Differentiable Short-Time Fourier Transform Window Length Selection Driven by Cyclo-Stationarity
##plugins.themes.bootstrap3.article.main##
##plugins.themes.bootstrap3.article.sidebar##
http://orcid.org/0000-0002-2650-7120
Konstantinos Gryllias
Abstract
The Short-Time Fourier transform is widely applied in the condition monitoring of rotating machinery. Even so, selecting the optimal window length for the Short-Time Fourier Transform remains a challenge. This work presents a procedure for adapting the Short Time Fourier Transform algorithm to be differentiable with respect to window length by using continuous window functions defined over the entire input signal duration. Thanks to this modification, a differentiable loss criterion can be defined to measure the Short-Time Fourier quality, and the gradient of the loss criterion with respect to window length can be computed. The optimal window length for a given loss criterion can then be efficiently solved for using a gradient-based optimization algorithm. Results from a simulated bearing dataset and three experimental bearing datasets are used to compare the optimal spectrograms obtained using different loss criteria. Specifically, a sparsity-based loss criterion is compared with two loss criteria inspired by the characteristic cyclo-stationarity machine of faults in rotating machinery. The results demonstrate the effectiveness of the differentiable window length selection method and highlight the importance of selecting appropriate loss criteria for defining STFT quality. Loss criteria that account for the cyclo-stationary nature of the signals are shown to be less likely to target single high-amplitude impulsive events compared to the sparsity-based loss criterion.
How to Cite
##plugins.themes.bootstrap3.article.details##
bearing, condition monitoring, differentiable, short-time Fourier Transform, cyclo-stationary
987–1036. doi: 10.1016/j.ymssp.2008.10.010
Antoni, J., Xin, G., & Hamzaoui, N. (2017, August). Fast computation of the spectral correlation. Mechanical Systems and Signal Processing, 92, 248–277. doi: 10.1016/j.ymssp.2017.01.011
Case Western Reserve University Bearing dataset. (n.d.). https://engineering.case.edu/bearingdatacenter.
Czerwinski, R., & Jones, D. (1997, February). Adaptive short-time Fourier analysis. IEEE Signal Processing Letters, 4(2), 42–45. doi: 10.1109/97.554468
Fang, B., Hu, J., Yang, C., Cao, Y., & Jia, M. (2022, February). A blind deconvolution algorithm based on backward automatic differentiation and its application to rolling bearing fault diagnosis. Measurement Science and Technology, 33(2), 025009. doi: 10.1088/1361-6501/ac3fc7
Leiber, M., Barrau, A., Marnissi, Y., & Abboud, D. (2022, August). A differentiable short-time Fourier transform with respect to the window length. In 2022 30th European Signal Processing Conference (EUSIPCO) (pp. 1392–1396). Belgrade, Serbia: IEEE. doi: 10.23919/EUSIPCO55093.2022.9909963
Leiber, M., Marnissi, Y., Barrau, A., & Badaoui, M. E. (2023, June). Differentiable Adaptive Short-Time Fourier Transform with Respect to the Window Length. In ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) (pp. 1–5). doi: 10.1109/ICASSP49357.2023.10095245
Mateo, C., & Talavera, J. A. (2018, June). Short-time Fourier transform with the window size fixed in the frequency domain. Digital Signal Processing, 77, 13–21. doi: 10.1016/j.dsp.2017.11.003
McFadden, P., & Smith, J. (1984, September). Model for the vibration produced by a single point defect in a rolling element bearing. Journal of Sound and Vibration, 96(1), 69–82. doi: 10.1016/0022460X(84)90595-9
Paszke, A., Gross, S., Chintala, S., Chanan, G., Yang, E., DeVito, Z., … Lerer, A. (2017). Automatic differentiation in PyTorch. In NIPSW.
Qiu, H., Lee, J., Lin, J., & Yu, G. (2006, February). Wavelet filter-based weak signature detection method and its application on rolling element bearing prognostics. Journal of Sound and Vibration, 289(4-5), 1066–1090. doi: 10.1016/j.jsv.2005.03.007
Wodecki, J., Michalak, A., & Zimroz, R. (2021, February). Local damage detection based on vibration data analysis in the presence of Gaussian and heavy-tailed impulsive noise. Measurement, 169, 108400. doi: 10.1016/j.measurement.2020.108400
Xie, H., Lin, J., Lei, Y., & Liao, Y. (2012, July). Fast-varying AM–FM components extraction based on an adaptive STFT. Digital Signal Processing, 22(4), 664–670. doi: 10.1016/j.dsp.2012.02.007
Zhao, A., Subramani, K., & Smaragdis, P. (2021, June). Optimizing Short-Time Fourier Transform Parameters via Gradient Descent. In ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) (pp. 736– 740). doi: 10.1109/ICASSP39728.2021.9413704
This work is licensed under a Creative Commons Attribution 3.0 Unported License.
The Prognostic and Health Management Society advocates open-access to scientific data and uses a Creative Commons license for publishing and distributing any papers. A Creative Commons license does not relinquish the author’s copyright; rather it allows them to share some of their rights with any member of the public under certain conditions whilst enjoying full legal protection. By submitting an article to the International Conference of the Prognostics and Health Management Society, the authors agree to be bound by the associated terms and conditions including the following:
As the author, you retain the copyright to your Work. By submitting your Work, you are granting anybody the right to copy, distribute and transmit your Work and to adapt your Work with proper attribution under the terms of the Creative Commons Attribution 3.0 United States license. You assign rights to the Prognostics and Health Management Society to publish and disseminate your Work through electronic and print media if it is accepted for publication. A license note citing the Creative Commons Attribution 3.0 United States License as shown below needs to be placed in the footnote on the first page of the article.
First Author et al. This is an open-access article distributed under the terms of the Creative Commons Attribution 3.0 United States License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.