Uncertainty Analysis of a Dynamic Model of a Novel Remotely Piloted Airship

TLDR: In this paper, a probabilistic Bayesian uncertainty analysis was performed, whereby the output of a model is sampled over a set of input points and the response of the model is emulated by a Gaussian process, allowing a reliable uncertainty analysis to be performed for considerably less computational expense than conventional Monte Carlo methods.

Abstract: As the sophistication of finite element models increases, the need to investigate the effects of uncertainties in model inputs becomes increasingly important in the interests of developing a robust model. A novel design of an unmanned airship is under development at the Politecnico di Torino, Italy. Structural and fluid. structure interaction models were developed to ascertain the response of the structure under operational and aerodynamic loading; however, uncertainties in material properties (due to variation with temperature), pressure, and aerodynamic loading necessitated an uncertainty analysis. Since the computational expense of a large finite element model makes Monte Carlo methods impractical, a probabilistic Bayesian uncertainty analysis was performed, whereby the output of the model is sampled over a set of input points and the response of the model is emulated by a Gaussian process. Quantities pertaining to uncertainty analysis were then inferred, allowing a reliable uncertainty analysis to be performed for considerably less computational expense than conventional Monte Carlo methods. The results showed that uncertainty in model stress and deflection is indeed significant, although the highly nonlinear response of the fluid. structure interaction model required a high sampling density in order to accurately emulate its response. Copyright © 2011 by the American Institute of Aeronautics and Astronautics, Inc. All rights reserved.