Перегляд за автором "Khrustalev, K."
Зараз показано 1 - 2 з 2
Результатів на сторінку
Варіанти сортування
Публікація Automated System Development for the Printed Circuit Boards Optical Inspection Using Machine Learning Methods(ХНУРЕ, 2021) Nevliudov, I.; Botsman, I.; Chala, O.; Khrustalev, K.The problem of printed circuit boards (PCB) quality optical inspection at their production stage is considered. The automated method of PCB optical inspection on the machine learning methods basis is proposed. The necessary neural network parameters to develop an automated PCB inspection method are calculated. The main capabilities of the created artificial neural network for identifying PCB under test defects are analyzed. The results of the conducted neural network testing that confirm its operability and possibility of use for PCB inspection at the stage of production are presented. The software program was developed that is used for transformations over images, such as converting an image to a grayscale color space and image binarization, which speeds up the neural network by reducing the size of the input matrix to a binary value per pixel of the image. The accuracy of finding each of the PCB defects types was also investigated.Публікація System for detection and identification of potentially explosive objects in open area(ХНУРЕ, 2022) Pakhnуts, I.; Khrustalova, S.; Khrustalev, K.The subject of this research is the methods, means and systems for detecting potentially dangerous military objects in open terrain. The purpose of the study is to develop a system for the detection and identification of potentially explosive military objects using an unmanned aerial vehicle (drone), which includes a system for detecting an explosive object using a metal detector with the technology of adjusting the flight height and the detection method using a thermal imager. To achieve the goal, the following tasks were solved: a review and analysis of modern methods and systems for the detection and identification of potentially explosive military objects was carried out, the classification of identifiable explosive objects was determined, system components were selected, a structural diagram and an algorithm of the software control tool were developed system of identification of potentially explosive objects in an open area, a software tool for detection and identification of potentially explosive objects in an open area was created. The following methods are used in the work: the mathematical method of constructing cartographic grids, the method of recording infrared radiation, the method of eddy currents, methods and means of data collection and processing. The following results were obtained: the components of the system were selected, the structure, diagram and algorithm of the software tool for the identification of potentially explosive objects in the open area were developed, and the corresponding software was created. Conclusions: the application of the proposed system makes it possible to increase the accuracy of finding or the absence of a potentially explosive object in a certain area due to the use of two methods of detecting potentially explosive objects at once, and provides the opportunity to identify a sufficiently wide range of objects. The developed system is safe, as it is controlled by an operator who is at a safe distance, allows you to get special maps with terrain markings with information about the possible presence of potentially explosive objects in certain areas of the terrain and, in general, maps of metal detector and thermal imager signals.