Automatic steel grades design for Jominy profile achievement through neural networks and genetic algorithms

Abstract

The paper proposes an approach to the design of the chemical composition of steel, which is based on neural networks and genetic algorithms and aims at achieving a desired hardenability behavior possibly matching other constraints related to the steel production. Hardenability is a mechanical feature of steel, which is extremely relevant for a wide range of steel applications and refers to the steel capability to improve its hardness following a heat treatment. In the proposed approach, a neural-network-based predictor of the so-called Jominy hardenability profile is exploited, and an optimization problem is formulated, where the optimization function allows taking into account both the desired accuracy in meeting the target Jominy profile and other constraint. The optimization is performed through genetic algorithms. Numerical results are presented and discussed, showing the efficiency of the proposed approach together with its flexibility and easy customization with respect to the user demands and production objectives.

A Novel Approach to Jominy Profile Prediction Based on 1D Convolutional Neural Networks and Autoencoders that Supports Transfer Learning

“…new product types, different plants). These results encourage further developments of this technology that will involve testing in a material design context as in [10], the evaluation of different and types of autoencoders for profile encoding, and development of a chemical encoder that exploits the theoretical knowledge regarding the influence of various chemical elements in different regions of the profile.…”

“…filters 2,3,5,10 Dimension 1D Conv. filters 2,3,4 Pooling dimension 2,3,4 Latent space dimension 2,3,4,5,6 JEncoder-JDecoder layers (10,10), (10,10,10), (20,10), (20,20), (20,20,20), (30,30) ChemEncoder layers (10,10), (10,10,10), (20,10), (20,20), (20,20,20), (30,30)…”