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

The authors propose a new method of predictive replacements of belt sections in a conveyor belt loop with their refurbishment based on their condition recognized by specially designed diagnostic devices: DiagBelt and BeltSonic. Selection of the moment for belt replacement is made on the basis of forecasted state of its wear, when steel cable failure density exceeds the selected threshold or the percentage of belt covers abrasion exceeds the permissible level. The use of double belt refurbishment extends the total belt operation time, but without diagnostics, the reconditioning success rate is relatively low. Visual inspection allows only an uncertain assessment of cable condition. New devices give precise assessment of their condition and allow the selection of a non-linear rate of belt condition based on consecutive scans. The assessed condition of the cables is the key factor in successful belt refurbishment and obtained cost savings. Additionally, diagnostics can help extend belt life. Identified failures can be repaired in order to prevent accelerated belt degradation. The use of diagnostics in the current replacement strategy significantly improves the economic efficiency of belt reconditioning. The reuse of the belt core ensures efficient use of resources and reduces the level of waste, which fits into the circular economy.

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