DOI QR코드

DOI QR Code

Neural Network Based Adaptive Control for a Flying-Wing Type UAV with Wing Damage

주익이 손상된 전익형 무인기를 위한 신경회로망 적응제어기법에 관한 연구

  • Kim, DaeHyuk (Research Institute of Marine Systems Engineering, Seoul National University) ;
  • Kim, Nakwan (Research Institute of Marine Systems Engineering, Seoul National University) ;
  • Suk, Jinyoung (Department of Aerospace Engineering, Chungnam National University) ;
  • Kim, Byungsoo (Department of Aerospace Engineering, Gyeongsang National University)
  • Received : 2013.01.25
  • Accepted : 2013.04.29
  • Published : 2013.05.01

Abstract

A damage imposed on an unmanned aerial vehicle changes the flight dynamic characteristics, and makes difficult for a conventional controller based on undamaged dynamics to stabilize the vehicle with damage. This paper presents a neural network based adaptive control method that guarantees stable control performance for an unmanned aerial vehicle even with damage on the main wing. Additionally, Pseudo Control Hedging (PCH) is combined to prevent control performance degradation by actuator characteristics. Asymmetric dynamic equations for an aircraft are chosen to describe motions of a vehicle with damage. Aerodynamic data from wind tunnel test for an undamaged model and a damaged model are used for numerical validation of the proposed control method. The numerical simulation has shown that the proposed control method has robust control performance in the presence of wing damage.

무인항공기가 외형손상을 입는 경우, 비행역학 특성이 변하기 때문에 손상 이전 설계된 제어기는 더 이상 안정적인 제어성능을 보장하지 않는다. 본 논문에서는 주익의 손상이 일어난 무인항공기에 대해서도 강건한 제어성능을 보장하는 신경회로망 적응제어기법을 소개한다. 구동기의 특성에 의한 제어기의 성능저하를 방지하기 위해 Pseudo Control Hedging (PCH)를 추가적으로 사용하였다. 기체고정좌표계의 중심이 항공기의 무게중심에 위치하지 않는 비대칭 동역학을 사용하였으며, 전익형 무인기를 대상 비행체로 하였다. 날개가 손상되지 않은 모델과 손상된 모델의 풍동시험을 통해 얻은 공력데이터를 이용하여 시뮬레이션을 수행하였다. 시뮬레이션의 결과를 통해 제안된 제어기법이 주익의 손상이 발생한 항공기에 대해서도 여전히 안정적인 조종성능을 보장하는 제어기법임을 검증하였다.

Keywords

References

  1. Barton J. Bacon and Irene M. Gregory, "General Equations of Motion for a Damaged Asymmetric Aircraft," Proceedings of 2007 AIAA GNC Conference, No. AIAA-2007-6306, Hilton Head, SC, August 2007.
  2. A. J. Calise, N. Hovakimyan, M. Idan, "Adaptive output feedback control of nonlinear systems using neural networks," Automatica, Vol.37, No.8, 2001, pp. 1201-1211. https://doi.org/10.1016/S0005-1098(01)00070-X
  3. B.S. Kim. and A. J. Calise, "Nonlinear Flight Control Using Neural Networks," Journal of Guidance, Control and Dynamics, Vol.20, No.1, 1997, pp. 26-33. https://doi.org/10.2514/2.4029
  4. Corey Ippolito and Yoo-Hsiu Yeh, John Kaneshige, "Neural Adaptive Flight Control Testing on an Unmanned Experimental Aerial Vehicle," Proceedings of 2007 Aerospace Conference and Exhibit, AIAA-2007-2827, 2007.
  5. Liu, Y., and Tao, G., "Multivariable MRAC for Aircraft with Abrupt Damages," Proceedings of 2008 American Control Conference, Inst. of Elecrical and Electronics Engineers, Piscataway, NJ, June 2008, pp. 2981-2986.
  6. Nhan Nguyen, Kalmanje Krishnakumar, John Kaneshige, Pascal Nespeca, "Dynamics and Adaptive Control for Stability Recovery of Damaged Asymmetric Aircraft," AIAA Guidance, Navigation, and Control Conference and Exhibit, AIAA-2006-6049.
  7. A. J. Calise, Seungjae Lee, and Manu Sharma, "Development of a Reconfigurable Flight Control Law for Tailless Aircraft," Journal of Guidance, Control and Dynamics, Vol.24, No.5, 2001, pp. 896-902. https://doi.org/10.2514/2.4825
  8. Jongmin Ahn, Kijoon Kim, Jinyoung Suk, "Study of Damaged Asymmetric Aircraft's Flight Dynamics Characteristics," Proceedings 2011 of Korean Society for Aeronautical and Space Sciences, 2011, pp. 459-462.
  9. Kijoon Kim, Jong-min Ahn, Jae-Ha Lee, Jong Su Choi, Heungsik Lim, Ki-Bong Huh, Jinyoung Suk, "Flight Dynamic Characteristics of a Flying-Wing Type UAV with Wing Damage," Proceedings 2012 of Korean Society for Aeronautical and Space Sciences, 2012, pp. 394-399.
  10. Nelson, R.C., "Flight stability and automatic control", McGraw Hill 2nd edition, 1998.
  11. Nakwan Kim, Eung Tai Kim, Jangho Lee, "Development of a Reconfigurable Flight Controller Using Neural Networks and PCH", Journal of Institute of Control, Robotics and Systems, Vol.13, No.5, pp.422-428 https://doi.org/10.5302/J.ICROS.2007.13.5.422