Artificial Neural Networks as Applied to Aircraft Flight Test Planning / Wykorzystanie Sztucznych Sieci Neuronowych W Planowaniu Badań W Locie

Abstract

Abstract Any flight test programme is essentially based on a flight test plan, i.e. a document agreed upon and accepted by all the parties interested in the tests, and authorised by the superior body/authorities responsible for the execution of the tests. The flight test plan determines the number of flights and flight hours indispensable to verify whether a given aircraft satisfies specified requirements. Many and various external factors may have significant and adverse effect on the execution of the flight test program according to the earlier agreed schedule. The study also covers the structure of a model of a management system for aircraft prototype testing, and the structure of artificial neural network (ANN) developed on the basis of experimentally gained data from the military aircraft testing. A mathematical model based on the artificial neural network and its potential for the managing of aircraft prototypes testing has been formulated as well.