Neuro-wavelet parametric characterization of Jominy profiles of steels

This work compares a few attempts based on Wavelet and Neural networks, for extracting the Jominy hardness profiles of steels directly from chemical c omposition. That is essentially a black-box modeling problem: Wavelet and N eural networks seem powerful, especially when compared with classical metho ds commonly found in literature. In particular, the paper proposes a multi- network architecture, where a first network is used as a parametric modeler of the Jominy profile, while a second one is used as a parameter estimator from the steel chemical composition. Several combinations of Wavelet and N eural networks have been compared. The paper also proposes an innovative me thod to train the activation function which significantly improves network performance.