Document Type
Conference Paper
Publication Date
2026
DOI
10.1016/j.mfglet.2026.07.019
Publication Title
Manufacturing Letters
Volume
49
Pages
98-109
Conference Name
54th SME North American Manufacturing Research Conference (NAMRC 54 2026), 14-18 June 2026, State College, Pennsylvania
Abstract
Accurate and reliable bearing fault diagnosis is critical for the safe and efficient operation of rotating machinery. Conventional time–frequency (TF) analysis techniques, such as the short-time Fourier transform (STFT), are limited by their fixed window sizes and the inherent trade-off between time and frequency resolution, often leading to suboptimal fault representation under varying operating conditions. To address these challenges, this paper proposes a deep learning-based framework that reconstructs high-resolution, noise-robust TF representations directly from raw vibration signals. The proposed model integrates a denoising encoder with a learnable TF transformation network to adaptively capture fault related frequency patterns without manual parameter tuning. The proposed model’s performance is evaluated using multiple CNN-based classifiers on two benchmark datasets: Case Western Reserve University (CWRU) and HUST. Experimental results demonstrate that the proposed approach achieves superior classification performance, with improvements of up to 1.5 2% in accuracy and F1-score over HRSpecNet, and over 13% compared to TFA-Net. These results confirm the proposed model’s ability to generate discriminative, high-resolution TF representations suitable for intelligent bearing-fault analysis and real-time industrial predictive maintenance.
Rights
© 2026 The Authors.
This is an open access article under the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International (CC BY-NC-ND 4.0) License.
Original Publication Citation
Biswas, S., Tushar, S. R., Karim, M. E., Mamun, A. A., & Bappy, M. M. (2026). Deep learning-based high-resolution spectrogram reconstruction for robust bearing fault diagnosis. Manufacturing Letters, 49, 98-109. https://doi.org/10.1016/j.mfglet.2026.07.019
Repository Citation
Biswas, Sabyasachi; Tushar, Saifur Rahman; Karim, Md Ebtidaul; Mamun, Abdullah Alam; and Bappy, Mahathir Mohammad, "Deep Learning-Based High-Resolution Spectrogram Reconstruction for Robust Bearing Fault Diagnosis" (2026). Engineering Technology Faculty Publications. 292.
https://digitalcommons.odu.edu/engtech_fac_pubs/292