An application of learning machine methods in prediction of wear rate of wear resistant casting parts

► Different function of SVM and ISVM models are used to relate the wear rate and chromium content in the alloy. ► A trained algorithm is used for estimating the wear rate of floatation balls. ► The model was tested in real operating condition. ► The statistical indicators for SVM and ISVM models are presented. ► The absolute mean error of ERB (SVM) is 5.85%, while the error of ERBF+POLY (ISVM) is 6.67%.