Application of Deep Learning Models for Aircraft Maintenance
ResumoNeural networks provide useful approaches for determining solutions to complex nonlinear problems. The use of these models offers a feasible approach to help aircraft maintenance, especially health monitoring and fault detection. The technical complexity of aircraft systems poses many challenges for maintenance lines that need to optimize time, efficiency, and consistency. In this work, we first employ Convolutional Neural Networks (CNN), and Multi-Layer Perceptron (MLP) for the classification of aircraft Pressure Regulated Shutoff Valves (PRSOV). We classify a wide range of defects such as Friction, Charge and Discharge faults considering single and multi-failures. As a result of this work, we observed a significant improvement in the classification accuracy in the case of applying neural networks such as MLP (0.9962) and CNN (0.9937) when compared to a baseline KNN (0.8788).
de Assis Silva, L., Sano, H. H., and Júnior, C. L. N. (2022). Degradation estimation analysis of an aeronautical pneumatic valve using machine learning. In 2022 IEEE International Systems Conference (SysCon), pages 1-6.
Fuan, W., Hongkai, J., Haidong, S., Wenjing, D., and Shuaipeng, W. (2017). An adaptive deep convolutional neural network for rolling bearing fault diagnosis. Measurement Science and Technology, 28(9):095005.
Gao, Z., Ma, C., and Luo, Y. (2017). Rul prediction for ima based on deep regression method. In 2017 IEEE 10th International Workshop on Computational Intelligence and Applications (IWCIA), pages 25-31. IEEE.
Goodfellow, I., Bengio, Y., and Courville, A. (2016a). Convolutional networks. In Deep learning, volume 2016, pages 330-372. MIT Press Cambridge, MA, USA.
Goodfellow, I., Bengio, Y., and Courville, A. (2016b). Deep learning. MIT press.
Iata, A. (2021). The impact of covid-19 on aviation. https://www.airlines.iata.org/news/the-impact-of-covid-19-on-aviation.
Li, X., Ding, Q., and Sun, J.-Q. (2018). Remaining useful life estimation in prognostics using deep convolution neural networks. Reliability Engineering & System Safety, 172:1-11.
Maneenop, S. and Kotcharin, S. (2020). The impacts of covid-19 on the global airline industry: An event study approach. Journal of air transport management, 89:101920.
Reddy, K. K., Sarkar, S., Venugopalan, V., and Giering, M. (2016). Anomaly detection and fault disambiguation in large flight data: A multi-modal deep auto-encoder approach. In Annual Conference of the PHM Society, volume 8.
Rengasamy, D., Morvan, H. P., and Figueredo, G. P. (2018). Deep learning approaches to aircraft maintenance, repair and overhaul: A review. In 2018 21st International Conference on Intelligent Transportation Systems (ITSC), pages 150-156. IEEE.
Sano, H., Malere, J., and Berton, L. (2019). Single and multiple failures diagnostics of pneumatic valves using machine learning. In Anais do XVI Encontro Nacional de Inteligência Artificial e Computacional, pages 202-213, Porto Alegre, RS, Brasil. SBC.
Sano, H. H. and Berton, L. (2022). Dataset. https://doi.org/10.5281/zenodo.7191171.
Sarkar, S., Reddy, K. K., and Giering, M. (2016). Deep learning for structural health monitoring: A damage characterization application. In Annual Conference of the PHM Society, volume 8.
Turcio, W., Yoneyama, T., and Moreira, F. (2013). Quasi-lpv gain-scheduling control of a nonlinear aircraft pneumatic system. In 21st Mediterranean Conference on Control and Automation, pages 341-350.
Zafar, I., Tzanidou, G., Burton, R., Patel, N., and Araujo, L. (2018). Hands-On Convolutional Neural Networks with TensorFlow: Solve Computer Vision Problems with Modeling in TensorFlow and Python. Packt Publishing.