Real-time fault detection in multirotor UAVs using lightweight deep learning and high-fidelity simulation data with single and double fault magnitudes

View Full Paper

Ask AI

Bookmark

Fault localization achieved with 100% accuracy using a lightweight deep learning model.
High-fidelity simulation dataset includes 114,230 labeled samples across various flight phases.
Two innovative networks enhance fault feature extraction and severity estimation with minimal parameters.
Findings highlight the potential for real-time applications with efficient embedded deployment.

Discussion

No takes yet. Share an insight, caveat, or question.

Model improves fault detection accuracy in multirotor UAVs, suggesting efficient diagnosis of motor degradation levels.

Ferdous Sohel (2025) studied this question.

View Full Paper

Ask AI

Bookmark