Ayad Amjad Abdul-Razzak
Abstract
An artificial neural network (ANN) model has been developed for theprediction of nonlinear response for plates with built-in edges and differentsizes, thickness and uniform loads. The ...
Read More ...
An artificial neural network (ANN) model has been developed for theprediction of nonlinear response for plates with built-in edges and differentsizes, thickness and uniform loads. The model is based on a six-layer neuralnetwork with back propagation learning algorithm. The learning data wereperformed using a nonlinear finite element program, the set of 1500x16represent the deflection response of load. Incremental stages of the nonlinearfinite element analysis was generated by using 25 schemes of built-inrectangular plates with different thickness and uniform distributed loads.The neural network model has four input nodes representing the uniformdistributed load, thickness, length of plate and length to width ratio, fourhidden layers and sixteen output nodes representing the deflection response.Regression analysis between finite element results and values predicted by theneural network model shows the least error. This approach helps in thereduction of the effort and time required determining the load-deflectionresponse of plate as the FE methods usually deal with only a single problemfor each run while ANN methods can solve simultaneously for a patch ofproblems.
