Enhanced Fault-Tolerant Neural Controller for Aircraft Auto-Landing

Pashilkar, AA (2005) Enhanced Fault-Tolerant Neural Controller for Aircraft Auto-Landing. Technical Report. National Aerospace Laboratories, Bangalore, India.

[img] PDF
Restricted to Repository staff only

Download (13MB)
[img] Indexer Terms (Generate index codes conversion from application/pdf to indexcodes)
Restricted to Repository staff only

Download (3kB)


This report presents a neural-aided controller that enhances the fault tolerant high performance fighter aircraft during the landing phase when subjected to severe winds and failures such as stuck control surfaces. The controller architecture uses a neural controller aiding an existing conventional controller using a feedback error learning mechanism. The neural controller employs a dynamic Radial Basis Function neural network called Extended Minimal Resource Allocating Network (EMRAN), which uses only on-line learning and does not need prior training. The information about actuator failures is not available to the controller for use in reconfiguration. It is also assumed that the aircraft control system does not use angle of attack and sideslip for purposes of feedback.13; The neural controller augmentation improves the ability of the baseline control system to handle large faults and meet the strict touchdown dispersion requirements, thus enlarging the fault-tolerance envelope. The performance of this controller is also compared to the Nonlinear Dynamic Inversion (ND!) controller and a high gain version of the baseline controller. A separately designed fault tolerant controller using Reliable H2 approach is also used as the baseline and it is shown that its performance is also improved by neural network augmentation. Finally parameter selection of the EMRAN learning algorithm using Genetic Algorithm based optimization is presented.

Item Type: Monograph (Technical Report)
Uncontrolled Keywords: Neural network;Fault tolerant;Actuator failure;Auto landing
Subjects: AERONAUTICS > Aircraft Stability and Control
Depositing User: Smt Bhagya Rekha KA
Date Deposited: 16 Jan 2009
Last Modified: 24 May 2010 04:12
URI: http://nal-ir.nal.res.in/id/eprint/1490

Actions (login required)

View Item View Item