Description du projet
Des drones pour inspecter les éoliennes
Les véhicules aériens sans pilote (UAV) commencent à jouer un rôle dans l’inspection des pales d’éoliennes. Or ces méthodes d’inspection par drones pourraient s’avérer plus flexibles et plus rentables que celles réalisées manuellement. Le projet Windrone Zenith, financé par l’UE, travaille sur une solution qui permettra de contrôler trois pales en un seul vol. Sa technologie consiste en un matériel d’inspection de haute précision couplé à un logiciel intelligent. Des algorithmes d’apprentissage automatique seront utilisés pour améliorer en permanence la détection des défauts à partir d’une base de données exponentielle constituée des images et de leur analyse. Une plateforme spéciale de réalisation de rapports dans le cloud mettra à la disposition des clients des documents exploitables.
Objectif
"Over the lifetime of a wind turbine, operation and maintenance costs represent 25% of total levelised cost per kWh produced. The majority of these costs are attributed to the wind turbine’s blades, yet current methods of inspecting these blades are outdated and inefficient.
Blade inspection procedures still largely relies on qualified inspectors roping down each blade to manually inspect for any flaws or defects present on the blade. This is clearly a very hazardous, time-consuming (5 hours), and expensive method (€1500).
Other less used methods of blade inspection include capturing blade images from ground cameras and manual review by
experts. However, poor image quality and strong backlight leaves many blade flaws undetected.
Unmanned Aerial Vehicles (UAVs) are now being used to take pictures of the blades from much closer up. Current UAV's however require dedicated experts for both flight control as well as image processing, analysis, and fault detection.
Pro-Drone's integrated WindDrone Zenith’s solution is a breakthrough solution providing enabling 3-blade inspection in a single flight. Our technology solution is fully equipped with highly accurate inspection equipment hardware coupled with smart software. The software allows the UAV to be fly autonomously, avoid collisions, automatically detect any faults, and generate reports for the customer on each wind turbine inspected. Machine learning algorithms are used to continuously improve automated fault detection based on a growing database of captured images and their analysis. Our ""BladeInsight"" cloud reporting platform makes actionable reports available to our customers as part of this solution. Pro-Drone Zenith provides for a 50% direct cost saving, and decreases turbine inspection downtime by 6X, as compared to existing methods."
Champ scientifique
- natural sciencescomputer and information sciencessoftware
- engineering and technologyelectrical engineering, electronic engineering, information engineeringelectronic engineeringsensorsoptical sensors
- engineering and technologyenvironmental engineeringenergy and fuelsrenewable energywind power
- engineering and technologyelectrical engineering, electronic engineering, information engineeringelectronic engineeringroboticsautonomous robotsdrones
- natural sciencescomputer and information sciencesartificial intelligencemachine learning
Programme(s)
Régime de financement
SME-2 - SME instrument phase 2Coordinateur
2740-122 PORTO SALVO
Portugal
L’entreprise s’est définie comme une PME (petite et moyenne entreprise) au moment de la signature de la convention de subvention.