Key points are not available for this paper at this time.
Abstract The utility poles of electric power distribution lines are very vulnerable to many natural hazards, while power outages due to pole failures can lead to adverse economic and social consequences. Utility companies, therefore, need to monitor the conditions of poles regularly and predict their future conditions accurately and promptly to operate the distribution system continuously and safely. This article presents a novel pole monitoring method that uses state-of-the-art deep learning and computer vision methods to meet the need. The proposed method automatically captures the current pole inclination angles using an unmanned aerial vehicle. The method calculates the bending moment exerted on the poles due to wind and gravitational forces, as well as cable weight, to compare it with the moment of rupture. The method also includes a machine learning-based model that is built by using a support vector machine to predict the resilience conditions of a pole after a wind event in a faster manner. The three modules of the proposed method are effective tools to classify pole conditions and are expected to enable utility companies to increase the resilience of their systems.
Alam et al. (Sat,) studied this question.