Optimization of fatigue life of pearlitic Grade 900A steel based on the combination of genetic algorithm and artificial neural network

In this paper, the fatigue life of pearlitic Grade 900A steel used in railway applications is investigated. To predict the fatigue life of pearlitic Grade 900A steel based on the number of cycles of the particular stress level in the load block, occurrence ratio and overload ratio, a feed-forward neural network is designed. The results of this artificial neural network are compared to the surface fitting method. Then sensitivity analysis is applied to the obtained artificial neural network values to measure the effect of each input parameter on the fatigue life. Finally, the genetic algorithm is applied to find the maximum fatigue life based on the input values.