Posters
Siblings:
ProceedingsProgrammeSpeakersPostersContent PartnersPowering the FutureMarkets TheatreResearch & Innovation in actionStudent programmePresenters dashboardCome meet the poster presenters to ask them questions and discuss their work
We would like to invite you to come and see the posters at our upcoming conference. The posters will showcase a diverse range of research topics, and will give delegates an opportunity to engage with the authors and learn more about their work. Whether you are a seasoned researcher or simply curious about the latest developments in your field, we believe that the posters will offer something of interest to everyone. So please join us at the conference and take advantage of this opportunity to learn and engage with your peers in the academic community. We look forward to seeing you there!
PO013: Intelligent device for structural damage detection combining computer vision and edge computing
Miguel Ángel Rodríguez López, Data Science & Artificial Intelligence Senior Manager , Digital Hub de Acciona S.A.
Abstract
Advancements in Edge Computing and standard hardware devices have paved the way for the development of cost-effective devices with embedded AI, enabling us to detect in real time not only fractures but also structural damages caused by rust or torque losses in bolts. These solutions are particularly crucial in Offshore installations where challenging weather conditions, high humidity, limited accessibility due to the remote location of the equipment, and the need for wind and sea access windows make digitalization solutions indispensable, enabling proactive maintenance and minimizing downtime. At Acciona's Digital Hub, we are developing solutions that combine image recognition algorithms powered and machine learning, being able to effectively identify objects or events that should not be present within an image, including both fatigue fractures or structural damages caused by vibration, excessive loads or the presence of rust. These algorithms are designed to adapt and learn from different situations, ensuring accurate and reliable detection. Regarding torque losses, we also detect, by using computer vision, misalignments within the torque marks done between the bolt and the frame. The versatility of IoT and Edge computing devices allows us to develop solutions with multiple architectures tailored to the specific needs of each application. For instance, we have centralized solutions that utilize a single processing module to receive and process multiple images from critical points of a wind turbine, with direct wireless connections to the processing unit. In other cases, we leverage micro IoT devices equipped with image capture and computing modules, enabling the execution of AI algorithms directly on the device itself. Only the analysis results are transmitted to the wind turbine control PLC. With these cost-effective devices, we can monitor a wide variety of locations into the wind turbine and structural elements for diverse purposes.