ESTIMATION OF CONTACT FORCE ON COMPOSITE PLATES USING IMPACT-INDUCED STRAIN AND NEURAL NETWORKS

A method of determining the contact force on laminated composite plate s subjected to low velocity impact is developed using the finite eleme nt method and a neural network. The backpropagation neural network is used to estimate the contact force on the composite plates using the s train signals. The neural network is trained using the contact force a nd strain histories obtained from finite element simulation results. T he finite element model is based on a higher order shear deformation t heory and accounts for von-Karman non-linear strain-displacement relat ions. The non-linear time dependent equations are solved using a direc t iteration scheme in conjunction with the Newmark time integration sc heme. The training process consists of training the network with strai n signals at three different locations. The effectiveness of different neural network configurations for estimating contact force is investi gated. The neural network approach to the estimation of contact force proved to be a promising alternative to more traditional techniques, p articularly for on-line health-monitoring system. (C) 1998 Elsevier Sc ience Limited. All rights reserved.