Unmanned aerial vehicle resilience: A new approach to fault diagnostics framework
Abstract
The unmanned aerial vehicles (UAVs) have become crucial resources for various tasks, from surveillance and tracking to environmental monitoring and responding to disasters. However, as UAV systems and their tactical surroundings get more complicated, there is a greater chance that they will malfunction or fail. A novel method for fault classifier using Genetic-Tuna Swarm Optimized Deep Neural Network (GTSO-DNN) is applied for anomaly identification. The collection of data from simulated propeller damage, Min-Max normalization for pre-processing, and Principal Component Analysis (PCA) for feature extraction are all included. A UAV model integrates dynamic and propeller models built using a Gated Recurrent Unit (GRU) network. Experimental findings demonstrate the GTSO-DNN’s superior performance compared to existing methods (K Nearest Neighbour, Decision Tree, Support Vector Machines) in terms of accuracy—98.51%, precision—98.7%, recall—98.9%, and F1 score—97.2%. The GTSO-DNN efficiently locates and classifies problems, improving UAV resilience. With potential applications for improving real-time UAV safety, this comprehensive methodology enhances fault diagnosis.
Keywords
Full Text:
PDFReferences
1. Yaqot M, Menezes BC. Unmanned Aerial Vehicle (UAV) in Precision Agriculture: Business Information Technology Towards Farming as a Service. In: Proceedings of the 2021 1st International Conference on Emerging Smart Technologies and Applications (eSmarTA).
2. Iqbal U, Barthelemy J, Perez P. Emerging role of unmanned aerial vehicles (UAVs) for disaster management applications. In: Nanotechnology-Based Smart Remote Sensing Networks for Disaster Prevention. Elsevier; 2022.
3. Madni AM, Erwin D, Sievers M. Constructing Models for Systems Resilience: Challenges, Concepts, and Formal Methods. Systems. 2020; 8(1): 3. doi: 10.3390/systems8010003
4. Chen M, Wang H, Chang CY, et al. SIDR: A Swarm Intelligence-Based Damage-Resilient Mechanism for UAV Swarm Networks. IEEE Access. 2020; 8: 77089-77105. doi: 10.1109/access.2020.2989614
5. Debele Y, Shi HY, Wondosen A, et al. Deep Learning-Based Robust Actuator Fault Detection and Isolation Scheme for Highly Redundant Multirotor UAVs. Drones. 2023; 7(7): 437. doi: 10.3390/drones7070437
6. Wang G, Gu C, Li J, et al. Heterogeneous Flight Management System (FMS) Design for Unmanned Aerial Vehicles (UAVs): Current Stages, Challenges, and Opportunities. Drones. 2023; 7(6): 380. doi: 10.3390/drones7060380
7. Bondyra A, Kołodziejczak M, Kulikowski R, et al. An Acoustic Fault Detection and Isolation System for Multirotor UAV. Energies. 2022; 15(11): 3955. doi: 10.3390/en15113955
8. Hsiao YS, Wan Z, Jia T, et al. April. Mavfi: An end-to-end fault analysis framework with anomaly detection and recovery for micro aerial vehicles. In: 2023 Design, Automation & Test in Europe Conference & Exhibition (DATE). IEEE; 2023.
9. Sadhu V, Zonouz S, Pompili D. On-board Deep-learning-based Unmanned Aerial Vehicle Fault Cause Detection and Identification. In: Proceedings of the 2020 IEEE International Conference on Robotics and Automation (ICRA).
10. Zhang Y, Li S, He Q, et al. An Intelligent Fault Detection Framework for FW-UAV Based on Hybrid Deep Domain Adaptation Networks and the Hampel Filter. International Journal of Intelligent Systems. 2023; 2023: 1-19. doi: 10.1155/2023/6608967
11. Corbetta M, Jarvis KJ, Schuet S. Hybrid Modeling of Unmanned Aerial Vehicle Electric Powertrain for Fault Detection and Diagnostics. In: AIAA AVIATION 2023 Forum. AIAA; 2023.
12. Segovia Ramírez I, Das B, García Márquez FP. Fault detection and diagnosis in photovoltaic panels by radiometric sensors embedded in unmanned aerial vehicles. Progress in Photovoltaics: Research and Applications. 2021; 30(3): 240-256. doi: 10.1002/pip.3479
13. Hossain NUI, Sakib N, Govindan K. Assessing the performance of unmanned aerial vehicle for logistics and transportation leveraging the Bayesian network approach. Expert Systems with Applications. 2022; 209: 118301. doi: 10.1016/j.eswa.2022.118301
14. El Jery A, P S, Mahmood Salman H, et al. Comparison of different approaches for numerical modeling of nanofluid subcooled flow boiling and proposing predictive models using artificial neural network. Progress in Nuclear Energy. 2023; 156: 104540. doi: 10.1016/j.pnucene.2022.104540
15. Al-Abiad MS, Javad-Kalbasi M, Valaee S. Effectiveness of Reconfigurable Intelligent Surfaces to Enhance Connectivity in UAV Networks. ArXiv. 2023; arXiv:2308.10788.
16. Perry BJ, Guo Y, Atadero R, et al. Streamlined bridge inspection system utilizing unmanned aerial vehicles (UAVs) and machine learning. Measurement. 2020; 164: 108048. doi: 10.1016/j.measurement.2020.108048
17. Eichleay M, Evens E, Stankevitz K, et al. Using the Unmanned Aerial Vehicle Delivery Decision Tool to Consider Transporting Medical Supplies via Drone. Global Health: Science and Practice. 2019; 7(4): 500-506. doi: 10.9745/ghsp-d-19-00119
18. Ejaz W, Azam MA, Saadat S, et al. Unmanned Aerial Vehicles enabled IoT Platform for Disaster Management. Energies. 2019; 12(14): 2706. doi: 10.3390/en12142706
19. Bronz M, Baskaya E, Delahaye D, et al. Real-time Fault Detection on Small Fixed-Wing UAVs using Machine Learning. In: Proceedings of the 2020 AIAA/IEEE 39th Digital Avionics Systems Conference (DASC).
20. Phadke A, Medrano FA. Towards Resilient UAV Swarms—A Breakdown of Resiliency Requirements in UAV Swarms. Drones. 2022; 6(11): 340. doi: 10.3390/drones6110340
21. Neves FS, Claro RM, Pinto AM. End-to-End Detection of a Landing Platform for Offshore UAVs Based on a Multimodal Early Fusion Approach. Sensors. 2023; 23(5): 2434. doi: 10.3390/s23052434
22. Phadke A, Medrano FA, Chu T, et al. Drone2Drone (D2D): A Search and Rescue Framework Module for Finding Lost UAV Swarm Agents. In: Proceedings of the 2023 Congress in Computer Science, Computer Engineering, & Applied Computing (CSCE).
23. Zhang P, Wu T, Cao R, et al. UAV Swarm Resilience Assessment Considering Load Balancing. Frontiers in Physics. 2022; 10. doi: 10.3389/fphy.2022.821321
24. El Jery A, P S, Mahmood Salman H, et al. Comparison of different approaches for numerical modeling of nanofluid subcooled flow boiling and proposing predictive models using artificial neural network. Progress in Nuclear Energy. 2023; 156: 104540. doi: 10.1016/j.pnucene.2022.104540
25. Jerome Vasanth J, Naveen Venkatesh S, Sugumaran V, et al. Enhancing Photovoltaic Module Fault Diagnosis with Unmanned Aerial Vehicles and Deep Learning-Based Image Analysis. International Journal of Photoenergy. 2023; 2023: 1-17. doi: 10.1155/2023/8665729
26. Tong JJ, Zhang W, Liao F, et al. Machine Learning for UAV Propeller Fault Detection based on a Hybrid Data Generation Model. arXiv. 2023; arXiv:2302.01556.
27. Altinors A, Yol F, Yaman O. A sound based method for fault detection with statistical feature extraction in UAV motors. Applied Acoustics. 2021; 183: 108325. doi: 10.1016/j.apacoust.2021.108325
DOI: https://doi.org/10.32629/jai.v7i5.1637
Refbacks
- There are currently no refbacks.
Copyright (c) 2024 Authors
License URL: https://creativecommons.org/licenses/by-nc/4.0/