Neural Network Approach to Construct a Processing Map from a Non-linear Stress–Temperature Relationship

Abstract

An accurate processing map for a metal provides a means of attaining a desired microstructure and required shape through thermo-mechanical processing. To construct such a map, the isothermal flow stress, σ_iso, is required. Conventionally, the non-isothermal flow stress measured by experiment is corrected to σ_iso using whole-temperature-range linear interpolation (WRLI) or partial-temperature-range linear interpolation (PRLI). However, these approaches could incur significant errors if the non-isothermal flow stress exhibits a non-linear relationship with the temperature. In this study, an artificial neural network (ANN) model was applied to correct the non-isothermal flow stress in 10 wt% Cr steel, which exhibits a non-linear temperature dependence within a target temperature range of 750–1250 °C. Processing maps were constructed using σ_iso corrected by applying the WRLI, PRLI, and ANN approaches, respectively, and were then compared with the actual microstructures. The WRLI approach produced the highest minimum error of σ_iso (17.2%) and over-predicted the shear-band formation. The PRLI approach reasonably predicted the microstructural changes, but the minimum error for σ_iso (8.9%) was somewhat high. The ANN approach not only realized the lowest minimum error of σ_iso (~ 0%), but also effectively predicted the microstructural changes.