Caruna distributes electricity and builds, maintains and repairs an electrical grid for ∼700,000 people. Together with Norrin, Caruna built a computer vision application to help identify damages to their 87,300-kilometer-long electrical network.
From Image Data to Actionable Maintenance with Computer Vision
Reliable electricity supply is paramount to Caruna. As their electrical network spans multiple regions, supervision and maintenance is time-consuming, particularly in rural areas. Caruna already had a system in place to photograph and monitor their electricity distribution components, but manually processing thousands of photographs was laborious. Caruna approached us with the task of creating a computer vision algorithm that could accelerate supervision and maintenance.
To reduce the manual workload on maintenance teams and speed up fault detection, Caruna partnered with us to build a computer vision solution capable of analyzing thousands of images from their electricity network. Working side by side with Caruna’s team, we designed and trained an AI algorithm that detects abnormalities and categorizes components based on their condition. Following a successful pilot, we developed a production-ready application that now flags and alerts for faults in real time, giving maintenance crews a clearer, faster starting point for action.
Since deployment, Caruna has reduced the volume of images requiring manual review by 50%. As the system continues to learn from more data, new use cases and refinements are already being explored with the long-term aim of scaling intelligent supervision across the grid.
Technologies used:
- Custom solution, comprising a computer vision based object detection module and a rule-based anomaly detection module
- Modern web app user interface for ease of access and control, deployed on cloud infrastructure
Could we help you with an AI-based solution? Contact us: myynti@norrin.com or read more about our AI solutions!
