Fatigue Life Prediction of Reinforced Concrete Using Artificial Neural Network

Abstract

Fatigue is a phenomenon of gradual, permanent internal changes in a material due to repeated or cyclic loading. The fatigue failure of structural elements may decreases the life of infrastructures, therefore the fatigue life of those structures should be considered. Highway and airfield pavements, bridge decks, offshore supporting structure, machinery foundation etc. are subjected to high cycle repeated loading. The randomness in parameters due to the heterogeneous nature of concrete due to fatigue loading leads to complexities in analysing fatigue failure of reinforced concrete. Probabilistic approach is more dependable for the prediction of fatigue life of reinforced concrete than deterministic approach as it can include variations and uncertainties. In recent years, artificial neural network emerged as a new promising computational tool which adopts a probabilistic approach for modelling complex relationships. The purpose of this study is to extract the data from fatigue tests conducted on reinforced concrete beam to create an artificial neural network predictive model. The developed model can able to predict the critical crack length of reinforced concrete members at which failure occurs by considering the fracture mechanics properties and material properties accountable for the softening behaviour of concrete as input. The developed ANN model and analytical model is capable of predicting the fatigue life of reinforced concrete with reasonable accuracy and in a faster approach.