Abstract
Runway overrun is one of the most typical landing incidents highly concerned by airlines in the aviation industry. Previous studies have shown that high landing speed is closely related to runway overrun risks, therefore the study of landing speed prediction based on flight data has drawn attention of many scholars in recent years. However, existing methods are mainly based on traditional machine learning models and handcrafted features, which not only rely heavily on flight experts’ priori knowledge, but also provide unsatisfactory prediction accuracy. To solve this problem, in this paper we propose an innovative deep encoder-decoder model for aircraft landing speed prediction based on Quick Access Recorder (QAR) data. Specifically, we first preprocess the QAR dataset through a data cleaning, Lagrange interpolation and normalization procedure. Second, based on the preprocessed QAR dataset, we use gradient boosting decision trees to select features which are most closely related to landing speed. Finally, we employ the LSTM encoder-decoder architecture where the encoder captures the pattern underlying in the past sequences while the decoder generates predictions for the future speed sequences. We evaluate our method on a dataset of 44,176 A321 flight samples. The experimental results show that the prediction accuracy of the proposed method is significantly higher than the conventional methods.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
Notes
- 1.
Owing to proprietary and privacy considerations, we do not disclose the airline name and data.
References
Boeing Commercial Airplanes: Statistical summary of commercial jet airplane accidents. In: Worldwide Operations, vol. 2008 (1959)
Lv, H., Yu, J., Zhu, T.: A novel method of overrun risk measurement and assessment using large scale QAR data. In: 2018 IEEE Fourth International Conference on Big Data Computing Service and Applications (BigDataService), pp. 213–220. IEEE (2018)
Van Es, G.W.H., Tritschler, K., Tauss, M.: Development of a landing overrun risk index, 21st annual European Aviation Safety Seminar (EASS) Nicosia, Cyprus, NLR Air Transport Safety Institute, Report NLR-TP-280 (2009)
Ayra, E.S., Ríos Insua, D., Cano, J.: Bayesian network for managing runway overruns in aviation safety. J. Aerosp. Inf. Syst. 16(12), 546–558 (2019)
Valdés, R.M.A., Comendador, V.F.G., Sanz, L.P., Sanz, A.R.: Prediction of aircraft safety incidents using Bayesian inference and hierarchical structures. Saf. Sci. 104, 216–230 (2018)
Sheridan, K., Puranik, T.G., Mangortey, E., Pinon-Fischer, O.J., Kirby, M., Mavris, D.N.: An application of DBSCAN clustering for flight anomaly detection during the approach phase. In: AIAA Scitech 2020 Forum, p. 1851 (2020)
Basora, L., Olive, X., Dubot, T.: Recent advances in anomaly detection methods applied to aviation. Aerospace 6(11), 117 (2019)
Calle-Alonso, F., Pérez, C.J., Ayra, E.S.: A Bayesian-network-based approach to risk analysis in runway excursions. J. Navig. 72(5), 1121–1139 (2019)
Wang, L., Ren, Y., Sun, H., Dong, C.: A landing operation performance evaluation system based on flight data. In: Harris, D. (ed.) EPCE 2017. LNCS (LNAI), vol. 10276, pp. 297–305. Springer, Cham (2017). https://doi.org/10.1007/978-3-319-58475-1_22
Wang, L., Wu, C., Sun, R.: An analysis of flight quick access recorder (QAR) data and its applications in preventing landing incidents. Reliab. Eng. Syst. Saf. 127, 86–96 (2014)
Hu, C., Zhou, S.-H., Xie, Y., Chang, W.-B.: The study on hard landing prediction model with optimized parameter SVM method. In: 2016 35th Chinese Control Conference (CCC), pp. 4283–4287. IEEE (2016)
Tong, C., Yin, X., Wang, S., Zheng, Z.: A novel deep learning method for aircraft landing speed prediction based on cloud-based sensor data. Future Gener. Comput. Syst. 88, 552–558 (2018)
Tong, C., et al.: An innovative deep architecture for aircraft hard landing prediction based on time-series sensor data. Appl. Soft Comput. 73, 344–349 (2018)
Wang, L., Ren, Y., Wu, C.: Effects of flare operation on landing safety: a study based on ANOVA of real flight data. Saf. Sci. 102, 14–25 (2018)
Khatwa, R., Helmreich, R.L.: Analysis of critical factors during approach and landing in accidents and normal flight. Flight Saf. Digest 17(11–12), 1–2 (1999)
Nielsen, T.D., Jensen, F.V.: Bayesian Networks and Decision Graphs. Springer, New York (2007). https://doi.org/10.1007/978-0-387-68282-2
Li, X., Shang, J., Zheng, L., Liu, D., Qi, L., Liu, L.: CurveCluster: automated recognition of hard landing patterns based on QAR curve clustering. In: IEEE 16th International Conference on Ubiquitous Intelligence and Computing (UIC), pp. 602–609. IEEE (2018)
Park, S.H., Kim, B., Kang, C.M., Chung, C.C., Choi, J.W.: Sequence-to-sequence prediction of vehicle trajectory via LSTM encoder-decoder architecture. In: 2018 IEEE Intelligent Vehicles Symposium (IV), pp. 1672–1678. IEEE (2018)
Janakiraman, V.M.: Explaining aviation safety incidents using deep temporal multiple instance learning. In: Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, pp. 406–415 (2018)
Berrut, J.-P., Trefethen, L.N.: Barycentric Lagrange interpolation. SIAM Rev. 46(3), 501–517 (2004)
He, X., et al.: Practical lessons from predicting clicks on ads at Facebook. In: Proceedings of the Eighth International Workshop on Data Mining for Online Advertising, pp. 1–9 (2014)
Hastie, T., Friedman, J., Tibshirani, R.: The Elements of Statistical Learning, vol. 1, no. 10. SSS, Springer, New York (2001). https://doi.org/10.1007/978-0-387-21606-5
Cho, K., et al.: Learning phrase representations using RNN encoder-decoder for statistical machine translation. arXiv preprint arXiv:1406.1078 (2014)
Luong, M.-T., Pham, H., Manning, C.D.: Effective approaches to attention-based neural machine translation. arXiv preprint arXiv:1508.04025 (2015)
Acknowledgements
We thank Dongcheng Chen, Xuan Ding, Lilin Yu, Hao Xie, Lin Qi, Liu Liu, Zhe Huang and Ziwen Liao for their professional opinions and discussions. This work was supported in part by: National Natural Science Foundation of China (Nos. 61702059, 61966008), Fundamental Research Funds for the Central Universities (Nos. 2019CDXYJSJ0021, 2020CDCGJSJ041), Frontier and Application Foundation Research Program of Chongqing City (No. cstc2018jcyjAX0340), Key Research and Development Program of Chongqing (No. cstc2019jscx-fxydX0071), Guangxi Key Laboratory of Optoelectronic Information Processing (No. GD18202), Guangxi Key Laboratory of Trusted Software (Nos. kx201701, kx201702).
Author information
Authors and Affiliations
Corresponding authors
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this paper
Cite this paper
Kang, Z. et al. (2020). A Deep Sequence-to-Sequence Method for Aircraft Landing Speed Prediction Based on QAR Data. In: Huang, Z., Beek, W., Wang, H., Zhou, R., Zhang, Y. (eds) Web Information Systems Engineering – WISE 2020. WISE 2020. Lecture Notes in Computer Science(), vol 12343. Springer, Cham. https://doi.org/10.1007/978-3-030-62008-0_36
Download citation
DOI: https://doi.org/10.1007/978-3-030-62008-0_36
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-62007-3
Online ISBN: 978-3-030-62008-0
eBook Packages: Computer ScienceComputer Science (R0)