Energinet leverages AI to cut inspection time and predict maintenance needs
The opportunity
High-voltage transmission towers are installed in a wide range of locations and environments and are exposed to all possible weather conditions. Due to this, transmission towers are prone to corrosion and can degrade over time. Energinet needed a solution to effectively spot and quantify the type and level of rust on its transmission towers and to be able to detect changes over time.
We needed a solution to help streamline our rust inspections and at the same time improve the end-to-end maintenance process. Working with eSmart Systems gives us access to world class AI and inspection management tools, and the ability to participate in the design of this all-new module is an exciting step on our innovation and digitalization journey.
The solution
In order to match Energinet’s specific needs, customized AI models were developed and trained. Thirty-six annotated pictures were initially made available by Energinet to train the models. The dataset was further enhanced by augmented data techniques and the use of synthetic images from our simulator. The resulting training dataset consisted of 285,025 examples of rust. Our customized model was able to detect rust with high accuracy, quantify the amount of rust on the pictures and easily visualize it for Energinet’s experts.
Benefits of Grid Vision® for Energinet
Identified rust occurrences in a large dataset of images with 96% accuracy in minutes, outperforming manual methods (80% accuracy).
Captured and transferred SME knowledge from human to machine using annotated images and map visualizations to reveal correlations with environmental factors.
Significantly reduced time spent reviewing inspection data while improving detection accuracy, helping cut costs and speed up inspections.
Enabled predictive maintenance through a custom solution that uses inspection results to extend the life of individual towers.
Start your journey with us today!