A Sound Based Method for Fault Classification with Support Vector Machines in UAV Motors

Year 2021, Volume: 4 Issue: 1, 5 - 10, 30.06.2021

Ferhat Yol Ayhan Altınors Orhan Yaman

Abstract

In this study, a machine learning-based method is proposed for Brushless DC (BLDC) motors used in unmanned aerial vehicles (UAV). Shaft failure, magnet failure, propeller failure, and bearing failure are common failures in BLDC motors. These fault types are created on UAV engines. Sound recordings were taken from the engines for each failure type. While collecting the dataset, the motors were run at a constant speed. First of all, sound data was collected for the sound engine. Then, fixed time-length audio recordings were taken for 4 fault classes at a constant speed and a data set was created. This dataset consists of five classes. In order to reduce the data size in these sounds, Average Filter, Average Polling, and Normalization processes were applied, respectively. Then, the Chi2 Method was used for feature selection. In the next step, the Support Vector Machine (SVM) algorithm is used to classify the obtained features. In classification, 96.70% accuracy was calculated with the Cubic SVM algorithm.

Keywords

Brushless motors, Fault detection, Machine learning, Support vector machines, Unmanned aerial vehicles

References

• [1] Park, J-H., Jun, C-Y., Jeong, J-Y., & Chang, D.E. (2020). Real-time quadrotor actuator fault detection and isolation using multivariate statistical analysis techniques with sensor measurements. Available at: [https://doi.org/10.23919/iccas50221.2020.9268391](https://doi.org/10.23919/iccas50221.2020.9268391).
• [2] Cheng, D.L., & Lai, W.H. (2019). Application of self-organizing map on flight data analysis for quadcopter health diagnosis system. International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences - ISPRS Archives, 42, 241–246. Available at: [https://doi.org/10.5194/isprs-archives-XLII-2-W13-241-2019](https://doi.org/10.5194/isprs-archives-XLII-2-W13-241-2019).
• [3] Iannace, G., Ciaburro, G., & Trematerra, A. (2019). Fault diagnosis for UAV blades using artificial neural network. Robotics, 8. Available at: [https://doi.org/10.3390/robotics8030059](https://doi.org/10.3390/robotics8030059).
• [4] Sadhu, V., Zonouz, S., & Pompili, D. (2020). On-board Deep-learning-based Unmanned Aerial Vehicle Fault Cause Detection and Identification. Proceedings of the IEEE International Conference on Robotics and Automation. Available at: [https://doi.org/10.1109/ICRA40945.2020.9197071](https://doi.org/10.1109/ICRA40945.2020.9197071).
• [5] Lu, H., Li, Y., Mu, S., Wang, D., Kim, H., & Serikawa, S. (2018). Motor Anomaly Detection for Unmanned Aerial Vehicles Using Reinforcement Learning. IEEE Internet of Things Journal, 5, 2315–222.
• [6] Pourpanah, F., Zhang, B., Ma, R., & Hao, Q. (2018). Anomaly Detection and Condition Monitoring of UAV Motors and Propellers. Proceedings of the IEEE Sensors. Available at: [https://doi.org/10.1109/ICSENS.2018.8589572](https://doi.org/10.1109/ICSENS.2018.8589572).
• [7] Keipour, A., Mousaei, M., & Scherer, S. (2019). Automatic Real-time Anomaly Detection for Autonomous Aerial Vehicles. arXiv. Available at: [https://arxiv.org/abs/1908.05679](https://arxiv.org/abs/1908.05679).
• [8] Titouna, C., Nait-Abdesselam, F., & Moungla, H. (2020). An Online Anomaly Detection Approach for Unmanned Aerial Vehicles. Proceedings of the International Wireless Communications & Mobile Computing Conference. Available at: [https://doi.org/10.1109/IWCMC48107.2020.9148073](https://doi.org/10.1109/IWCMC48107.2020.9148073).
• [9] Liu, W., Chen, Z., & Zheng, M. (2020). An Audio-Based Fault Diagnosis Method for Quadrotors Using Convolutional Neural Network and Transfer Learning. Proceedings of the American Control Conference. Available at: [https://doi.org/10.23919/ACC45564.2020.9148044](https://doi.org/10.23919/ACC45564.2020.9148044).
• [10] Bondyra, A., Gasior, P., Gardecki, S., & Kasinski, A. (2017). Fault diagnosis and condition monitoring of UAV rotor using signal processing. Proceedings of the Signal Processing: Algorithms, Architectures, Arrangements, and Applications Conference. Available at: [https://doi.org/10.23919/SPA.2017.8166870](https://doi.org/10.23919/SPA.2017.8166870).
• [11] Ghalamchi, B., Jia, Z., & Mueller, M.W. (2020). Real-Time Vibration-Based Propeller Fault Diagnosis for Multicopters. IEEE/ASME Transactions on Mechatronics, 25, 395–405. Available at: [https://doi.org/10.1109/TMECH.2019.2947250](https://doi.org/10.1109/TMECH.2019.2947250).
• [12] Rangel-Magdaleno, J.D.J., Urena-Urena, J., Hernandez, A., & Perez-Rubio, C. (2019). Detection of unbalanced blade on UAV by means of audio signal. In 2018 IEEE International Autumn Meeting on Power, Electronics and Computing (ROPEC) (pp. 2–6). Available at: [https://doi.org/10.1109/ROPEC.2018.8661459](https://doi.org/10.1109/ROPEC.2018.8661459).
• [13] Benini, A., Ferracuti, F., Monteriu, A., & Radensleben, S. (2019). Fault detection of a VTOL UAV using acceleration measurements. In 2019 18th European Control Conference (ECC) (pp. 3990–3995). Available at: [https://doi.org/10.23919/ECC.2019.8796198](https://doi.org/10.23919/ECC.2019.8796198).
• [14] Ray, D.K., Roy, T., & Chattopadhyay, S. (2020). Skewness Scanning for Diagnosis of a Small Inter-Turn Fault in Quadcopter’s Motor based on Motor Current Signature analysis. IEEE Sensors Journal. Available at: [https://doi.org/10.1109/jsen.2020.3038786](https://doi.org/10.1109/jsen.2020.3038786).
• [15] Wang, X., Fan, W., Li, X., & Wang, L. (2019). Weak degradation characteristics analysis of UAV motors based on Laplacian Eigenmaps and Variational Mode Decomposition. Sensors, 19. Available at: [https://doi.org/10.3390/s19030524](https://doi.org/10.3390/s19030524).
• [16] Yazıcı, B., Yaslı, F., Gürleyik, H.Y., & Turgut, U.O. Veri Madenciliğinde Özellik Seçim Tekniklerinin Bankacılık Verisine Uygulanması Üzerine Araştırma ve Karşılaştırmalı Uygulama. (n.d.). Available at: [https://doi.org/10.1016/j.measurement.2020.108323](https://doi.org/10.1016/j.measurement.2020.108323).
• [17] Yaman, O. (2021). An automated faults classification method based on binary pattern and neighborhood component analysis using induction motor. Measurement: Journal of the International Measurement Confederation, 168. Available at: [https://doi.org/10.1016/j.measurement.2020.108323](https://doi.org/10.1016/j.measurement.2020.108323).
• [18] Gangsar, P., & Tiwari, R. (2019). A support vector machine-based fault diagnostics of induction motors for practical situations of multi-sensor limited data case. Measurement: Journal of the International Measurement Confederation, 135, 694–711. Available at: [https://doi.org/10.1016/j.measurement.2018.12.011](https://doi.org/10.1016/j.measurement.2018.12.011).
• [19] Tuncer, T., Ertam, F., Dogan, S., & Subasi, A. (2020). An Automated Daily Sports Activities and Gender Recognition Method Based on Novel Multikernel Local Diamond Pattern Using Sensor Signals. IEEE Transactions on Instrumentation and Measurement, 69, 9441–9448. Available at: [https://doi.org/10.1109/TIM.2020.3003395](https://doi.org/10.1109/TIM.2020.3003395).