<![CDATA[High Voltage Overhead Transmission Lines require routine inspections to detect potential fault and ensure reliable operation. These inspections are conducted through manual tower climbing, known as Climb Up Inspection (CUI). With the advancement of technology, drones—Unmanned Aerial Vehicles (UAVs)—have increasingly been adopted as a more efficient alternative for conducting such inspections. While drone-based inspections significantly improve the speed of data acquisition, they often create a bottleneck at the stage of data analysis and image processing due to limited human resources and concurrent operational tasks. To address this issue, this study presents the development of an Artificial Intelligence (AI) based software application utilizing Deep Learning, specifically the Convolutional Neural Network (CNN) algorithm, to automate the classification of insulator conditions captured by drone imagery. The proposed application is designed to categorize insulators into two conditions: broken and normal. By automating the analysis process, this system is expected to enhance inspection efficiency, reduce maintenance response time, and support the creation of a more reliable and resilient power transmission network.]]>
Copyrights © 2026
