Purpose: The purpose of this paper is to work out the computer aided method for selecting grades of steel with a required hardenability.

Design/methodology/approach: The purpose has been achieved in two stages. In the first stage a neural network model for calculating the Jominy curve on the basis of the chemical composition has been worked out. This model made possible to prepare, in the second stage, a representative set of data and to work out the neural classifier that would aid the selection of steel grade with the required hardenability. Findings: The calculations made in the paper have confirmed the purposefulness of applying artificial neural networks for aiding the selection of steel with the required hardenability. Research limitations/implications: The presented system may be used in the range of the accepted in the paper mass concentrations of elements. The methodology demonstrated in the paper makes it possible to add new grades of steel to the system.

Practical implications: The worked out model may be used in computer systems of steel selection for the parts of machines exposed to the heat treatment.

Originality/value: The use of the artificial neural networks as an aiding tool for selecting the steel with the required hardenability.