ANN based prediction model for fatigue crack growth in DP steel

摘要

An artificial neural network (ANN)-based model was developed to analyse high-cycle fatigue crack growth rates (da/dN) as a function of stress intensity ranges (△K) for dual phase (DP) steel. The training data consisted of da/dN at △K ranges between 5 and 16 Mpa /m for DP STEEL WITH MARTENSITE CONTENTS IN THE RANGE 32 TO 76/100. The ANN back-propagation model with Gaussian activation function exhibited excellent agreement with the experimental results. The fatigue crack growth rate predictions were made to demonstrate its practical significance in a given real-life situation. Because of the wide range of data points used during training of the model, it will provide a useful predictor for fatigue crack growth in DP steels.