International Journal of Engineering and Technology

Environmental awareness today motivates the researchers, worldwide on the studies of natural fiber reinforced polymer composite and cost effective option to synthetic fiber reinforced composites. This work is concerned with the modeling and simulation of bearing properties of hybrid fiber polymer composite mechanical joint using Artificial Neural Network (ANN). In general it was found that increase in bearing capacity was always with increasing the e/d and w/d ratio. However, the extent of increase/decrease depends on the type of stacking sequence. There was increase in strength with rise in natural fiber loading. In this study, an artificial neural network is developed to predict the response of bolt-loaded fiber reinforced polymer composite plates. To predict the behavior of the laminate failure, a multilayered feed-forward neural network trained with the back-propagation algorithm is constructed. The ANN was trained and verified using experimental data. Comparisons of ANN results with desired values showed that there is a good agreement between input and output variables of the experimental data. The results indicate that ANN was illustrated to be a valid useful and powerful tool for the prediction of bearing properties predictions of bolted joints in composite laminates.