Abstract
Purpose – The purpose of this paper is to present a new technique based on the combination of wavelet packet transform (WPT) and artificial neural networks (ANNs) for predicting the ice accretion on the surface of an airfoil. Design/methodology/approach – Wavelet packet decomposition is used to reduce the number of input vectors to ANN and to improve the training convergence. An ANN is developed with five variables (velocity, temperature, liquid water content, median volumetric diameter and exposure time) taken as input data and one dependent variable (the decomposed ice shape) given as the output. For the purpose of comparison, three different ANNs, back-propagation network (BP), radial basis function network (RBF) and generalized regression neural network (GRNN), are trained to simulate the wavelet packet coefficients as a function of the in-flight icing conditions. Findings – The predicted ice accretion shapes are compared with the corresponding results from previously published NASA experimentation, L...
Highlights
Aircraft icing has long been recognized for over sixty years and continues to be an important flight safety issue in the aerospace community
It is well recognized that several parameters, such as exposure time, liquid water content (LWC), median volumetric diameter (MVD), temperature, flight speed, angle of attack (AOA) and the chord length, play an dominate role in ice accretion
The present study proposes a new methodology by the application of wavelet packet transform (WPT) and artificial neural networks (ANNs) to predict a 2D aircraft ice accretion
Summary
Aircraft icing has long been recognized for over sixty years and continues to be an important flight safety issue in the aerospace community. Droplets may freeze directly, building up rime ice or form a thin water film before freezing, and it may lead to glaze ice under certain conditions of high temperature and large LWC [3,4] The former ice shape presents a smooth outline and can be simulated . In order to overcome these limitations, some researchers proposed a fast prediction method for aircraft icing through statistical strategy [9,10,11] These efforts have achieved success in improving the icing prediction efficiency, but owning to the insufficiency and non-grid of the experimental data, a considerable computing time is still needed to obtain numerical simulation samples for the interpolation procedure.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
