Modelling fatigue life of multidirectional GFRP laminates under constant amplitude loading with artificial neural networks

Abstract

An artificial neural network has proven to be a sufficient tool for modelling fatigue life of multidirectional composite laminates made of Glass Fibre Reinforced Plastic (GFRP) composite materials and tested under constant amplitude loading patterns. Modelling efficiency of the network was satisfactory for both on- and off-axis coupons life, irrespective of test conditions, i.e., R-ratio that defines the developed stress state on the coupon. Tension-Tension, Compression-Compression and even Tension-Compression loading patterns were investigated and modelling accuracy of the proposed ANN model was validated. The main benefit that this new modelling tool brings is that only a small portion, in the order of 40%-50%, of the experimental data is needed for the whole analysis and thus, expensive and time consuming tests needed for the establishment of S-N curves could be eliminated without any significant loss of accuracy.