Розглянуто область застосування, класифікацію, фізико-механічні властивості композитів, проблему використання композиційних матеріалів у сучасному машинобудуванні.

Розглянуто проблеми в галузі проектування та розрахунку на міцність і жорсткість елементів, на яких діють сили і теплові навантаження.

Досліджено кореляцію залежностей параметрів акустичної емісії й амплітуди комбінаційної сумарної гармоніки двох зустрічних ультразвукових хвиль великої амплітуди у монокристалах LiF. Дана кореляція пов'язується з релаксацією структури дефектів у полі ультразвукової хвилі.

Проаналізовано експериментальні результати під час дослідження акустичної емісії (АЕ) в разі динамічного та статичного впливу. Показано, що порогове виникнення АЕ супроводжується тимчасовими або постійними змінами в залежностях характеристик і властивостей функціональних матеріалів (ФМ) від величини даного впливу. Ці зміни можна пояснити прискоренням процесів релаксації та деградації, що супроводжують виникнення АЕ під час перебудови структури у локальних ділянках ФМ.

Індекс рубрикатора НБУВ: В251.630.35

Рубрики:

Коливання < Пластини >

Шифр НБУВ: Ж41115 Пошук видання у каталогах НБУВ 

Індекс рубрикатора НБУВ: Л782.120.9

Рубрики:

Використання відходів і одержання побічних продуктів при одержанні олій

Шифр НБУВ: Ж24320 Пошук видання у каталогах НБУВ 

Шифр НБУВ: Ж24320 Пошук видання у каталогах НБУВ 

This paper considers a model of the neural network for semantically segmenting the images of monitored objects on aerial photographs. Unmanned aerial vehicles monitor objects by analyzing (processing) aerial photographs and video streams. The results of aerial photography are processed by the operator in a manual mode; however, there are objective difficulties associated with the operator's handling a large number of aerial photographs, which is why it is advisable to automate this process. Analysis of the models showed that to perform the task of semantic segmentation of images of monitored objects on aerial photographs, the U-Net model (Germany), which is a convolutional neural network, is most suitable as a basic model. This model has been improved by using a wavelet layer and the optimal values of the model training parameters: speed (step) - 0,001, the number of epochs - 60, the optimization algorithm - Adam. The training was conducted by a set of segmented images acquired from aerial photographs (with a resolution of 6,000 x 4,000 pixels) by the Image Labeler software in the mathematical programming environment MATLAB R2020b (USA). As a result, a new model for semantically segmenting the images of monitored objects on aerial photographs with the proposed name U-NetWavelet was built. The effectiveness of the improved model was investigated using an example of processing 80 aerial photographs. The accuracy, sensitivity, and segmentation error were selected as the main indicators of the model's efficiency. The use of a modified wavelet layer has made it possible to adapt the size of an aerial photograph to the parameters of the input layer of the neural network, to improve the efficiency of image segmentation in aerial photographs; the application of a convolutional neural network has allowed this process to be automatic.

This paper reports a procedure devised to forecast the level of chemical pollution of the atmosphere, which includes a mathematical model for the distribution of the concentration of dangerous gas in the atmosphere at its active deposition by dispersed jets of liquid, as well as a technique for its implementation. Based on the differential equations of gas distribution in space, a phased model of the propagation of a cloud of a dangerous chemical substance was built. The model describes stages in the discharge of a dangerous gaseous substance from emergency technological equipment, the deposition of dangerous gas by a finely-dispersed flow, and free propagation of the cloud in the air. The reported mathematical model makes it possible to calculate the size of pollution zones while determining the boundary safety conditions. When forecasting, the main meteorological parameters, the width of the deposition zone, and the chemical properties of both the gas and liquid are taken into consideration. The comparative analysis of the results of forecasting a conditional zone of chemical damage with the free propagation of the cloud, and at the active deposition by precipitation or technical devices, was carried out. The simulation results revealed that with an increase in the wind speed from 1 m/s to 5 m/s, the size of the affected area increases by 2,7 times, while the concentration of dangerous gas in the cloud falls by 2,5 - 3 times. An algorithm has been proposed for integrating the devised methodology of forecasting the level of chemical pollution of the atmosphere into a general cycle of emergency management. It should be especially noted that the devised procedure contains the entire range of components that are necessary for its practical application. It includes a description of the procedure and practical recommendations for the use of the proposed technique in the elimination of emergencies, as well as a list of probable events when the use of the developed procedure would be most effective.