SavedAdd your journal

Journals / İTÜ Dergisi Seri D: Mühendislik / 2006 / Cilt: 5 - Sayı: 2/1 2/2

Aircraft icing detection and reconfigurable control based on EKF and neural networks

EKF ve yapay sinir ağları ile uçak kanat buzlanmalarının tespiti ve yeniden şekillendirilebilir kontrol

Rahmi AYKAN
Çingiz HACIYEV
Fikret ÇALIŞKAN
Pages
122–132
Publication Date
2022-11-05
DOI
—
🏛️Bibliographic metadata and full text access for this article are provided via DergiPark.
DergiPark Record ↗
✨

AI Summary & Key Takeaways

AI Insight
⚡ TL;DR(Too Long; Didn't Read)

The methods proposed in this work provides insight on how flight data can be processed.

📌 3 Key Takeaways

🎯
Objective & Hypothesis:The recent improvements and research on aviation have focused on the subject of aircraft safe flight even in the severe weather conditions.
📊
Key Findings & Data:This work aims at the detection and identification of icing and reconfigurable control in one military aircraft, F16.
💡
Conclusion & Impact:The methods proposed in this work provides insight on how flight data can be processed.
🔬Design:Modeling & Simulation
📍Scope:Comprehensive Sample
⚙️Variables:Domain Parameters

Abstract

The recent improvements and research on aviation have focused on the subject of aircraft safe flight even in the severe weather conditions. In military and commercial aviation, flight in all weather conditions has necessitated the correctly detecting icing and taking reasonable measures against this. This work aims at the detection and identification of icing and reconfigurable control in one military aircraft, F16. Icing model of aircraft is represented with five parameters based on past experiments about wing airfoils. Icing is detected by EKF innovation sequence approach on aircraft dynamic characteristics. A neural network structure is embodied such that its inputs are the aircraft states measured and unmeasured, and its outputs are icing parameters. The necessary training and validation set for the neural networks model of iced aircraft are obtained from the simulations, which are performed various icing conditions. In order to decrease noise effects on the states and to increase training performance of the neural network, the state estimations by EKF are used. A suitable neural network model of iced aircraft is obtained by using the system identification methods and learning algorithms. This trained network model is used as an application for the control of the aircraft that has lost its controllability due to icing. The methods proposed in this work provides insight on how flight data can be processed.

Özet

Askeri ve sivil uçakların bütün hava koşullarında güvenli uçabilmesi dış yüzeylerdeki buzlanmanın doğru tanımlanmasını ve ona karşı önlem alınmasını gerektirmiştir. Bu çalışma ile F16 savaş uçağının uçuş sırasındaki kanat buzlanmalarının tespit, teşhisi ve kontrolü amaçlanmaktadır. Kanat profillerinde yapılan deneysel çalışmalara göre uçağın buzlanma modeli beş adet parametre ile temsil edilmiştir. Uçağın dinamik karakteristiklerinin EKF innovasyon sürecindeki değişiklikleri izlenerek buzlanma tespit edilmektedir.Girişleri ölçülen veya ölçülemeyen uçak durumları ve çıkışları buzlanma parameteleri olan bir yapay sinir ağ yapısı oluşturulmuştur. Eğitilmiş yapay sinir ağı modeli daha sonra buzlanmadan dolayı normal kontrol prensibi ile kontrol edilemeyen uçağın kontrolü için kullanılmıştır.

🔖

Cite This Article

AYKAN, R., HACIYEV, Ç., ÇALIŞKAN, F. (2022). Aircraft icing detection and reconfigurable control based on EKF and neural networks. İTÜ Dergisi Seri D: Mühendislik, Cilt: 5 - Sayı: 2/1 2/2, 122–132. https://ajindex.com/articles/652169

📄 Full Text PDF Viewer

📄

PDF görüntüleyici hazırlanıyor...

References (12)

  1. Aykan, R., (1997). Düzgün doğrusal yatay uçuş yapan bir uçağın kararlılık türevlerinin bulunuşu ve kararlılığının analizi, Yüksek Lisans Tezi, ITU Fen Bilimleri Enstitüsü, İstanbul.
  2. Bragg, M. B., Perkins, W. R., Sarter, N. B., Başar, T., Voulgaris, P. G., Gurbacki, H. M., Melody, J. W., ve McCray, S. A., (1998). An interdisciplinary approach to inflight aircraft icing safety, 36th AIAA Aerospace Sciences Meeting and Exhibit, Bildiri No AIAA-98-0095,
  3. Reno, NV, USA. Bragg, M. B., Hutchison, T., Oltman, R., Pokhariyal, D., ve Merritt, J., (2000). Effect of ice accretion on aircraft flight dynamics, 38th AIAA Aerospace Sciences Meeting and Exhibit, Bildiri No. AIAA- 2000-0360,
  4. Reno, NV, USA. Bragg, M. B., Perkins, W. R., Basar, T., Sarter, N. B., Voulgaris, P. G., Selig, M., ve Melody, J., (2002). Smart ıcing systems for aircraft ıcing safety, 40th AIAA Aerospace Science Meeting and Exhibit, Bildiri No: 2002-0813,
  5. Reno, NV, USA. Gurbacki, M. H. ve Bragg, M. B., (1999). Sensing aircraft ıcing effects by flap hinge moment measurement, 17th Applied Aerodynamic Meeting, Bildiri No. AIAA-99-3149,
  6. Norfolk VA, USA. Hajiyev, Ch. M. ve Çalışkan, F., (2001) Integrated sensor / actuator fdı and reconfigurable control for fault-tolerant flight control system design, The Aeronautical Journal, 105, 1051, 525-533. Johnson M.D, ve Rokhsan K., (2000). Using artificial neural networks and self organizing maps for detection of airframe ıcing, Atmospheric Flight Mechanics Conference, Bildiri No AIAA- 2000-4099,
  7. Denver, USA. Lyshevski, S.E., (1997). State-space identification of nonlinear flight dynamics, In proceedings of theConference on Control Applications, Hartford, Connecticut, 496-498.
  8. McLean, D., (1990).
  9. Automatic flight control systems, Prentice Hall International Ltd., London, UK. Melody, J.W., Başar, T., Perkins, W.R. ve Voulgaris, P. G., (2000). H-infinity parameter identification for inflight detection of aircraft icing, IFAC Control Eng. Practice, 8, 985-1001.
  10. Melody, J.W., Hillbrand, T., Başar, T. ve Perkins, W.R., (2000). H-Infinity parameter ıdentification for ın-flight detection of aircraft ıcing: the time varying case, IFAC Control Engineering Practice, 1327-1335.
  11. Melody, J. W., Pokhariyal, D., Merret, J., Başar, T. ve Bragg, M. B., (2001). Sensor ıntegration for ınflight ıcing characterization using neural networks, 39th Aerospace Science Meeting and Exhibit, AIAA Bildiri No: 2001-0542,
  12. Reno, NV, USA. Mehra, R. K. ve Peschon, J., (1971). An innovations approach