Search
Close this search box.
Search
Close this search box.

Enedis: Drone‑image AI inspection for 20 kV overhead lines

4 June 2026
    AI analyses drone photos of 20 kV poles to detect anomalies and speed up repair / replacement decisions

    Context

    Medium‑voltage (MV) overhead networks require regular inspection and maintenance at scale.
    The scale of the network and the need to inspect overhead lines efficiently create constraints on the speed and cost of inspection when relying on previous helicopter-based methods.

    Challenge

    Enedis with 310,000 km of 20 kV overhead lines (around 47% of the MV network), maintaining overhead infrastructure is a major operational challenge, particularly for segments expected to stay in service long term.
    Efficient inspection is crucial to identify defects early and support consistent, standardised O&M decisions. The practical challenge is to process large volumes of pole-condition information and accelerate decisions on what should be repaired or replaced.

    AI Solution

    DORA is a platform that collects photos of 20 kV poles taken by drones, classifies the photos by pole, and applies AI to analyse the images for anomalies. The outputs are used to speed up the selection process and support replacement decisions for MV overhead assets.

    Impact & evidence

    The solution inspects up to 20 km of network per day at roughly half the cost of previous helicopter-based methods. Target outcomes and usage figures include 8,000 km of lines inspected per year, Progressive national rollout across 25 Regional Directions (2021–2024) with c.250 daily users.

    Implementation / Adoption

    Replication requires a sufficiently large overhead MV network and permissive drone regulation.
    Prerequisites include the ability to run large-scale drone photo campaigns, a rich and up-to-date information system, prior harmonisation of renewal practices over 18 months, a dataset of more than 30,000 labelled photos to train the AI model, and internal or partner expertise in computer vision and Machine Learning (ML).

    Data

    Operational data inputs include high-definition photos of poles from drones, helicopters, and ground operators; grid cartography; incident history data; and structure ageing data. Data preparation and collection needs include labelling of 30,000 photos and new data collection through drone inspection campaigns.
    It’s an customised vendor solution Enedis co-built with Alteia.

    Future enhancements

    Extension to additional anomaly types; integration with autonomous drones; development of CartoLine HTA for MV aerial network.

    Additional information

    https://www.edsoforsmartgrids.eu/success_cases/dora

    [L’instant tech] Comment Enedis scrute ses lignes électriques avec des drones et l’IA de la pépite Alteia

    Pour renforcer les lignes haute-tension face aux aléas climatiques, Enedis utilise des drones et l’IA – ICI

    Inspection de réseaux et d’éoliennes automatisée par drone – Escadrone

    Related news

    Connecting and accelerating e-mobility across Europe.
    More than a tool: Utilities and tech firms leading the charge in unlocking the potential of AI.
    Community of leading companies powering Europe's energy transition. Add how many companies are BAs, make it visible.
    Accelerating power system decarbonisation by moving towards 24/7 carbon free energy matching.
    Europe's electricity production, demand, prices, capacity, CO2 emissions, and cross-border flows.
    An annual report that provides a comprehensive analysis of the electricity and energy market trends in Europe.