Data-driven Fault Detection and Isolation (FDI) systems receive a lot of attention from researchers. Several recent applications utilize acoustic signals recorded on-board of the Unmanned Aerial Vehicle (UAV) to assess the condition of propulsion system and diagnose rotor blade impairments. In this work, we propose two major improvements to the previously developed FDI scheme. They are aimed at reducing the computational load of the deep LSTM-based (Long ShortTerm Memory) fault classifier. First, the PCA-based (Principal Component Analysis) feature space reduction allows reducing the size of neural networks and thus decreasing the number of mathematical operations. Secondly, a modified algorithm introduces an ensemble of multiple weak classifiers with a decision-fusion strategy that provides the final status of the system. The developed schemes were evaluated in comparison to the original algorithm, using an extensive dataset of real-flight acoustic data. The results show that the proposed improvements significantly reduce the computation time within the assumed performance constraints.
Toward lightweight acoustic fault detection and identification of UAV rotors
2023-06-06
5194763 byte
Aufsatz (Konferenz)
Elektronische Ressource
Englisch
From compound to aluminium lightweight rotors
Kraftfahrwesen | 2013
|Thermally Sprayed Coatings for Lightweight Brake Rotors
British Library Conference Proceedings | 1999
|Thermally sprayed coatings for lightweight brake rotors
Kraftfahrwesen | 1999
|Thermally Sprayed Coatings for Lightweight Brake Rotors
SAE Technical Papers | 1999
|