Online Prediction of Plate Deformations Under External Forces Using Neural Networks

Abstract

Recently online prediction of plate deformations in modern systems have been considered by many researchers, common standard methods are highly time consuming and powerful processors are needed for online computation of deformations. Artificial neural networks have capability to develop complex, nonlinear functional relationships between input and output patterns based on limited data. A good trained network could predict output data very fast with acceptable accuracy. This paper describes the application of an artificial neural network to identify deformation pattern of a four-side clamped plate under external loads. In this paper the distributed loads are approximated by a set of concentrated loads. An artificial neural network is designed to predict plate deformation pattern under external forces. Results indicate a well trained artificial neural network reveals an extremely fast convergence and a high degree of accuracy in the process of predicting deformation pattern of plates. Additionally this paper represents application of neural network in inverse problem. This part illustrates the capability of neural networks in identification of plate external loads based on plate deformations. Load identification has many applications in identification of real loads in machineries for design and development.