PET-AE: Physics-informed enhanced temporal autoencoder for incipient fault detection of shafting systems

•A physics-informed enhanced temporal autoencoder is proposed for incipient fault detection.•A differential Transformer autoencoder is used to mine temporal dependencies from monitoring signals.•A spectrum module is designed to capture abundant periodic representations.•An enhanced memory module is...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Mechanical systems and signal processing Ročník 240; s. 113345
Hlavní autoři: Gao, Zhan, Yu, Kaiwei, Wu, Jun, Jiang, Weixiong, Yang, Bo
Médium: Journal Article
Jazyk:angličtina
Vydáno: Elsevier Ltd 01.11.2025
Témata:
Autoencoder
Bearing
Fault detection
Physics-informed
Shafting system
Transformer network
Shafting system
Physics-informed
Transformer network
Fault detection
Autoencoder
Bearing
ISSN:0888-3270
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:•A physics-informed enhanced temporal autoencoder is proposed for incipient fault detection.•A differential Transformer autoencoder is used to mine temporal dependencies from monitoring signals.•A spectrum module is designed to capture abundant periodic representations.•An enhanced memory module is built to enlarge the distribution interval between normal and degradation samples. Incipient fault detection is crucial for improving the stable operation of shafting systems. Autoencoders (AEs) have gained popularity in the field of incipient fault detection. However, AE-based methods are weak in capturing temporal and periodic dependencies hidden in monitoring signals. This hinders the timely detection of incipient faults. To tackle these challenges, a physics-informed enhanced temporal autoencoder (PET-AE) is proposed for incipient fault detection of shafting systems. In this method, a Transformer autoencoder is constructed to reconstruct signals, where the differential Transformer encoder is used to mine temporal features from input signals. Moreover, a spectrum module is designed to capture global and local frequency information to enhance the periodic representations. Then, an enhanced memory module is employed to enlarge the distribution gap between normal samples and degradation samples. To verify the effectiveness of the proposed method, experimental studies are implemented on IMS bearing dataset and a self-built propulsive shafting system. Experimental results demonstrate that the proposed PET-AE has outstanding fault detection performance compared to other advanced detection methods.
ISSN:0888-3270
DOI:10.1016/j.ymssp.2025.113345