Deep Learning-Based Airspeed Estimation System for a Commercial Aircraft
Ticari Uçaklar için Derin Öğrenme Tabanlı Hava Hızı Tahmin Sistemi
Keywords:
Aircraft Sensor, Estimation, Machine Learning, Deep LearningAbstract
Airspeed data is so important for an aircraft operation. This study is focused on the estimation of the airspeed data without any additional measurement source such as hardware redundancy. The flight data obtained from a commercial aircraft is processed with a deep learning algorithm, particularly LSTM recurrent neural networks that are developed based on Matrix Laboratory (MATLAB). Correlation analysis is carried out for related data according to a 95% confidence interval for each coefficient in the study to show strong predictor candidates. Data related to the airspeed are processed using Holdout Cross-Validation Technique. According to the results, the designed model achieved an R-squared of 0.9999, a root-mean-squared error of 0.8303 knots, and a standard error of 0.0092 knots. These results show that it is possible to accurately estimate aircraft airspeed data using LSTM recurrent neural network in case of the airspeed data cannot be provided to the flight crew.
Downloads
References
S. Makó, M. Pilát, P. Šváb, J. Kozuba, M. Čičváková, Evaluation of MCAS System, Acta Avionica Journal 40(1), 21–28 (2020).
R. P. G. Collinson, Introduction to Avionics Systems. London New York: Springer, 2011, pp. 377–413.
O. Hazbon Alvarez, L. B. Gutierrez Zea, C. Bil, M. Napolitano, and M. L. Fravolini, “Review of Methodologies for Aircraft Sensors Fault Detection and Correction,” in Proc. of the 2019 18th Australian International Aerospace Congress, AIAC 2018, 24-26 February 2019, Melbourne, Australia [Online]. Available: https://researchrepository.rmit.edu.au. [Accessed: Jul. 04, 2023].
A. Transport Safety Bureau, “Airspeed indication failure on take-off involving Airbus A330, 9M-MTK ATSB Transport Safety Report Aviation Occurrence Investigation (Systemic),” 2018. [Online]. Available: www.atsb.gov.au. [Accessed: Jul. 04, 2023].
C. Voo, “Sunday, 10 April 2022 For Immediate Release Caam Reviews Initial Safety Investigation Report For Malaysia Airlines Flights MH2664,” 2022. [Online]. Available: https://www.caam.gov.my/. [Accessed: Jul. 04, 2023].
J. M. Gauber, “Currently Developing and Future Communications and Technology Impact on AMDAR Instruments and Observing Methods,” 2016. [Online]. Available: http://library.wmo.int/opac. [Accessed: Jul. 04, 2023].
D. Ossmann and H. D. Joos, “Enhanced detection and isolation of angle of attack sensor faults,” in Proc. of the 2016 AIAA Guidance, Navigation, and Control Conference, MNGC 2016, 4-8 January 2016, San Diego, California, USA [Online]. Available: https://elib.dlr.de. [Accessed: Jul. 04, 2023].
J. Barthe, “Unreliable Speed,” 2007. [Online]. Available: https://w3.airbus.com/. [Accessed: Jul. 04, 2023].
I. Turkmen, An alternative neural airspeed computation method for aircrafts, Aircraft Engineering and Aerospace Technology 90(2), 368–378 (2018).
F. A. P. Lie, D. Gebre-Egziabher, Synthetic air data system, J Aircr 50(4), 1234–1249 (2013).
H. Ryu et al., In-Flight Estimation of Drag Parameters and Air Data for Unmanned Aircraft, Journal of Aerospace Information Systems 19(3), 166–178 (2022).
Q. He, W. Zhang, P. Lu, J. Liu, Performance comparison of representative model-based fault reconstruction algorithms for aircraft sensor fault detection and diagnosis, Aerosp Sci Technol 98(105649), 1-18 (2020).
P. Lu, E. J. van Kampen, C. de Visser, Q. Chu, Air Data Sensor Fault Detection and Diagnosis in the Presence of Atmospheric Turbulence: Theory and Experimental Validation With Real Flight Data, IEEE Transactions on Control Systems Technology 29(5), 1–9 (2020).
K. Sun and D. Gebre-Egziabher, “A Fault Detection and Isolation Design for a Dual Pitot Tube Air Data System,” in Proc. of the 2020 IEEE/ION Position, Location and Navigation Symposium, PLANS 2020, 20-23 April 2020, Portland, OR, USA [Online]. Available: https://ieeexplore.ieee.org. [Accessed: Jul. 04, 2023].
M. Taimoor, L. Aijun, Neural-sliding mode approach-based adaptive estimation, isolation and tolerance of aircraft sensor fault, Aircraft Engineering and Aerospace Technology 92(2), 237–255 (2020).
C. Lijia, T. Yu and Z. Guo, “Adaptive observer-based fault detection and active tolerant control for unmanned aerial vehicles attitude system”, in Proc. of the 2019 5th IFAC Symposium on Telematics Applications, TA 2019, 25-27 September 2019, Chengdu, China [Online]. Available: https://www.sciencedirect.com. [Accessed: Jul. 04, 2023].
M. L. Fravolini, M. R. Napolitano, G. Del, U. Papa, Experimental interval models for the robust Fault Detection of Aircraft Air Data Sensors, Control Eng Pract 78(9), 196–212 (2018).
J. T. Pearson, R. M. Goodall, and M. Eastham, “Aircraft Air Data Estimation Using a Model-Based Approach,” in Proc. of the 2007 17th IFAC Symposium on Automatic Control in Aerospace, IFAC 2007, 25-29 June 2007, Toulouse, France [Online]. Available: https://www.sciencedirect.com. [Accessed: Jul. 04, 2023].
A. Omar Alkhamisi and R. Mehmood, “An Ensemble Machine and Deep Learning Model for Risk Prediction in Aviation Systems,” in Proc. of the 2020 6th Conference on Data Science and Machine Learning Applications, CDMA 2020, 4-5 March 2020, Riyadh, Saudi Arabia [Online]. Available: https://ieeexplore.ieee.org. [Accessed: Jul. 04, 2023].
M. Chen, Z. Li, X. Lei, S. Liang, S. Zhao, Y. Su, Unsupervised Fault Detection Driven by Multivariate Time Series for Aeroengines, J Aerosp Eng 36(2), (2023).
V. E. Atasoy, A. E. Suzer, S. Ekici, A Comparative Analysis of Exhaust Gas Temperature Based on Machine Learning Models for Aviation Applications, Journal of Energy Resources Technology, Transactions of the ASME 144 (8), 1-13 (2022).
X. Qiu, C. Gao, K. Wang, W. Jing, Attitude Control of a Moving Mass–Actuated UAV Based on Deep Reinforcement Learning, J Aerosp Eng 35(2), (2022).
H. Shafienya, A. C. Regan, 4D flight trajectory prediction using a hybrid Deep Learning prediction method based on ADS-B technology: A case study of Hartsfield–Jackson Atlanta International Airport (ATL), Transp Res Part C Emerg Technol 144(103878), 1-12 (2022).
Y. Zhu, C. Du, Z. Liu, Y. B. Chen, Y. P. Zhao, A Turboshaft Aeroengine Fault Detection Method Based on One-Class Support Vector Machine and Transfer Learning, J Aerosp Eng 35(6), (2022).
K. Kayaalp, S. Metlek, S. Ekici, Y. Şöhret, Developing a model for prediction of the combustion performance and emissions of a turboprop engine using the long short-term memory method, Fuel 302(121202), 1-12 (2021).
H. O. Verma, N. K. Peyada, Estimation of aerodynamic parameters near stall using maximum likelihood and extreme learning machine-based methods, The Aeronautical Journal 125 (1285), 489–509 (2021).
F. Yildirim Dalkiran, M. Toraman, Predicting thrust of aircraft using artificial neural networks, Aircraft Engineering and Aerospace Technology 93(1), 35–41 (2021).
H. O. Verma, N. K. Peyada, Aircraft parameter estimation using ELM network, Aircraft Engineering and Aerospace Technology 92(6), 895–907 (2020).
K. Yang, M. Bi, Y. Liu, and Y. Zhang, “LSTM-Based Deep Learning Model for Civil Aircraft Position and Attitude Prediction Approach,” in Proc. of the 2019 Chinese Control Conference, CCC 2019, 27-30 July 2019, Guangzhou, China [Online]. Available: https://ieeexplore.ieee.org. [Accessed: Jul. 04, 2023].
C. Tong, X. Yin, S. Wang, Z. Zheng, A novel deep learning method for aircraft landing speed prediction based on cloud-based sensor data, Future Generation Computer Systems 88(C), 552–558 (2018).
J. Zhang, P. Wang, R. Yan, R. X. Gao, Long short-term memory for machine remaining life prediction, J Manuf Syst 48, 78–86 (2018).
H. Lim et al., Deep Learning-Aided Synthetic Airspeed Estimation of UAVs for Analytical Redundancy with a Temporal Convolutional Network, IEEE Robot Autom Lett 7(1), 17–24 (2022).
A. Lerro, P. Gili, M. L. Fravolini, M. Napolitano, Experimental Analysis of Neural Approaches for Synthetic Angle-of-Attack Estimation, International Journal of Aerospace Engineering, 1-13 (2021).
W. Youn et al., State Estimation for HALE UAVs with Deep-Learning-Aided Virtual AOA/SSA Sensors for Analytical Redundancy, IEEE Robot Autom Lett 6(3), 5276–5283 (2021).
K. Trolle Borup, T. Inge Fossen, T. Arne Johansen, S. Member, A Machine Learning Approach for Estimating Air Data Parameters of Small Fixed-Wing UAVs Using Distributed Pressure Sensors, IEEE Trans Aerosp Electron Syst 56(3), 2157–2173 (2020).
K. Sun, C. D. Regan, D. Gebre-Egziabher, Observability and performance analysis of a model-free synthetic air data estimator, J Aircr 56(4), 1471–1486 (2019).
M. B. Rhudy, M. L. Fravolini, Y. Gu, M. R. Napolitano, S. Gururajan, H. Chao, Aircraft model-independent airspeed estimation without pitot tube measurements, IEEE Trans Aerosp Electron Syst 51(3), 1980–1995 (2015).
A. Calia, E. Dentin, R. Galatolo, F. Schettini, Air data computation using neural networks, J Aircr 45(6), 2078–2083 (2008).
MathWorks, “Long Short-Term Memory Networks,” 2022. [Online]. Available: https://www.mathworks.com/help/deeplearning/ug/long-short-term-memory-networks.html. [Accessed: Jul. 04, 2023].
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2023 Journal of Aeronautics and Space Technologies
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
The manuscript with title and authors is being submitted for publication in Journal of Aeronautics and Space Technologies. This article or a major portion of it was not published, not accepted and not submitted for publication elsewhere. If accepted for publication, I hereby grant the unlimited and all copyright privileges to Journal of Aeronautics and Space Technologies.
I declare that I am the responsible writer on behalf of all authors.