Aircraft parameter estimation using recurrent neural networks - A critical appraisal

Raol, JR and Jategaonkar, RV (1995) Aircraft parameter estimation using recurrent neural networks - A critical appraisal. In: AIAA Atmospheric Flight Mechanics Conference, 7-9 Aug 1995, Maryland, United States.

Full text available as:
[img] PDF
Restricted to CSIR-NAL Registered users only

Download (973Kb)


    This paper investigates applicability of dynamic neural networks, often called as Recurrent Neural Networks (RNN), to aircraft parameter estimation. It is demonstrated that the RNNs are amenable to state space model representation and hence adoptable for estimation of aerodynamic derivatives retaining the model parametrization based on the physical insight. Several aspects of similarity between the RNN approach and the conventional aircraft parameter estimation methods such as output error, equation error, or extended Kalman filter are brought out. The proposed approach is first validated on simulated data and then extended to estimate from flight data the aerodynamic derivatives pertaining to the lateral-directional motion of an aircraft. Based on the identification results, the practical utility, advantages and limitations of the RNN approach are critically appraised.

    Item Type: Conference or Workshop Item (Paper)
    Additional Information: Copyright for this paper belongs to AIAA
    Uncontrolled Keywords: Aircraft;Neural networks;Parameter estimation;Errors; Aerodynamics;Mathematical models
    Subjects: AERONAUTICS > Aircraft Stability and Control
    Division/Department: Flight Mechanics and Control Division, Other
    Depositing User: M/S ICAST NAL
    Date Deposited: 20 Aug 2008
    Last Modified: 24 May 2010 09:50

    Actions (login required)

    View Item