Identification-based aeroengine nonlinear modeling: a comparative study

Abstract

Aeroengine modeling plays an important role in the development of advanced controls and other intelligent functions such as engine health management etc. This is particularly true for those on-board applications, where identification-based modeling approaches are often utilized. While linear modeling methodologies have been extensively introduced in the literature, identification-based nonlinear modeling should be investigated, due to the inherent nonlinear nature of an aeroengine’s dynamical properties. Three approaches, i.e., back propagation (BP) neural networks (BPNN), improved BP neural networks (IBPNN), and a piecewise nonlinear autoregression with extra inputs (PNARX) model, are presented. A comparative study is given for systematic development and illustration of nonlinear modeling techniques. Some practical considerations are also given for guidance of implementing the identification-based nonlinear modeling methodologies.