Outdoor high voltage insulators play a crucial role in ensuring the reliable and efficient operation of electrical power systems. Over time, these insulators can degrade due to various environmental and operational factors, leading to po- tential electrical failures and safety hazards. This research abstract highlighted the recent advancements in AI-based techniques employed in condition monitoring of outdoor high voltage insulators. The abstract provided an overview of the key challenges associated with traditional condition monitoring approaches and the potential of AI techniques in overcoming these limitations. It discussed various AI methods, including machine learning, deep learning, and data analytics, that had been explored for high voltage insulator condition monitoring. The focus was on developing accurate and efficient methods to detect and diagnose insulation defects, such as pollution, ageing, surface degrada- tion, and mechanical stress. Also, the comparative analysis of insulators&rsquo physical, chemical, and electrical properties under the influence of ageing was reported. The primary objective of this report was to employ a machine-learning approach for the classification of partial discharge, an electrical property of the insulator. Additionally, this study pre-sented the utilization of deep learning-based object detection methods for condition monitoring of transmission line insulators. Finally, a hydrophobicity classification study was conducted to investigate the physical property of polymeric insulators by utilizing vision transformers.
In summary, the research emphasized on the significance of AI-based approaches in addressing the limitations of traditional monitoring methods and highlights the potential benefits for the electrical power industry in terms of reliability, safety, and cost-efficiency. This report would be helpful to implement in future research for applying the HV overhead line insulator