Automatic feature extraction of time-series applied to fault severity assessment of helical gearbox in stationary and non-stationary speed operation

[Display omitted] •An automatic feature extraction method is proposed.•Manual feature extraction procedures can be replaced with deep learning approach.•Valid features can be extracted from a time-frequency representation of time-series.•A pre-trained layer by layer model is better than a model with...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Applied soft computing Ročník 58; s. 53 - 64
Hlavní autoři: Cabrera, Diego, Sancho, Fernando, Li, Chuan, Cerrada, Mariela, Sánchez, René-Vinicio, Pacheco, Fannia, de Oliveira, José Valente
Médium: Journal Article
Jazyk:angličtina
Vydáno: Elsevier B.V 01.09.2017
Témata:
Auto-encoder
Convolution
Deep learning
Helical gearbox
Wavelet packets
Deep learning
Wavelet packets
Helical gearbox
Convolution
Auto-encoder
ISSN:1568-4946, 1872-9681
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:[Display omitted] •An automatic feature extraction method is proposed.•Manual feature extraction procedures can be replaced with deep learning approach.•Valid features can be extracted from a time-frequency representation of time-series.•A pre-trained layer by layer model is better than a model without pre-training. Signals captured in rotating machines to obtain the status of their components can be considered as a source of massive information. In current methods based on artificial intelligence to fault severity assessment, features are first generated by advanced signal processing techniques. Then feature selection takes place, often requiring human expertise. This approach, besides time-consuming, is highly dependent on the machinery configuration as in general the results obtained for a mechanical system cannot be reused by other systems. Moreover, the information about time events is often lost along the process, preventing the discovery of faulty state patterns in machines operating under time-varying conditions. In this paper a novel method for automatic feature extraction and estimation of fault severity is proposed to overcome the drawbacks of classical techniques. The proposed method employs a Deep Convolutional Neural Network pre-trained by a Stacked Convolutional Autoencoder. The robustness and accuracy of this new method are validated using a dataset with different severity conditions on failure mode in a helical gearbox, working in both constant and variable speed of operation. The results show that the proposed unsupervised feature extraction method is effective for the estimation of fault severity in helical gearbox, and it has a consistently better performance in comparison with other reported feature extraction methods.
ISSN:1568-4946
1872-9681
DOI:10.1016/j.asoc.2017.04.016