Application of neural networks for the prediction of multidirectional magnetostriction

Inverse identification of pipeline steel mechanical state by means of coupled magnetic measurements and artificial neural networks

“…It is especially interesting for the modeling of complex problems involving non linear relationships between inputs and outputs. For example, [19] used ANN to predict the magnetostriction characteristics of transformer core material and showed good ability to fit experiments. Similarly, a Genetic Algorithm (GA) based Back-Propagation (BP) neural network was used to characterize the crack depth and width in a ferromagnetic material in [20].…”