A Prognostics Approach for Gearbox based on Spectrogram and Deep Learning
PHM Society Asia-Pacific Conference · 2017
DOI: 10.36001/phmap.2017.v1i1.1681 ↗Kurz gefasst
Fachartikel in der Zeitschrift PHM Society Asia-Pacific Conference, 2017. Verfasst von Dengwei Song und 5 weiteren Autor:innen.
Abstract (Originalsprache)
This paper presents a method and solution for Asia Pacific Conference of the Prognostics and Health Management 2017 Data Challenge. Considering the complex of gearbox signal, a novel approach utilizing spectrogram and deep learning is proposed. Spectrogram can transform the raw signal into time-frequency space that is an effective method to process vibration signal of gearbox. Deep learning is a useful method that has the ability of automatically feature learning. The spectrogram is obtained by using short-time Fourier transform (STFT). Then, the way of the stacked auto-encoders (SAE), is trained to auto-extract feature and realize the prediction. For diagnosis, the cepstrum algorithm is performed to simplify the spectrum and find the most severely-degraded component. This solution earned the 3rd highest score of the results from all teams in the competition, which demonstrate the effective of proposed method.
Zitieren
APA
Song, D., Su, H., Ma, J., Chao, L., Ding, Y., & Lu, C. (2017). A Prognostics Approach for Gearbox based on Spectrogram and Deep Learning. PHM Society Asia-Pacific Conference. https://doi.org/10.36001/phmap.2017.v1i1.1681
Vancouver
Song D, Su H, Ma J, Chao L, Ding Y, Lu C. A Prognostics Approach for Gearbox based on Spectrogram and Deep Learning. PHM Society Asia-Pacific Conference. 2017. doi:10.36001/phmap.2017.v1i1.1681
BibTeX
@article{Song2017,
author = {Song, Dengwei and Su, Hua and Ma, Jian and Chao, Likun and Ding, Yu and Lu, Chen},
title = {A Prognostics Approach for Gearbox based on Spectrogram and Deep Learning},
journal = {PHM Society Asia-Pacific Conference},
year = {2017},
doi = {10.36001/phmap.2017.v1i1.1681}
}
EUVIMED