Detecting problematic vibration on unmanned aerial vehicles via genetic-algorithm methods
Unmanned Aerial Vehicles (UAV) problematic vibration detection as a flaw detection and identification (FDI) method has emerged as a feasible tool for assessing a UAV's health and condition. This paper shows the potential of optimization-based UAV problematic vibration detection. A proposed fitn...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Conference or Workshop Item |
| Language: | English English |
| Published: |
Institute of Electrical and Electronics Engineers Inc.
2024
|
| Subjects: | |
| Online Access: | http://umpir.ump.edu.my/id/eprint/41738/1/Detecting%20problematic%20vibration%20on%20unmanned%20aerial%20vehicles.pdf http://umpir.ump.edu.my/id/eprint/41738/2/Detecting%20problematic%20vibration%20on%20unmanned%20aerial%20vehicles%20via%20genetic-algorithm%20methods_ABS.pdf http://umpir.ump.edu.my/id/eprint/41738/ https://doi.org/979-835038231-0 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | Unmanned Aerial Vehicles (UAV) problematic vibration detection as a flaw detection and identification (FDI) method has emerged as a feasible tool for assessing a UAV's health and condition. This paper shows the potential of optimization-based UAV problematic vibration detection. A proposed fitness function based on the frequency domain has been detailed. The fitness function with the Genetic Algorithm (GA) optimization method is tested and evaluated based on Root Mean Squared Error (RMSE), Mean Absolute Percentage Error (MAPE), and detection time. 51 sets of data have been collected using software in the loop (SITL) methods and are used to determine the effectiveness of the proposed fitness function and GA. The test results show promising results with obtained mean RMSE =1407.2303, mean MAPE =0.7135, and mean detection time =2.6129s for a data range of between 3955 to 9057. |
|---|