Plataforma digital de avaliação da condição para pontes ferroviárias resilientes e sustentáveis

Digi4RailBridges is aligned with key strategic orientations for R&D at international level. Important Challenges (C) are addressed: C1 Lead the development of key emerging technologies, with autonomous DTs that integrate IoT systems and AI methods for the management of railway bridges, increasing adaptability and resilience. C2 Promote a climate-neutral and sustainable economy. The project accelerates green transition by providing real-time data for proactive maintenance, improving resource use and enhancing sustainability in transportation sector. C3 Extent service life of civil infrastructures, reducing the need for replacement and CO2 footprint. The project implements predictive models integrated in a DT of railway bridges towards optimal inspection and extending service life. C4 Faster and more accurate maintenance needs in existing bridges using AI methods for early damage identification. C5 Promote costs savings in maintenance operations. The project promotes the transition to predictive-based maintenance of railway bridges, improving maintenance schedules and avoiding traffic disruptions due to unexpected maintenance operations. Digi4RailBridges goes beyond the state-of-the-art on 4 fundamental Ambitions (A) of innovation: A1 Enhance remote inspection & wireless monitoring. Promotes transition from wired monitoring systems to fully remote inspection & monitoring of railway bridges. The main advantages are rapid, cost-effective and safer handling under demanding conditions. A2 Efficient early damage identification using AI. The project proposes a holistic strategy that fuses damage-sensitive features from sensor data and computer-vision. This is a step forward for more reliable and informed bridge management systems. A3 Enhance the implementation of DT for informed maintenance decisions. Current DTs for railway bridges are still not fully consolidated. The project enhances sensor integration, real-time data synchronization and AI algorithms for predictive analysis. A4 Demonstration of the solution on a railway bridge, leading to high-impact research that addresses the challenges in operation environment. In this context, the following specific objectives (O) are set: O1 Deploy a distributed and non-intrusive wireless system to collect and transfer data from the bridge to the cloud. O2 Stablish a procedure for remote inspection & reality capture of railway bridges using UAVs mounted with cameras and LiDAR. O3 Develop machine learning strategies based on time-series from structural monitoring for automatic early damage identification. O4 Develop computer-vision strategies based on images from remote inspections for automatic classification of multiple anomalies. O5 Perform data augmentation using advanced FE modelling & simulation. O6 Develop an architecture of the DT for railway bridges capable of interacting with the technologies and methodologies implemented O7 Develop a method to merge features extracted from time-series and images and adopt a condition rating to efficiently evaluate the anomalies severity. O8 Develop a tool for predicting the Remaining Useful Life of the bridge O9 Implement and validate the proposed digital framework in a railway bridge. Interdisciplinarity is achieved within the project through cutting-edge knowledge brought together by a team including civil, electronic and computer engineers to cover different domains: data analytics (30%), sensoring & robotics (30%), digitalization (25%), simulation (15%).