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 authors developed a method for the automated detection and calculation of quantitative parameters of dimples of ductile fracture on the digital images of fracture surfaces obtained at different scales. The processing algorithm of fractographic images was proposed, which allowed high quality recognition of the shape and size of dimples to be achieved, taking into account the morphological features of their digital images. The developed method for identifying dimples of various physical and morphological characteristics was tested on the VT23M alloy. The test results showed that the method meets the quality requirements for the automated diagnostics of fracture mechanisms of titanium alloys.

This contribution is focused on the influence of build orientation on hardness of materials sintered using direct metal laser sintering (DMLS) technology. It builds on the current research works that has monitored the influence of build orientation on a fatigue life, mechanical properties, roughness after machining, etc. In the mentioned work, a slight influence of build orientation on the above properties was shown. The hardness was measured on a Ti6Al4V alloy which was made of powder by DMLS technology. The individual materials were sintered at different laser powers, then annealed to remove internal stresses. Part of the experiment examined the metallographic analysis of materials in the direction perpendicular to the sintered layers and parallel with the sintered layers. Microhardness was measured on metallographic cross-sections and the results were statistically processed. The influence of laser power on a respective material hardness was assessed by one-way analysis of variance (ANOVA), a comparison of the hardness between sintered and sintered-annealed samples, as well as the comparison of hardness in the two considered directions was performed by t-test and F-test. A statistically significant difference in the hardness of the materials prepared at different laser powers was found. The influence of heat treatment, as well as the direction of material building also showed a statistically significant difference.

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.