.png){kind=icon}
.png){kind=icon}
Return
SAGE-PD: Spectral Attention-Guided Episodic Prototype Displacement for Few-Shot Open-Set UUV Thruster Diagnosis
.png){kind=icon}
OA
AI
H
J
Y
Y
J
DOI：10.3390/drones10080615.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Thruster health monitoring is essential for unmanned underwater vehicles (UUVs), where propulsion degradation can reduce manoeuvrability, tracking accuracy, and mission safety. Practical diagnosis remains difficult because labelled vibration samples are scarce and deployed vehicles may encounter fault states absent from the support library. Closed-set few-shot classifiers are unreliable in this setting because every query must be assigned to a known state. SAGE-PD (Spectral Attention-Guided Episodic Prototype Displacement) is a few-shot open-set method for UUV thruster vibration monitoring. It encodes each vibration window through raw-waveform and STFT branches, constructs episode-specific prototypes for known thruster states, and models their relational geometry. Unknown-state evidence is obtained by replacing the predicted prototype with the query embedding and measuring the displacement of the transformed prototype structure. Spectral attention weights this displacement toward thruster-related time–frequency components. On the analysed UUV thruster dataset, SAGE-PD achieved 0.9078 ± 0.0573 Open OA and 0.9011 ± 0.0407 AUROC in a 5-shot evaluation, and 0.8745 ± 0.0457 Open OA and 0.8953 ± 0.0409 AUROC in a 1-shot evaluation. The results show that SAGE-PD improves both known-state recognition and unknown-state rejection by combining support-structure compatibility with vibration-aware spectral evidence.
Keywords:
unmanned underwater vehicle
thruster health monitoring
vibration diagnosis
few-shot open-set recognition
spectral attention
episodic prototype displacement
Journal
D
IF:
4.8
Papers:
3.7K
Citations:
8.3K
Organization
Cited Papers