Statistical Analysis and Neural Network in Detecting Steel Cord Failures in Conveyor Belts

This paper presents the identification and classification of steel cord failures in conveyor belt core based on an analysis a two-dimensional image magnetic field changes recorded using Diagbelt system around scanned test belt. The obtained set identified images, for numerous parameters settings device, were base statistical analysis. makes it possible to determine Pearson’s linear correlation coefficient between being changed failures. In second stage research, artificial intelligence methods applied construct multilayer neural network (MLP) teach appropriate damage. both methods, same data sets used, which made compare methods.