The modern gas and oil industry faces ongoing challenges in ensuring the reliability and safety of gas and oil pipelines. Gas leaks can pose risks to human life, environmental contamination, and economic losses. This Master's dissertation explores the process of developing and implementing an automated dual-channel system that combines optical and infrared observation with the use of unmanned aerial vehicles (UAV) for the detection of gas leaks. The research encompasses a theoretical analysis of control methods and system parameter determination, equipment selection, the development of software for data processing and analysis, as well as the deployment of the system under real-world conditions. The research findings demonstrate that the developed system effectively detects gas leaks, providing reliable monitoring of gas and oil pipelines. The use of UAVs allows for monitoring in remote and hard-to-reach areas, making the system versatile and suitable for various conditions and industries. This dissertation contributes significantly to the advancement of gas and oil pipeline safety systems and can be applied in the gas transportation industry, environmental organizations, urban monitoring, and other sectors where reliable monitoring is critically important.
Relevance of the topic: Today, in various technical applications in the field of automated non-destructive testing (NDT), the issue of determining the coordinates of defects, various types of material inhomogeneities, etc., which do not meet the quality requirements of the controlled products, is relevant. The use of coordinate information makes it possible to monitor defects, as well as to build B- and C-scans, which contain not only information about defects, but also the coordinates of their location on the surface of the control object (OC). With this approach, according to the obtained data, it is possible to observe the process of the development of defects, and to monitor the appearance of new defects, to conduct additional studies of the detected defects by other NC methods, as well as to perform an assessment of the general condition of the object of control. Solving the issues of NDT automation in many practical tasks requires the use of non-contact methods of registration of coordinate information. Such methods require the use of additional means of information and measurement technology, focused on the use of various physical fields and phenomena - acoustic, optical, etc., and the formation of appropriate information signals that are carriers of coordinate information. In real conditions, such signals are observed against the background of significant noise and interference. Therefore, the study of non-contact methods of coordinate registration of information in systems of automated NDT, which provide reliable and accurate determination of coordinates under conditions of low signal/noise ratio, is an actual direction of development of NDT.
Relevance of the topic. Detecting defects has always been and will always be an urgent task. Untimely and insufficiently reliable defect detection can lead to user dissatisfaction, loss of revenue, increased costs, safety hazards, and impact on the organization's competitiveness. Surface defects in metal products, such as cracks, stains, dents, corrosion, etc., can negatively affect the quality and durability of products. The development and application of advanced segmentation algorithms will allow you to detect potentially dangerous defects in time and take appropriate measures to eliminate them, ensuring the safety and reliability of products. Segmentation of images of surface defects in metal products can be used to automate the production quality control process. An automated defect detection system will reduce dependence on human work and increase the speed and reliability of defect detection, which will positively affect production efficiency and reduce costs. For this purpose, it is promising to use machine learning methods. Purpose: to automate the process of segmentation of images of surface defects of metal products obtained during visual and optical flaw detection using neural network technologies.
To achieve this goal, the following tasks are necessary: 1. Analyze the current state of development of methods for detecting surface defects in metal products and identify the main problems of visual flaw detection. Identify areas for their improvement. 2. Analyze existing methods of image segmentation with image defect recognition. Justify the use of neural networks to improve the quality of defect detection and select the required type of network. 3. Develop algorithmic and software. 4. Conduct testing on real data and obtain quantitative estimates of the system's performance. 5. Analyze the system's performance using different backbones and different mask binarization thresholds.
Object of research: the process of visual and optical flaw detection of metal products. Subject of research: methods of automated detection of metal defects using neural networks.
Scientific novelty: The algorithms for segmentation of images of surface defects of metal products have been improved by using the latest models of neural networks with deep learning, which has increased the reliability of automated defect detection. Practical value: software for automated defect segmentation and software algorithms that automate this process and increase reliability have been developed. Recommendations for the selection of backbones and thresholds for mask binarization have been developed.
The Master's thesis consists of 4 chapters, 97 pages, contains 39 illustrations, 33 tables, 46 sources were processed. Purpose of the work: automation of the process of recognition of cancer, which will increase the accuracy and reliability of diagnostic systems. The object of research is tumor diseases. The subject of research is neural network algorithms for detection and classification of diseases based on ultrasound images.
Tasks of the master's work: 1. To analyze existing diseases and methods of their detection. Analyze treatment algorithms in order to identify the right moment for diagnosis. To scrutinize all existing systems and find ways to improve them.
The master's dissertation consists of 5 sections, 95 pages, contains 23 illustrations, 38 tables, was processed 38 sources. Purpose of the work: automation process of analysis thermographic images using neural network technologies, which will increase the information content and reliability of thermal imaging video surveillance systems.
Tasks of the master's dissertation: 1. Analyze the current state of thermal imaging video surveillance systems and identify areas for their improvement. 2. To get acquainted with the existing methods automated detection and recognition of objects on thermographic images. 3. Justify use of neural networks to improve quality of object detection and select the required type of network.
