In the master's thesis, a magnetic inspection system for detecting defects in the side frames of freight car bogies was developed and investigated.
Relevance of the topic:
The relevance of the topic of the master's thesis is to solve the important problem of improving the safety of railway transport by developing a modern automated method of non-destructive testing. The side frames of freight car bogies are critical structural elements that are subjected to intense cyclic loads. This significantly increases the risk of defects such as cracks and pores, which can cause serious accidents and jeopardize transportation safety.

Hits: 330

The master's thesis is devoted to the development of an automated weight control system for railway cargo handling. The primary focus is on developing software to enhance the productivity of cargo transshipment points.
The aim of this master's thesis is to improve the efficiency of transshipment points through the development of software and the use of modern engineering solutions and accessible technologies.  
The object of the study is the processes of automating weight control on railway scales.  
The subject of the study includes the methods, algorithms, and technologies that implement automated weight control systems.  

Hits: 996

The Master's thesis consists of an introduction, seven chapters, conclusions, and a list of references. It also contains 182 pages, including 65 figures, 32 tables, and 125 sources.
The aim of the Master's thesis is to improve the productivity, reliability, and rhythm of the technological process for sorting fruits of vegetable crops by developing an intelligent automated sorting system. To achieve this goal, methods of machine learning, computer vision, and deep learning algorithms were employed. The results of the work demonstrated a high classification accuracy of the fruits, which allows for the effective use of the system in real production environments.

Hits: 330

The thesis explores and implements an automated real-time object recognition system based on the NVIDIA Jetson Nano platform.
     The purpose of this study is to develop a high-performance and energy-efficient object recognition system that meets real-time requirements while operating under limited hardware resources.
     The research analyzes modern methods and algorithms of computer vision, including YOLOv8, Faster R-CNN, and SSD. A review and comparison of hardware platforms such as Raspberry Pi, Jetson Nano, and Google Coral have been conducted. Data augmentation was applied for model training, and the neural network was optimized using ONNX and TensorRT. A software suite was developed for object recognition, achieving high accuracy (mAP 95%) and a processing speed of 15 frames per second.

Hits: 317

Relevance of the topic
The topic of this master's thesis concerns the development of an automated lighting system for a cottage, which is relevant given the need for energy efficiency, comfort and safety of modern housing. Optimizing lighting is important for improving the quality of life, rationalizing energy use, and creating an attractive environment in residential areas. Traditional lighting control methods are limited due to low efficiency, the need for manual control, or the lack of adaptation to changing environmental conditions. In this regard, the introduction of intelligent lighting systems using modern sensors and microcontrollers is becoming an important task.
The development of digital technologies opens up new opportunities for creating more affordable, efficient and innovative lighting solutions. As part of this work, we developed two automated lighting systems for the cottage: one for the bathroom and one for the living room. These systems are based on the use of Arduino, presence sensors, light levels, and other components to automate lighting processes, providing comfort and convenience to users.

Hits: 310

  1. Panasko D. Automated fabric moisture control system
  2. Hryshyn D. Improvement of the measuring system
  3. Zemliakov O. Automation of the cartographic image segmentation process
  4. Pitukh I. Web application for visualization of ultrasonic flow detector data

Page 5 of 29

АСНК КПІ ім. Ігоря Сікорського, 2021