Automatic Detection of Broken Insulator Service for power line inspections [I-NERGY]
The project SuperPower 2.0 developed thanks to I-NERGY open calls has developed an AI tool for automatic detection of broken insulators using a YOLO architecture.
The end-goal of the developed system is to be able to provide end clients (power line owners) with the best inspection possible of the infrastructure so they can detect defects as early as possible to perform maintenance before the defect becomes a real safety concern. This AI asset is one of the parts of the complete data value chain in the inspection process
of the powerlines.
This tool has been developed by ATLAS company and offers the opportunity to automatically detects the defects in the RGB images captured during the inspection process of a powerline, speeding and improving the defect detection process.
The service aims to automatically detect the broken insulator on a power line tower image. The service follows this process:
-The client captures the visual data in .jpg format using drones.
-The client transfers the data from the drones to a computer where the data is uploaded into the cloud and sent to our team.
-Our team receives the data, and stores it in an input folder. After that, the team process the data and prepare it for running the algorithms developed in the project to obtain the images with defect in an output folder.
-The output data is sent back to the client using the demanded service.
After the complete process, the client will have the images with defects and where is the defect placed, so the company can apply the maintenance actions required for the detected defect.
With this service, ATLAS aims to provide automatic broken insulators detection to companies that inspect power lines. This technology enables to speedup the process with an automatic detection of failures using AI.
This project has received funding from the European Union's Horizon 2020 research and innovation programme within the framework of the I-NERGY Project, funded under grant agreement No 101016508