2.39120

Refbacks

  • There are currently no refbacks.


Creative Commons License
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.

Published by:
Electrical Engineering Department
Faculty of Engineering
State University of Gorontalo
Jalan B.J.Habibie Desa Moutong Kecamatan Tilongkabila Kabupaten Bone Bolango
Telp. 0435-821175; 081340032063
Email: [email protected]/[email protected]

Creative Commons License

This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.