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.

The quality, wear and safety of metal structures can be controlled effectively, provided that surface defects, which occur on metal structures, are detected at the right time. Over the past 10 years, researchers have proposed a number of neural network architectures that have shown high efficiency in various areas, including image classification, segmentation and recognition. However, choosing the best architecture for this particular task is often problematic. In order to compare various techniques for detecting defects such as “scratch abrasion”, we created and investigated U-Net-like architectures with encoders such as ResNet, SEResNet, SEResNeXt, DenseNet, InceptionV3, Inception-ResNetV2, MobileNet and EfficientNet. The relationship between training validation metrics and final segmentation test metrics was investigated. The correlation between the loss function, the $DSC$, $IoU$, $Recall$, $Precision$ and $F1$ validation metrics and $DSC$ test metrics was calculated. Recognition accuracy was analyzed as affected by the optimizer during neural network training. In the context of this problem, neural networks trained using the stochastic gradient descent optimizer with Nesterov momentum were found to have the best generalizing properties. To select the best model during its training on the basis of the validation metrics, the main test metrics of recognition quality (Dice similarity coefficient) were analyzed depending on the validation metrics. The ResNet and DenseNet models were found to achieve the best generalizing properties for our task. The highest recognition accuracy was attained using the U-Net model with a ResNet152 backbone. The results obtained on the test dataset were $DSC=0.9304$ and $IoU=0.9122$.

The impact of the illumination level on the quantitative indicators of mechanical damage of the rolled strip is investigated. To do so, a physical model experiment was conducted in the laboratory. The obtained images of defects at light levels in the range of 2–800 lx were recognized by a neural network model based on the U-net architecture with a decoder based on ResNet152. Two levels of illumination were identified, at which the total area of recognized defects increased: 50 lx and 300 lx. A quantitative assessment of the overall accuracy of defect recognition was conducted on the basis of comparison with data from images marked by an expert. The best recognition result (with Dice similarity coefficient DSC = 0.89) was obtained for the illumination of 300 lx. At lower light levels (less than 200 lx), some of the damage remained unrecognized. At high light levels (higher than 500 lx), a decrease in DSC was observed, mainly due to the fact that the surface objects are better visible and the recognized fragments become wider. In addition, more false-positives fragments were recognized. The obtained results are valuable for further adjustment of industrial systems for diagnosing technological defects on rolled metal strips.

Features of the defect class “scratches, attritions, lines”, their geometric structure, and their causes are analyzed. An approach is developed that defines subclasses within this class of technological defects based on additional analysis of morphological features. The analysis of the reasons for these subclasses allows additional information to be obtained about the rolling process, identifying additional signs of defects, regulating the rolling conditions of steel strips more accurately, and diagnosing the equipment condition.

The paper presents research results on the quality of hardfacing layers made during the renovation of unheated mold surfaces designed for injection of aluminum alloys using the plasma transferred arc (PTA) technology. As mold material, the medium alloy steel X38CrMoV5-1 (H11) was used. For the formation of functional layers, three types of additives in the form of powder were applied: two types on an iron basis with the designation HSS 23 and HSS 30 and one type on a nickel basis with the designation DEW Nibasit 625-P. The hardfacing layers were made on a 120 × 350 × 50 mm plate in two layers on the plasma hardfacing machine PPC 250 R6. The quality of the layers was evaluated by means of nondestructive and destructive tests. The surface integrity of the layers was assessed using visual and capillary tests. The samples passed these tests. The impact of the parameters used and the mixing of the hardfacing metal with base material, as well as the structure analysis, were assessed by means of light and electron microscopy (SEM). The chemical composition of the elements was determined by energy-dispersive X-ray spectroscopy (EDX) analysis using a SEM microscope. The hardness of the individual layers was evaluated. Since, during operation, molds are subjected to significant wear due to friction, the friction coefficients for selected temperatures were determined by the equipment for the evaluation of tribology properties. Based on the experiments conducted, all three types of additives can be used for renovation. However, from a tribology perspective, the additive DEW Nibasit 625-P on a nickel alloy basis is recommended for renovation.

In this article, we analyse five types of coatings, in terms of their microstructure, hardness, porosity, and wear resistance, in the as-sprayed state. The coatings are WC-based (WC-FeCrAl, WC-WB-Co, and WC-NiMoCrFeCo), alloy-based (Co-MoCrSi), or nanoWC coating-based (nanoWC-CoCr). Two tests were applied to assess the wear resistance of the coatings: a dry-pot wear test with two impact angles and an abrasive test using an abrasive cloth with two grit sizes. Porosity was determined by image analysis. Vickers impression was performed on cross-sections of the coatings, in order to determine their indentation fracture toughness. The highest hardness of the tested coatings was recorded for the nanoWC coating, followed by the rest of the WC-based coatings; meanwhile, the lowest hardness was recorded for the alloy coating. Minimal porosity was achieved by the alloy coating, due to its different nature and the absence of hard particles with a higher melting point. The NanoWC coating and other WC-based coatings had a higher porosity; however, porosity did not exceed 1% for each coating. The best wear resistance was achieved by the nanoWC coating, followed by the other WC-based coatings, with the lowest obtained by the alloy coating. The same tendency was recorded when determining the indentation fracture toughness. From a microscopic point of view, the structure of the evaluated coatings is not compact; nevertheless, their properties are excellent, and they act as compact coatings under load.