Samples using powders of four different fractions, 15–20 μm, 20–30 μm, 30–40 μm and 40–45 μm, were fabricated to investigate the wear resistance, corrosion resistance and tribological properties of the 86WC-10Co-4Cr coating obtained using the HVOF method. The phase composition, microstructure and elemental distribution were analyzed using X-ray diffraction, scanning electron microscopy and energy dispersive spectroscopy techniques. The hardness was measured on a Vickers microhardness tester, the friction coefficient and wear rate were investigated using a tribometer, and the corrosion resistance was evaluated on an electrochemical corrosion station. The results showed that the cross-sectional microstructure of the coating is mainly represented by multifaceted WC crystals embedded in the Co-Cr matrix and the presence of lower tungsten carbides, particularly W₂C. The 15–20 μm fraction particles were subjected to superheating, contributing to the decarburization process. The 20–30 µm and 30–40 µm sized particles prevented overheating and had a more homogeneous structure. The 40–45 µm powder fractions did not reach sufficient temperature for complete melting, resulting in the formation of pores in the coating layers. The phase composition of the coatings included WC, W₂C and CoO phases. According to the results of the study, it was found that the optimal powder fraction for coating the 86WC-10Co-4Cr composition with improved characteristics is the fraction of the 20–30 µm sized particles.

The paper is devoted to machine learning methods that focus on texture-type image enhancements, namely the improvement of objects in images. The aim of the study is to develop algorithms for improving images and to determine the accuracy of the considered models for improving a given type of images. Although currently used digital imaging systems usually provide high-quality images, external factors or even system limitations can cause images in many areas of science to be of low quality and resolution. Therefore, threshold values for image processing in a certain field of science are considered. The first step in image processing is image enhancement. The issues of signal image processing remain in the focus of attention of various specialists. Currently, along with the development of information technology, the automatic improvement of images used in any field of science is one of the urgent problems. Images were analyzed as objects: state license plates of cars, faces, sections of the field on satellite images. In this work, we propose to use the models of Super-Resolution Generative Adversarial Network (SRGAN), Extended Super-Resolution Generative Adversarial Networks (ERSGAN). For this, an experiment was conducted, the purpose of which was to retrain the trained ESRGAN model with three different architectures of the convolutional neural network, i.e. VGG19, MobileNet2V, ResNet152V2 to add perceptual loss (by pixels), also add more sharpness to the prediction of the test image, and compare the performance of each retrained model. As a result of the study, the use of convolutional neural networks to improve the image showed high accuracy, that is, on average ESRGAN+MobileNETV2 – 91 %, ESRGAN+VGG19 – 86 %, ESRGAN+ResNet152V2 – 96 %. Робота присвячена методам машинного навчання, орієнтованим на покращення зображень текстурного типу, а саме на поліпшення об'єктів на зображеннях. Метою дослідження є розробка алгоритмів покращення зображень та визначення точності розглянутих моделей для покращення даного типу зображень. Незважаючи на те, що використовувані в даний час системи цифрової обробки зображень зазвичай забезпечують високу якість зображень, зовнішні фактори або навіть системні обмеження можуть привести до того, що зображення в багатьох областях науки матимуть низьку якість та роздільну здатність. Тому розглядаються порогові значення для обробки зображень у певній галузі науки. Першим етапом обробки зображень є покращення зображення. Питання обробки зображень сигналів залишаються у центрі уваги різних фахівців. В даний час, поряд з розвитком інформаційних технологій, одним із актуальних завдань є автоматичне покращення зображень, що використовуються в будь-якій галузі науки. Зображення аналізувалися як об'єкти: державні номерні знаки автомобілів, особи, ділянки поля на супутникових знімках. У даній роботі ми пропонуємо використовувати моделі генеративно-змагальної мережі надроздільної здатності (SRGAN), розширених генеративно-змагальних мереж надроздільної здатності (ERSGAN). Для цього був проведений експеримент, метою якого було перенавчання навченої моделі ESRGAN з трьома різними архітектурами згорткової нейронної мережі, тобто VGG19, MobileNet2V, ResNet152V2 для додавання втрат сприйняття (за пікселями), а також додавання різкості до прогнозування тестового зображення та порівняння продуктивності кожної перенавченої моделі. В результаті дослідження використання згорткових нейронних мереж для покращення зображення показало високу точність, тобто в середньому ESRGAN+MobileNetV2 – 91 %, ESRGAN+VGG19 – 86 %, ESRGAN+ResNet152V2 – 96 %

Modern developments in the fields of natural language processing (NLP) and computer vision (CV) emphasize the increasing importance of generating images from text descriptions. The presented article analyzes and compares two key methods in this area: generative adversarial network with conditional latent semantic analysis (GAN-CLS) and ultra-long transformer network (XLNet). The main components of GAN-CLS, including the generator, discriminator, and text encoder, are discussed in the context of their functional tasks—generating images from text inputs, assessing the realism of generated images, and converting text descriptions into latent spaces, respectively. A detailed comparative analysis of the performance of GAN-CLS and XLNet, the latter of which is widely used in the organic light-emitting diode (OEL) field, is carried out. The purpose of the study is to determine the effectiveness of each method in different scenarios and then provide valuable recommendations for selecting the best method for generating images from text descriptions, taking into account specific tasks and resources. Ultimately, our paper aims to be a valuable research resource by providing scientific guidance for NLP and CV experts.

This article discusses a method for analyzing the layered structure of soil using the phase-metric method of geoelectric monitoring to ensure the reliability of a railway track. The importance of monitoring soil layers for timely detection of changes that may affect the stability and safety of railway tracks is emphasized. The use of geophysical monitoring methods, such as phase monitoring of the geoelectric signals, allows us to optimize measures to strengthen the roadway and increase its durability. The present article describes laboratory experiments in which a specialized setup was created to simulate the process of drilling through various soil layers. Geoelectric methods involving the registration of phase characteristics of the electromagnetic field were used in an experimental setup. The experiments demonstrated the effectiveness of the phase-metric method for determining the characteristics of the layered structure of the soil. The results showed that the change in the phase of the signal recorded at the receiving electrodes can be used to identify different soil layers with different electrical characteristics, such as moisture and density. The method of modeling the physical and geological environment using equivalent circuits of elements in the form of a dielectric made it possible to more accurately analyze the electrical properties of the soil. Based on the obtained data, an automatic monitoring system was developed using recurrent neural networks (RNNs), in particular long short-term memory (LSTM) networks, for automatic detection of bends and transitions in signal time series. Evaluation of the model’s effectiveness showed high accuracy in identifying layers, which contributes to increasing the reliability and efficiency of monitoring the condition of the railway track.

This work presents a study of copper selenite nanocrystals, obtained for the first time by chemical deposition (template synthesis) in a SiO₂/Si track template, and investigates their properties. The obtained nanostructures were subjected to structural, optical, and electrical analysis. After deposition, X-ray diffraction (XRD) analysis confirmed the formation of the orthorhombic phase CuSeO₃. Subsequent annealing in a vacuum at 800 °C and 1000 °C led to successive phase transformations: to the monoclinic phase and, finally, to the triclinic polymorph of copper selenite. Photoluminescence (PL) analysis showed that the intensity and spectral position of the emission peaks vary depending on the crystal structure, which is associated with changes in defects and bandgap width as a result of heat treatment. Current–voltage characteristic (CVC) measurements showed that the phase composition significantly affects electrical conductivity. In particular, the transition to the triclinic phase after annealing at 1000 °C led to noticeable changes in optical and electrical properties compared to the initial material. Thus, a direct relationship has been established between heat treatment conditions, crystal structure, and functional properties of CuSeO₃-based materials, opening up possibilities for their application in photonics and electronics.