TNet: Power Pole Classification with Deep Learning for Automated Inspection in Smart Grids

With advancements in artificial intelligence, the field of power inspection faces challenges in utilizing upgraded AI technologies to improve operational efficiency. As part of the smart grid initiative, each power pole must be accurately modeled. However, manual classification of strain poles and tangent poles remains hindered by three primary limitations: low accuracy, high costs, and poor timeliness. To address these issues, this paper introduces the following contributions: (1) A computer vision model, TNet, is proposed to distinguish strain poles from tangent poles, leveraging a stable T module and ResNet to extract fine-grained features from images. This approach utilizes high-speed computing to enhance timeliness and mitigates high costs by reducing manual labor, with electricity being the only primary operational cost. (2) We introduce a newly collected power pole classification dataset, featuring images of pole heads from 6 and 10[Formula: see text]kV power lines in a specific city. This dataset includes 695 images of tangent poles and 329 images of strain poles, with a total size of 3.52[Formula: see text]GB. Finally, the model can achieve an accuracy of 93.76% and an F1-score of 0.91 on the MyGT2.0 dataset. Our work has been practically applied to the circuit maintenance work of a certain power supply company in 2024.