The paper presents the method in predicting hardness of steel cooled continuously from the austenitizing temperature, basing on the chemical composition, austenitizing temperature and cooling rate. The original method was used for calculating the anisothermic diagrams of the supercooled austenite transformations of the constructional steels using the artificial neural networks. The methods are presented for determining the structure type occurring in the steel after cooling from the austenitizing temperature and for calculating portions of the particular structural components. The set of training data was compiled to carry out this task (400 charges of constructional steels) including their chemical compositions, austenitizing temperatures, and the supercooled austenite transformation diagrams during their continuous cooling.