Large-Scale Visual Data–Driven Probabilistic Risk Assessment of Utility Poles Regarding the Vulnerability of Power Distribution Infrastructure Systems

Abstract

Inspecting and assessing existing utility poles has become increasingly important for reducing the vulnerability of power distribution infrastructure systems in disaster situations, which can enhance community resilience. Although vision-based systems have been applied to detect faults in power distribution infrastructures, little research currently exists on assessing component- and network-level failures of utility poles based on their geometric and environmental information. This paper aims to propose a new data-driven approach to support risk-informed decision-making for utility maintenance under extreme wind conditions. Large-scale open-source imagery from Google Street View is used to assess geometric properties of utility poles (i.e., leaning angle). Then the failure probability of utility poles is analyzed under varying conditions (e.g., age, leaning angle, and wind loads) in a three-dimensional virtual city model. The proposed method is tested through case studies in Texas to (1) validate an algorithm for estimating leaning angles of utility poles and (2) understand the progress of failures of leaning utility poles from a network perspective. The outcomes of the case studies demonstrate that the proposed method has the potential to leverage large-scale open-source visual data to assess the vulnerability of utility pole networks that may lead to cascading failures in power distribution infrastructure systems. Based on the proposed virtual environment, the method is expected to enable practitioners to facilitate risk-informed decision-making against disaster situations, which creates an opportunity for prioritizing maintenance tasks regarding power distribution infrastructures.