AI-Driven Condition Assessment of Overhead Power Lines

The AILI project focuses on the development of an AI‑driven image recognition solution designed to automatically identify defective components in overhead power lines.

With the ongoing energy transition, the demands on power grids are increasing significantly—driven in particular by the growing integration of renewable energy sources such as wind and solar power. Expanding and future‑proofing the grid for weather‑dependent operation presents a considerable challenge.

In this context, having accurate and reliable information on the condition of individual grid components—so‑called assets—is indispensable.
To meet these demands, we leverage state‑of‑the‑art artificial intelligence technologies to detect components and faults and to automate standard data‑processing workflows.

In collaboration with a transmission system operator, we have developed an innovative monitoring approach for assessing the condition of overhead power lines.
Through multi‑sensor inspection flights, entire line sections can be inspected in a single pass. By integrating all required sensors and cameras into one system, all inspection data can be captured in just one flight.

Engineers are supported in what was previously a purely manual image and video evaluation process by an intuitive dashboard. This solution consolidates data from multiple sources and formats—such as photos, videos, positional metadata, and laser scans—and highlights identified components, damage, and other anomalies. Experts then assess the severity of the damage, define appropriate measures, and provide the processed information in a customer‑specific format.