Optimisation of chemical composition of high speed steel with high vanadium content for abrasive wear using an artificial neural network

Abstract The wear weight loss were measured by pin-disk abrasive wear machine after high speed steels with V  = 5–10% and C  = 1.66–3.3% were quenched at 1050 °C, and tempered at 550 °C. By the use of back propagation (BP) network, the non-linear relationship between the wear weight losses ( W ) and carbon contents, vanadium contents ( C , V ) has been established on the base of dealing with the experimental data. The results show that the well-trained BP neural network can predict the wear weight loss precisely according to carbon contents and vanadium contents. The prediction results show the optimal V and C contents for abrasive wear are 9–10% and 3–3.4%, respectively. And the prediction values have sufficiently mined the basic domain knowledge of relationship between abrasive wear property and chemical composition of alloys. Therefore, a new way of optimising chemical composition for wear of materials has been provided by the authors.