Coming at the 2025 INMR WORLD CONGRESS
Ultraviolet (UV) imaging is a key method to identify corona-related partial discharge activity in high voltage equipment. Nonetheless, despite the benefits offered, UV inspections have traditionally relied on manual interpretation. Fortunately, introduction of AI-assisted detection has eliminated this limitation by automating identification of corona events, including their frequency and spatial location. Combined with a structured evaluation framework based on published industry guidelines, this is now creating a pathway linking raw UV imagery to risk-informed severity assessment.
Introduction
Partial discharge (PD) is one of the earliest indicators of insulation stress in high voltage equipment. Corona discharges are a type of PD when localized electric field stress causes ionization of the surrounding air and often occur along the surfaces of insulators or metal fittings. These discharges can degrade insulation, accelerate ageing, and eventually lead to equipment failure.
UV cameras are uniquely suited to detect corona because they capture the photon emissions produced by these discharges. Unlike infrared (IR) imaging, which reveals heating in components such as conductors and joints, UV inspection highlights electric field phenomena that can precede thermal symptoms. This makes UV a vital tool for preventive maintenance of transmission lines, substations, and switchgear.
However, interpretation of UV inspection results has historically been qualitative. Inspectors often classify corona activity by visual observation, introducing both subjectivity and variability. Without standardized quantification, integrating UV data into predictive and risk-based asset management frameworks has been a challenge.
Plan to attend the 2025 INMR WORLD CONGRESS in Panama, where UV detection expert, Amit Ashkenazi of Ofil Systems will review UV technology in electrical inspections and explore application of AI for event detection. He will then propose how such diagnostic platforms can integrate condition and risk evaluation with the goal of strengthening asset management and grid reliability.
