Using Artificial Neural Networks and self-Organizing Maps for Detection f Airframe Icing

摘要

A method of using artificial neural networks (ANNs) and Kohonen self-organizing maps (SOMs) to detect airframe ice is proposed and investigated. It is hypothesized that ANN systems trained on the aircraft dynamics in real time would converge to different connection weights for iced and clean aircraft. Hohonen SOMs are proposed for detecting these differences automatically and, therefore, recognizing airframe ice accretion.