AnoSense: Edge computing for real-time flight anomaly detection by using embedded deep neural networks

Year 2025, Volume: 15 Issue: 3, 797 - 808, 15.09.2025

Hatice Vildan Dudukcu , Murat Taşkıran , Nihan Kahraman

https://doi.org/10.17714/gumusfenbil.1676270

Abstract

Autonomous systems, including unmanned aerial vehicles and commercial airplanes, are increasingly integrated into modern aircraft to minimize pilot errors while enhancing flight control. Ensuring flight safety requires accurate detection of anomalies in sensor data that causes error. This study, AnoSense, proposes an autoencoder-based deep neural network designed to detect anomalies in an unmanned aerial vehicle. AnoSense processes 20 flight sensor parameters to identify irregularities that could compromise operational safety. The model is trained and evaluated using NASA’s DASHlink anomaly data set, achieving 97.07% precision, outperforming conventional deep learning methods. Additionally, AnoSense is optimized for deployment on resource-constrained edge devices, with implementation and performance validation conducted on a Raspberry Pi. The experimental results demonstrate the feasibility of real-time flight anomaly detection on embedded systems, making AnoSense a promising solution to improve aircraft safety through edge computing.

Keywords

Anomaly detection , Deep neural networks , Edge computing , Embedded systems , Flight data

AnoSense: Gömülü derin sinir ağları kullanarak gerçek zamanlı uçuş anormalliklerinin tespiti için uç birim hesaplama

Abstract

Otonom sistemler — insansız hava araçları ve ticari uçaklar da dahil olmak üzere — modern hava araçlarında giderek daha fazla kullanılmaktadır. Bu sistemler, pilot hatalarını en aza indirmeyi ve uçuş kontrolünü geliştirmeyi amaçlamaktadır. Uçuş güvenliğini sağlamak için, hatalara yol açabilecek sensör verilerindeki anormalliklerin doğru şekilde tespit edilmesi büyük önem taşır. Bu çalışmada AnoSense adı verilen bir sistem önerilmektedir. AnoSense, insansız hava araçlarında meydana gelebilecek anormallikleri tespit etmek amacıyla geliştirilmiş, autoencoder tabanlı bir derin sinir ağı modelidir. Sistem, uçuş güvenliğini riske atabilecek düzensizlikleri belirleyebilmek için 20 farklı uçuş sensörü parametresini analiz eder. Model, NASA’nın DASHlink anormallik veri seti kullanılarak eğitilmiş ve test edilmiştir. Yapılan değerlendirmeler sonucunda %97.07 doğruluk oranına ulaşmış ve geleneksel derin öğrenme yöntemlerinden daha iyi bir performans sergilemiştir. Ayrıca AnoSense, donanım kaynakları sınırlı olan uç birimlerde çalışacak şekilde optimize edilmiştir. Gerçek zamanlı performansı doğrulamak amacıyla Raspberry Pi üzerinde uygulanmış ve başarılı sonuçlar elde edilmiştir. Elde edilen deneysel sonuçlar, gömülü sistemler üzerinde gerçek zamanlı uçuş anormalliği tespiti yapılabileceğini göstermektedir. Bu yönüyle AnoSense, uç bilişim teknolojisi kullanarak hava aracı güvenliğini artırmaya yönelik etkili ve umut vadeden bir çözüm sunmaktadır.

Keywords

Anomali tespiti , Derin sinir ağları , Uç bilişim , Gömülü sistemler , Uçuş verileri

References

• Albawi, S., Mohammed, T. A., & Al-Zawi, S. (2017). Understanding of a convolutional neural network. 2017 international conference on engineering and technology (ICET), 1–6.
• Bai, S., Kolter, J. Z., & Koltun, V. (2018). An empirical evaluation of generic convolutional and recurrent networks for sequence modeling. arXiv preprint arXiv:1803.01271.
• Cao, Y., Cao, J., Zhou, Z., & Liu, Z. (2021). Aircraft track anomaly detection based on mod-bi-lstm. Electronics, 10(9), 1007.
• Chung, J., Gulcehre, C., Cho, K., & Bengio, Y. (2014). Empirical evaluation of gated recurrent neural networks on sequence modeling. arXiv preprint arXiv:1412.3555. Chunhui, W., Zhou, J., Yuanhang, W., Shi, Z., Chuangmian, H., & Yunfan, Y. (2020). An anomaly detecting system for power system of four-rotor uav. 2020 International Symposium on Autonomous Systems (ISAS), 109–114.
• Cini, P. F., & Griffith, P. (1999). Designing for mfop: Towards the autonomous aircraft. Journal of Quality in Maintenance Engineering, 5(4), 296–308.
• Dangut, M. D., Jennions, I. K., King, S., & Skaf, Z. (2023). A rare failure detection model for aircraft predictive maintenance using a deep hybrid learning approach. Neural Computing and Applications, 35(4), 2991-3009.
• Dudukcu, H. V., Taskiran, M., & Kahraman, N. (2023). Uav sensor data applications with deep neural networks: A comprehensive survey. Engineering Applications of Artificial Intelligence, 123, 106476.
• Hochreiter, S., & Schmidhuber, J. (1997). Long short-term memory. Neural computation, 9(8), 1735–1780.
• Hossin, M., & Sulaiman, M. N. (2015). A review on evaluation metrics for data classification evaluations. International journal of data mining & knowledge management process, 5(2), 1.
• Keipour, A., Mousaei, M., & Scherer, S. (2019). Automatic real-time anomaly detection for autonomous aerial vehicles. 2019 International Conference on Robotics and Automation (ICRA), 5679–5685.
• Lea, C., Flynn, M. D., Vidal, R., Reiter, A., & Hager, G. D. (2017). Temporal convolutional networks for action segmentation and detection. proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 156–165.
• Lea, C., Vidal, R., Reiter, A., & Hager, G. D. (2016). Temporal convolutional networks: A unified approach to action segmentation. European conference on computer vision, 47–54.
• Lee, H., Li, G., Rai, A., & Chattopadhyay, A. (2020). Real-time anomaly detection framework using a support vector regression for the safety monitoring of commercial aircraft. Advanced Engineering Informatics, 44, 101071.
• Lian, B., Kartal, Y., Lewis, F. L., Mikulski, D. G., Hudas, R., Wan, Y., & Davoudi, A. (2022). Anomaly detection and correction of optimizing autonomous systems with inverse reinforcement learning. IEEE Transactions on Cybernetics.
• Liashchynskyi, P., & Liashchynskyi, P. (2019). Grid search, random search, genetic algorithm: A big comparison for nas. arXiv preprint arXiv:1912.06059.
• Liu, L., Liu, M., Guo, Q., Liu, D., & Peng, Y. (2018). Mems sensor data anomaly detection for the uav flight control subsystem. 2018 IEEE SENSORS, 1–4.
• Lu, H., Li, Y., Mu, S., Wang, D., Kim, H., & Serikawa, S. (2017). Motor anomaly detection for unmanned aerial vehicles using reinforcement learning. IEEE internet of things journal, 5(4), 2315–2322.
• Ma, X., Zou, H., He, P., Keung, J., Li, Y., Yu, X., & Sarro, F. (2024). On the influence of data resampling for deep learning-based log anomaly detection: Insights and recommendations. IEEE Transactions on Software Engineering.
• Matthews, B. (2022). Curated 4 class anomaly detection data set. https://c3.ndc.nasa.gov/dashlink/resources/1018
• Memarzadeh, M., Matthews, B., Templin, T., Sharif Rohani, A., & Weckler, D. (2023). Semi-supervised active learning for anomaly detection in aviation. Journal of Aerospace Information Systems, 20(4), 181–194.
• Nanduri, A., & Sherry, L. (2016). Anomaly detection in aircraft data using recurrent neural networks (rnn). 2016 Integrated Communications Navigation and Surveillance (ICNS), 5C2–1.
• Nonami, K. (2007). Prospect and recent research & development for civil use autonomous unmanned aircraft as uav and mav. Journal of system Design and Dynamics, 1(2), 120–128.
• Pezzicoli, F., Ros, V., Landes, F., & Baity-Jesi, M. (2025). Class imbalance in anomaly detection: Learning from an exactly solvable model. arXiv preprint arXiv:2501.11638.
• Wang, B., Wang, Z., Liu, L., Liu, D., & Peng, X. (2019). Data-driven anomaly detection for uav sensor data based on deep learning prediction model. 2019 Prognostics and System Health Management Conference (PHM-Paris), 286–290.
• Wang, Z., Yan, W., & Oates, T. (2017). Time series classification from scratch with deep neural networks: A strong baseline. 2017 International joint conference on neural networks (IJCNN), 1578–1585.
• Yang, L., Li, S., Li, C., Zhang, A., & Zhang, X. (2023). A survey of unmanned aerial vehicle flight data anomaly detection: Technologies, applications, and future directions. Science China Technological Sciences, 66(4), 901–919.
• Yong, D., Yuanpeng, Z., Yaqing, X., Yu, P., & Datong, L. (2017). Unmanned aerial vehicle sensor data anomaly detection using kernel principle component analysis. 2017 13th IEEE International Conference on Electronic Measurement & Instruments (ICEMI), 241– 246.