The commissioning of energy projects is a complex task and requires careful monitoring of all project assets. As part of its processes and services in the construction of photovoltaic plants, Gonvarri Solar Steel raises the possibility of designing and implementing a new system for monitoring the degree of progress of the works and quality control.
The approach initially includes photovoltaic plants with a solar tracking system (tracker) of different models in its portfolio. In the future, it is proposed to extend the solution to fixed structure systems.
It seeks to follow a strategy based on the As-Planned vs. As-Built methodology, measuring effectively, objectively and repeatably the activities that make up the data that represents the degree of progress of the installation.
Tracking procedural and automatic work
Merging CAD plans (as-planned) and drone image (as-built)
Generating reports and dashboards for monitoring
A system based on Artificial Intelligence is proposed, specifically, applying Artificial Vision and Deep Learning algorithms for the detection, location and classification of elements in images.
As input data sources, on the one hand, we have the CAD plan of the plant, which collects each of the regions and trackers that compose them in a georeferenced way. On the other hand, the images collected by a drone at the plant are reconstructed in a single GEOTIFF map, corresponding to a large size and resolution image, also georeferenced.
The Artificial Vision pipeline (processing flow) begins by pre-processing the images by areas. Subsequently, thanks to the recognition models based on neural networks and trained ad-hoc, each component present in the image is segmented, finally identified, classified according to its type.
Subsequently, the combined analysis of the components foreseen according to the plan and those actually visible in the images is carried out. Its presence and position intersect between both origins thanks to the GPS coordinates.
Lastly, the data is available for uploading to a dashboard designed by Gonvarri Solar Steel's engineering team, so that its display is representative and navigable according to monitoring requirements.
The system developed by Izertis is capable of counting and locating all the elements that make up each solar tracker, regardless of the degree of progress in its installation.
Starting from a simple flight with a commercial drone equipped with a high-resolution camera, images of the current moment of the plant are supplied, which are processed automatically by the system based on Artificial Intelligence.
With this, the location of the element and its presence are compared, calculating, based on its percentage weight, the degree of total progress of the work in an objective, repeatable way and without room for interpretation by any of the parties involved.