An Artificial Neural Network Approach to Fatigue Crack Growth
This paper proposes a new three-layer artificial neural network (ANN) to predict the fatigue crack length under constant amplitude mode I cyclic loading. It is shown that the proposed model predicts the crack length with an error of less than 0.05%, and more accurately than the current commonly-used models.
George Ferguson, Ashvin Thambyah, Michael A Hodgson and Kelly Wade
K. Zarrabi et al., "An Artificial Neural Network Approach to Fatigue Crack Growth", Advanced Materials Research, Vol. 275, pp. 3-6, 2011