APPLICATION OF ARTIFICIAL NEURAL NETWORKS TO LOAD IDENTIFICATION

The intended aim of the study is to develope an approach to the identi fication of the loads acting on aircraft wings, which uses an artifici al neural network to model the load-strain relationship in structural analysis. As the first step of the study, this paper describes the app lication of an artificial neural network to identify the loads distrib uted across a cantilevered beam. The distributed loads are approximate d by a set of concentrated loads. The paper demonstrates that using an artificial neural network to identify loads is feasible and a well tr ained artificial neural network reveals an extremely fast convergence and a high degree of accuracy in the process of load identification fo r a cantilevered beam model. (C) 1998 Elsevier Science Ltd. All rights reserved.