<![CDATA[This article discusses the development and application of machine vision technologies and thermal imaging diagnostics for monitoring the technical condition of traction substation equipment. The focus is on improving the efficiency and reliability of detecting equipment overheating and identifying potential failures by integrating image processing methods with thermal monitoring systems. Previous studies have demonstrated the effectiveness of using thermal imaging for detecting overheating zones in electrical equipment, such as transformers, switchgear, and high-voltage cables. Recent works have also applied machine vision techniques for the automated analysis of temperature distribution and defect detection in substation equipment. However, the integration of these methods for real-time diagnostics and predictive maintenance is still in its early stages. In comparison with previous research, this article presents a novel combined approach that combines thermal imaging data with machine learning models to predict temperature trends and identify early signs of thermal aging in equipment. Unlike prior studies that focused primarily on static analysis of thermal images, this work contributes by proposing a dynamic monitoring system that continuously evaluates the thermal condition of key substation components.]]>
Copyrights © 2025
