An automated method for detecting and classifying three classes of surface defects in rolled metal has been developed, which allows for conducting defectoscopy with specified parameters of efficiency and speed. The possibility of using the residual neural networks for classifying defects has been investigated. The classifier based on the ResNet50 neural network is accepted as a basis. The model allows classifying images of flat surfaces with damage of three classes with the general accuracy of 96.91% based on the test data. The use of ResNet50 is shown to provide excellent recognition, high speed, and accuracy, which makes it an effective tool for detecting defects on metal surfaces.
Abstract:The contribution presents the research results of hardfacing metals' resistance in conditions of abrasive wear. Two types of hardfacing electrodes with a different chemical composition were used in the creation of three layers of hardfacing metals. The chemical composition of electrodes determines the difference in a hardface deposit structure. We have investigated the influence of mixing the base metal and a filler metal and the influence of hardfacing welds structure on the resistance against abrasive wear. The results of the experiments have showed that the intensity of wear is very dependent on the parameters of wear as well as the morphology structure of hardfacing metals.
The factors that affect the life of continuous steel casting rollers were investigated. Rollers that were removed from a manufacturing line because they had failed were renovated by submerged arc welding and subjected to working conditions until they again failed. The welding parameters (welding current, welding voltage, welding speed, current polarity, preheating temperature, interpass, postheating, and cooling conditions of clad) and chemical reactions and compositions had important effects on roller lifetime. Chromium has a dominant influence on the abrasion resistance of hard martensitic structures of the roller. Cr produces several types of precipitates (M3C, M23C6, M7C3, and M3C2). Alloying elements Mo and V in welding wire form fine carbides Mo2C and VC in weld layers. In low-carbon welding wires, precipitation hardening by N2 is used, by formation of chromium nitrides CrN and Cr2N. This article analyzes the process of failure of the functional surfaces of the repaired roller, in order to identify the origin and propagation of the cracks and share of corrosive environment on the tribo-degradation processes.
Abstract:The paper presents the results of resistance spot welding of hot-dip galvanized microalloyed steel sheets used in car body production. The spot welds were made with various welding currents and welding time values, but with a constant pressing force of welding electrodes. The welding current and welding time are the dominant characteristics in spot welding that affect the quality of spot welds, as well as their dimensions and load-bearing capacity. The load-bearing capacity of welded joints was evaluated by tensile test according to STN 05 1122 standard and dimensions and inner defects were evaluated by metallographic analysis by light optical microscope. The welding parameters of investigated microalloyed steel sheets were optimized for resistance spot welding on the pneumatic welding machine BPK 20.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.