THE AERONAUTICAL JOURNAL 1 Page 1 of 20. c  Royal Aeronautical Society 2019 doi:10.1017/aer.2019.125 Nonlinear parameter estimation of airship using modular neural network S. Agrawal subhamagrwl246@gmail.com D. Gobiha gobiha@yahoo.com N.K. Sinha nandan@ae.iitm.ac.in Flight Dynamics and Control Lab Department of Aerospace Engineering Indian Institute of Technology Madras Chennai India ABSTRACT The prime focus of this work is to estimate stability and control derivatives of an airship in a completely nonlinear environment. A complete six degrees of freedom airship model has its aerodynamic model as nonlinear functions of angle of attack. Estimating the parameters of aerodynamic model in a nonlinear environment is challenging as it demands an exhaustive dataset that could cover the entire regime of operation of airship. In this work, data genera- tion is achieved by simulating the mathematical model of airship for different trim conditions obtained from continuation analysis. The mathematical model is simulated using predicted parameter values obtained using DATCOM methodology. A modular neural network is then trained using back-propagation and Adam optimisation algorithm for each of the aerodynamic coefficients separately. The estimated nonlinear airship parameters are found to be consistent with the DATCOM parameter values which were used for open-loop simulation. This vali- dates the proposed methodology and could be extended to estimate airship parameters from real flight data. Keywords: Parameter estimation; Neural network; Airship NOMENCLATURE B buoyant force, N b wingspan, m b z point of action of buoyant force along z axis, m C L , C D , C Y lift, drag and side force coefficients Received 30 March 2019; revised 11 July 2019; accepted 10 September 2019.