Aircraft Bleed Air System Fault Prediction based on Encoder-Decoder with Attention Mechanism

Su, Siyu; Sun, Youchao; Peng, Chong; Wang, Yifan

doi:10.17531/ein/167792

Artykuł - szczegóły

Tytuł artykułu

Aircraft Bleed Air System Fault Prediction based on Encoder-Decoder with Attention Mechanism

Autorzy

Su Siyu , Sun Youchao , Peng Chong , Wang Yifan

Treść / Zawartość

Pełne teksty:

Pobierz

Identyfikatory

DOI

10.17531/ein/167792

Warianty tytułu

Języki publikacji

Abstrakty

The engine bleed air system (BAS) is one of the important systems for civil aircraft, and fault prediction of BAS is necessary to improve aircraft safety and the operator's profit. A dual-stage two-phase attention-based encoder-decoder (DSTP-ED) prediction model is proposed for BAS normal state estimation. Unlike traditional ED networks, the DSTP-ED combines spatial and temporal attention to better capture the spatiotemporal relationships to achieve higher prediction accuracy. Five data-driven algorithms, autoregressive integrated moving average (ARIMA), support vector regression (SVR), long short-term memory (LSTM), ED, and DSTP-ED, are applied to build prediction models for BAS. The comparison experiments show that the DSTP-ED model outperforms the other four data-driven models. An exponentially weighted moving average (EWMA) control chart is used as the evaluation criterion for the BAS failure warning. An empirical study based on Quick Access Recorder (QAR) data from Airbus A320 series aircraft demonstrates that the proposed method can effectively predict failures.

Słowa kluczowe

bleed air system fault prediction attention mechanism deep learning EWMA control chart

Wydawca

Polskie Naukowo-Techniczne Towarzystwo Eksploatacyjne

Czasopismo

Eksploatacja i Niezawodność

Rocznik

2023

Tom

Vol. 25, no. 3

Strony

art. no. 167792

Opis fizyczny

Bibliogr. 42 poz., rys , tab., wykr.

Twórcy

autor

Su Siyu

siyu_su@nuaa.edu.cn

a Nanjing University of Aeronautics and Astronautics, China

https://orcid.org/0000-0002-5390-2898

autor

Sun Youchao

sunyc@nuaa.edu.cn

a Nanjing University of Aeronautics and Astronautics, China

https://orcid.org/0000-0002-8358-8019

autor

Peng Chong

chong_peng@nuaa.edu.cn

a Nanjing University of Aeronautics and Astronautics, China

autor

Wang Yifan

wang_yf@nuaa.edu.cn

a Nanjing University of Aeronautics and Astronautics, China

Bibliografia

1. Abdelrahman WG, Al-Garni AZ, Al-Wadiee W. Application of Back Propagation Neural Network Algorithms on Modeling Failure of B-737 Bleed Air System Valves in Desert Conditions. Applied Mechanics & Materials 2012; 225: 505-510, http://dx.doi.org/10.4028/www.scientific.net/AMM.225.505.
2. Asteriou D, Hall S. ARIMA Models and the Box-Jenkins Methodology. Applied Econometrics 2011, 2(2): 265-286, http://dx.doi.org/10.1057/978-1-137-41547-9_13.
3. Bahdanau D, Cho K, Bengio Y. Neural Machine Translation by Jointly Learning to Align and Translate. Computer Science 2014; 1409, https://arxiv.org/abs/1409.0473v7.
4. Cheng Y, Huang F, Zhou L, Jin C, Yuejie Z, Tao Z, editors. A hierarchical multimodal attention-based neural network for image captioning. Proceedings of the 40th International ACM SIGIR Conference on Research and Development in Information; 2017; Retrieval, http://dx.doi.org/10.1145/3077136.3080671.
5. Cho K, Merrienboer Bv, Bahdanau D, Bengio Y. On the Properties of Neural Machine Translation: Encoder-Decoder Approaches. Computer Science 2014, https://doi.org/10.48550/arXiv.1409.1259.
6. Cho K, Merrienboer Bv, Gulcehre C, Bahdanau D, Bougares F, Schwenk H, et al. Learning phrase representations using RNN encoder-decoder for statistical machine translation. 2014 Conference on Empirical Methods in Natural Language Processing; 25-29 October, 2014; Doha, Qatar: Association for Computational Linguistics (ACL); 2014; 1724-1734, http://dx.doi.org/10.3115/v1/D14-1179.
7. Di Gangi M, Federico M. Deep Neural Machine Translation with Weakly-Recurrent Units. EAMT 2018, https://arXiv:1805.04185.
8. Dokas IM, Karras DA, Panagiotakopoulos DC. Fault tree analysis and fuzzy expert systems: Early warning and emergency response of landfill operations. Environmental Modelling & Software 2009; 24(1): 8-25, https://doi.org/10.1016/j.envsoft.2008.04.011.
9. Elman JL. Distributed representations, simple recurrent networks, and grammatical structure. Mach Learn 1991; 7(2): 195-225, https://doi.org/10.1007/BF00114844.
10. Feng L, Wang H, Si X, Zou H. A State-Space-Based Prognostic Model for Hidden and Age-Dependent Nonlinear Degradation Process. IEEE Transactions on Automation Science and Engineering 2013; 10(4): 1072-1086, http://dx.doi.org/10.1109/TASE.2012.2227960.
11. Graves A, Mohamed A, Hinton G, editors. Speech recognition with deep recurrent neural networks. 2013 IEEE International Conference on Acoustics, Speech and Signal Processing; 2013 26-31 May 2013, http://dx.doi.org/10.1109/ICASSP.2013.6638947.
12. Guo T, Lin T. Multi-variable LSTM neural network for autoregressive exogenous model. 2018, https://arxiv.org/abs/1806.06384.
13. Guo Y, Sun Y, He Y, Du F, Su S, Peng C. A Data-driven Integrated Safety Risk Warning Model based on Deep Learning for Civil Aircraft. IEEE Transactions on Aerospace and Electronic Systems 2022: 1-14, http://dx.doi.org/10.1109/TAES.2022.3204224.
14. Hübner R, Steinhauser M, Lehle C. A Dual-Stage Two-Phase Model of Selective Attention. Psychological review 2010; 117: 759-784, http://dx.doi.org/10.1037/a0019471.
15. Karpathy A, Fei-Fei L. Deep Visual-Semantic Alignments for Generating Image Descriptions. Ieee T Pattern Anal 2017; 39(4): 664-676, http://dx.doi.org/10.1109/TPAMI.2016.2598339.
16. Kingma DP, Ba JL, editors. Adam: A method for stochastic optimization. 3rd International Conference on Learning Representations, ICLR 2015, May 7, 2015 - May 9, 2015; 2015; San Diego, CA, United states: International Conference on Learning Representations, ICLR, https://arxiv.org/abs/1412.6980v2.
17. Liang Y, Ke S, Zhang J, Yi X, Zheng Y, editors. GeoMAN: Multi-level Attention Networks for Geo-sensory Time Series Prediction. Twenty-Seventh International Joint Conference on Artificial Intelligence 2018, http://dx.doi.org/10.24963/ijcai.2018/476.
18. Liu J, Zio E. SVM hyperparameters tuning for recursive multi-step-ahead prediction. Neural Computing and Applications 2017; 28(12): 3749-3763, http://dx.doi.org/10.1007/s00521-016-2272-1.
19. Liu Y, Gong C, Yang L, Chen Y. DSTP-RNN: A dual-stage two-phase attention-based recurrent neural network for long-term and multivariate time series prediction. Expert Syst Appl 2020; 143, http://dx.doi.org/10.1016/j.eswa.2019.113082.
20. Montgomery DC. Introduction to Statistical Quality Control. NewYork: John Wiley & Sons; 2007.
21. Orchard M, Vachtsevanos G. A particle-filtering approach for on-line fault diagnosis and failure prognosis. Transactions of The Institute of Measurement and Control - TRANS INST MEASURE CONTROL 2009; 31, http://dx.doi.org/10.1177/0142331208092026.
22. Pawełczyk M, Fulara S, Sepe M, De Luca A, Bad ora M. Industrial gas turbine operating parameters monitoring and data-driven prediction. Eksploatacja i Niezawodnosc – Maintenance and Reliability 2020; 22 (3): 391–399, http://dx.doi.org/10.17531/ein.2020.3.2.
23. Peltier V, Dullenkopf K, Bauer H-J, editors. Numerical Investigation of the Aerodynamic Behaviour of a Compressor Bleed-Air System. ASME Turbo Expo 2014: Turbine Technical Conference and Exposition; 2014 June 16–20, http://dx.doi.org/10.1115/gt2014-25822.
24. Peltier V, Dullenkopf K, Bauer HJ, editors. Experimental investigation of the performance of different bleed air system designs. ASME Turbo Expo 2012: Turbine Technical Conference and Exposition, GT 2012, June 11, 2012 - June 15, 2012; Copenhagen, Denmark: American Society of Mechanical Engineers (ASME) 2012, http://dx.doi.org/10.1115/GT2012-68242.
25. Qin Y, Song D, Chen H, Cheng W, Jiang G, Cottrell G. A Dual-Stage Attention-Based Recurrent Neural Network for Time Series Prediction. IJCAI2017, https://arxiv.org/abs/1704.02971v1. https://doi.org/10.24963/ijcai.2017/366
26. Ramirez IS, Mohammadi-Ivatloo B, Marquez FPG. Alarms management by supervisory control and data acquisition system for wind turbines. Eksploatacja i Niezawodnosc 2021; 23(1): 110-6, http://dx.doi.org/10.17531/EIN.2021.1.12.
27. Shang L, Liu G, editors. Heat exchanger fouling detection in a simulated aircraft engine bleed air temperature control system. 2010 IEEE/ASME International Conference on Advanced Intelligent Mechatronics 2010, http://dx.doi.org/10.1109/AIM.2010.5695895.
28. Shang L, Liu G. Sensor and Actuator Fault Detection and Isolation for a High Performance Aircraft Engine Bleed Air Temperature Control System. IEEE Transactions on Control Systems Technology 2011; 19(5): 1260-1268, http://dx.doi.org/10.1109/TCST.2010.2076353.
29. Smith LN, editor Cyclical learning rates for training neural networks. 17th IEEE Winter Conference on Applications of Computer Vision, WACV 2017, March 24, 2017 - March 31, 2017; 2017; Santa Rosa, CA, United states: Institute of Electrical and Electronics Engineers Inc., http://dx.doi.org/10.1109/WACV.2017.58.
30. Smith M, Sulcs P, Walthall R, Mosher M, Kacprzynski G. Design and Implementation of Aircraft System Health Management (ASHM) Utilizing Existing Data Feeds. SAE 2015 AeroTech Congress & Exhibition 2015, https://doi.org/10.4271/2015-01-2587.
31. Su S, Sun Y, Li L, Peng C, Zhang H, Zhang T. Risk Warning for Aircraft Bleed Air System with Multivariate State Estimation Technique. Journal of Aerospace Information Systems 2022; 19(8): 550-564, https://doi.org/10.2514/1.I011011.
32. Sutskever I, Vinyals O, Le QV. Sequence to sequence learning with neural networks. Advances in neural information processing systems 2014; 27.
33. Swanson DC. A general prognostic tracking algorithm for predictive maintenance. 2001 IEEE Aerospace Conference Proceedings (Cat No01TH8542) 2001; 6: 2971-2977, https://doi.org/10.1109/AERO.2001.931317.
34. Wang H, Peng M-j, Wesley Hines J, Zheng G-y, Liu Y-k, Upadhyaya BR. A hybrid fault diagnosis methodology with support vector machine and improved particle swarm optimization for nuclear power plants. Isa T 2019; 95: 358-371, https://doi.org/10.1016/j.isatra.2019.05.016.
35. Wang WQ, Golnaraghi MF, Ismail F. Prognosis of machine health condition using neuro-fuzzy systems. Mech Syst Signal Pr 2004; 18(4): 813-831, https://doi.org/10.1016/S0888-3270(03)00079-7.
36. Yan J, Koç M, Lee J. A prognostic algorithm for machine performance assessment and its application. Production Planning & Control - PRODUCTION PLANNING CONTROL 2004; 15: 796-801, https://doi.org/10.1080/09537280412331309208.
37. Yang B-S, Widodo A. Support Vector Machine for Machine Fault Diagnosis and Prognosis. Journal of System Design and Dynamics 2008; 2: 12-23, https://doi.org/10.1299/jsdd.2.12.
38. Yang C, Lou Q, Liu J, Yang Y, Cheng Q. Particle filtering-based methods for time to failure estimation with a real-world prognostic application. Applied Intelligence 2018; 48(8): 2516-2526, https://doi.org/10.1007/s10489-017-1083-0.
39. Yao R, Guo C, Deng W, Zhao H. A novel mathematical morphology spectrum entropy based on scale-adaptive techniques. Isa T 2022; 126: 691-702, https://doi.org/10.1016/j.isatra.2021.07.017.
40. Zhang Z, Verma A, Kusiak A. Fault Analysis and Condition Monitoring of the Wind Turbine Gearbox. IEEE Transactions on Energy Conversion 2012; 27(2): 526-535, https://doi.org/10.1109/TEC.2012.2189887.
41. Zhao H, Liu J, Chen H, Chen J, Li Y, Xu J, et al. Intelligent Diagnosis Using Continuous Wavelet Transform and Gauss Convolutional Deep Belief Network. IEEE Transactions on Reliability 2022; 1-11, https://doi.org/10.1109/TR.2022.3180273.
42. Zuber N, Bajri R. Gearbox faults feature selection and severity classificatiousing machine learning. Eksploatacja i Niezawodnosc 2020; 22(4): 748-56, https://doi.org/10.17531/ein.2020.4.19.

Uwagi

Opracowanie rekordu ze środków MNiSW, umowa nr SONP/SP/546092/2022 w ramach programu "Społeczna odpowiedzialność nauki" - moduł: Popularyzacja nauki i promocja sportu (2024).

Typ dokumentu

Bibliografia

Identyfikator YADDA

bwmeta1.element.baztech-1c0b502d-1b77-4463-a3ed-bfbd800018c7