Automatic Assessment and Prediction of the Resilience of Utility Poles Using Unmanned Aerial Vehicles and Computer Vision Techniques

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.

Flood Susceptibility Modeling in a Subtropical Humid Low-Relief Alluvial Plain Environment: Application of Novel Ensemble Machine Learning Approach

“…Performance evaluation is the most important step in scientific works (Zhang et al, 2019a). Because no single or a set of universally valid model evaluation measurement matrices related guidelines could be found such as AUROC, TSS, RMSE (Zhou et al, 2018;Alam et al, 2020), and others, we have chosen two types of matrices to evaluate the performance of models used in this study: 1) threshold-independent and 2) threshold-dependent. Under the first category, area under the receiver operating characteristic (AUROC) curve has been used.…”

Novel trends in resilience assessment of a distribution system using synchrophasor application: A literature review

“…The conventional distribution system may have difficulty in handling the changing customer demands and increase in extreme events. So, in the future, a set of practical guidelines to overcome the geographical limitations to track distribution line status using unmanned aerial vehicle is needed 98 . Hence, fault diagnoses can be performed efficiently using synchrophasor data in preevent condition and using UAV for difficult to reach areas.…”

Utility‐pole Detection Based on Interwoven Column Generation from Terrestrial Mobile Laser Scanner Data

“…Converting point clouds into 2D representations was also studied in some papers (El‐Halawany and Lichti, 2013; Alam et al, 2020). Such methods could improve computational efficiency.…”