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.
An automated method for analyzing the shape and size of dimples of ductile tearing formed during static and impact fracture of titanium alloys VT23 and VT23M is proposed. The method is based on the analysis of the image topology. The method contains the operations of smoothing the initial fractographic image; its convolution with a filter to identify the topological ridges; thresholding with subsequent skeletonization to identify boundaries between dimples; clustering to isolate the connected areas that represent the sought objects-dimples. For each dimple, the following quantitative characteristics were calculated: area, coefficient of roundness and visual depth in units of image intensity. The surface of ductile tearing was studied by analyzing the peculiarities of parameter distribution of the found dimples. The proposed method is applied to fractograms of fracture surfaces of titanium alloys VT23 and VT23M.
Coatings based on epoxy diane oligomer ED-20 are being developed as environmentally benign, foulingresistant marine coatings. Silver oxide and carbonate (mixture) was used as filler, the dispersion of which is 0.5 µm. It is proved that for the formation of composites with the improved physical and mechanical properties it is necessary to add Mechanical Mixture of Silver Carbonate and Oxide (MMSCO) in the amount of q = 0.050…0.250 pts. wt. into the epoxy diane oligomer ED-20 (100 pts. wt.). The obtained values of impact toughness of composites during the introduction of MMSCO into the binder increased by 2.5 times compared to the epoxy matrix. Moreover, the maximum capacity to resist impact loads, including fracture toughness, was demonstrated by the Composite Material (CM) with the filler content q = 0.050 pts. wt. Impact toughness of this CM is а = 18.53 kJ/m2. The developed materials and protective coatings based on them were used on the dry cargo ship Oles Honchar.
The areas of low frequency and corrosion fatigue for basic metal and welding joints of oil and gas pipelines have been determined on the basis of corrosion-fatigue test results. The most dangerous diapasons of the operation loadings were also determined. The present work also proposes the methodical approaches to the survivability prediction.
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.