Neural Networks Based Fatigue Life Prediction of Multi Walled Carbon Nano Tubes Doped E-Glass/Epoxy Laminates

In recent years, carbon nano tubes and their applications have been the prime focus of research in the field of nanotechnology. In this paper, the fatigue life prediction of multi walled carbon nano tubes (MWCNT) doped E-Glass/Epoxy laminates is presented. Two different doping ratios of MWCNT (0.2% and 0.4%) are considered to demonstrate the improvement in fatigue life of the composite laminate. The fatigue tests are undertaken on an Instron 8802 universal testing machine using a uni-directional (UD) Glass/Epoxy laminate specimen fabricated as per the ASTM standard - ASTM D 3039. An artificial neural network (ANN) based approach with a back propagation algorithm is used to predict the fatigue life cycles. The proposed neural network is trained using the fatigue test data set. The predicted fatigue results from the ANN are in good agreement with the experimental results. The proposed approach can be utilised to predict the fatigue life of Glass/Epoxy laminates for varied MWCNT doping ratios.