ICGST- ACSE Journal

ACSE
 Volume (6), Issue (4) ICGST
 
FAULT TOLERANT FLIGHT CONTROLLER WITH NEURAL NETWORK AUGMENTATION FOR A HIGH PERFORMANCE FIGHTER AIRCRAFT DURING AUTO-LANDING
NAGARAJ RAMRAO1, T.V. RAMAMURTHY2
1Director, Centre for Cognitive Technologies, Department of Electronics & Communication Engineering, R. V. College of Engineering, Bangalore, INDIA
2Professor & HOD, Department of Electronics & Communication Engineering, Sir M. Visvesvaraya Institute of Technology, Bangalore, INDIA,  
Visvesvaraya Technological University, Karnataka, INDIA

Abstract:

There are regimes during which the aircraft has to fly at high angle of attack. The control laws for such maneuvers are very non-linear. This non-linearity arises due to non-linear aerodynamics and the non-inertial couplings in this flight regime. These control laws are based on inverting the dynamic and the kinematics equations of motion. During this inversion process the state variables are measured and then these are used to model the forces and moments corresponding to the undesired aerodynamic, gravitational or the inertial contributions. In this paper we use opposing forces and moments to negate the undesired contributions followed by the application of the desired forces and moments needed to complete the maneuver. Here we deal with NDI controllers for fault tolerance to control surface faults. The non-linear inverse functions appearing in the NDI controller are approximated online using Radial Basis Functions Neural Networks (RBFNN). The function approximation algorithm is called Extended Minimum Resource Allocation Network (EMRAN), which is based on RBFNN, is used in our work. This algorithm is based on the feedback error learning strategy proposed by Gomi and Kawato.

Keywords:  Auto-landing, Nonlinear dynamic inversion, neural network, radial basis function, minimum resource allocation, surface actuators.

(Full Paper, 681 KB)

Biographies:

Mr. Nagaraj Ramrao, is Director, Centre for Cognitive Technologies, Department of Electronics & Communication Engineering, R. V. College of Engineering, Bangalore, Karnataka, India. He is pursuing his doctoral degree in Automatic Flight Control Systems. He obtained his Masters degree in Power Electronics from Gulbarga University and BE in Electronics from Bangalore University. His research interests are Aerospace Electronics, Industrial Electronics & Control and Digital Signal Processing. He has guided more than 30 undergraduate projects. Currently he is teaching courses on Power Electronics, Information & coding theory, Control engineering and Statistical signal processing. He has presented and published several papers at national and International conference/journals. He is also a life member of Indian Society for Technical Education and Institute of Electronics & Telecommunication Engineers. He has several ongoing research projects under his supervision, funded by various research labs in India.                       

Dr. T.V. Ramamurthy, joined National Aerospace Laboratories in 1973 after obtaining his Bachelors degree in distinction fro IISc, Bangalore. During his stay at NAL (1973-1999), he was involved in R & D activities in the area of Aerospace Electronics & Systems. He obtained his Masters and Doctorate degrees from IIT, Madras for his research contributions in the thrust areas of NAL. He joined Sir M. Visvesvaraya  Institute of Technology, Bangalore in 2000 where he is currently a Professor and Head of the Department of Electronics & Telecommunication Engineering. Dr. Ramamurthy is a member of Board of Studies of the Visvesvarya Technological University and also was the chairman of Board of Examiners of the same university. He is an IEEE member and also a life member of Indian society for technical education. He has several national and international publications in journals and conferences. He was also an external examiner for the Coventry University (UK).

BibTex:

@ARTICLE{P1110649004,

AUTHOR = {NAGARAJ RAMRAO and T.V. RAMAMURTHY},

TITLE = {NEURAL NEWORK AUGMENTED FAULT TOLERANT FLIGHT CONTROLLER FOR A HIGH PERFORMANCE FIGHTER AIRCRAFT DURING AUTO LANDING},

JOURNAL = {ICGST International Journal on Automatic Control and Systems Engineering, ACSE},

YEAR = {2006},

VOLUME = {06},

ISSUE = {IV},

PAGES={31--38}

}

(Full Paper, 681 KB)