Periodic Reporting for period 1 - BRIDGITISE (Industrial Doctoral Network on Bridge Digitalised Integrity Management)
Reporting period: 2024-01-01 to 2025-12-31
Many European bridges built in the mid‑20th century are now ageing, exposed to growing traffic, environmental pressures and the effects of climate change. At the same time, the bridge sector remains only partially digitalised, relying heavily on manual inspections and fragmented information. This situation limits timely decision‑making and leads to higher costs, reduced reliability and avoidable environmental impacts. Digital technologies—such as sensors, drones, satellite measurements, cloud platforms and artificial intelligence—offer major opportunities to improve accuracy, efficiency and sustainability across the whole lifecycle of bridges, yet their uptake in the sector remains slow.
BRIDGITISE addresses this challenge by establishing the first European Industrial Doctorate devoted to the digital transformation of bridge integrity management. The project brings together academic institutions, technology providers and infrastructure operators to train a new generation of specialists capable of merging engineering knowledge with advanced digital skills. Its core objective is to develop and validate innovative methods to collect, process and model bridge information in a cost‑effective and sustainable way.
The project focuses on three research goals: improving data collection using emerging technologies; creating secure and efficient tools to process and share large volumes of information; and developing digital models to support better maintenance and investment decisions. These solutions will be tested using real‑world bridge data. BRIDGITISE also promotes open science, inclusiveness and responsible innovation, ensuring that digitalisation benefits society widely.
By enabling earlier detection of deterioration, reducing disruptions, extending service life and lowering emissions, the project is expected to strengthen the resilience, safety and sustainability of Europe’s transport infrastructure while helping to close the digital skills gap in the construction sector.
BRIDGITISE addresses this challenge by establishing the first European Industrial Doctorate devoted to the digital transformation of bridge integrity management. The project brings together academic institutions, technology providers and infrastructure operators to train a new generation of specialists capable of merging engineering knowledge with advanced digital skills. Its core objective is to develop and validate innovative methods to collect, process and model bridge information in a cost‑effective and sustainable way.
The project focuses on three research goals: improving data collection using emerging technologies; creating secure and efficient tools to process and share large volumes of information; and developing digital models to support better maintenance and investment decisions. These solutions will be tested using real‑world bridge data. BRIDGITISE also promotes open science, inclusiveness and responsible innovation, ensuring that digitalisation benefits society widely.
By enabling earlier detection of deterioration, reducing disruptions, extending service life and lowering emissions, the project is expected to strengthen the resilience, safety and sustainability of Europe’s transport infrastructure while helping to close the digital skills gap in the construction sector.
1. Overview
During the first reporting period, BRIDGITISE advanced its objectives in sensing, data processing and digital decision‑support for bridge infrastructure. Activities included theoretical work, simulations, algorithm development, laboratory testing, UAV and robotic workflows, satellite monitoring and early field validation. Overall, the project achieved clear progress toward a fully digital bridge information chain.
2. Advances in Bridge Data Collection (RO1)
The project developed new methods to capture accurate and cost‑effective bridge information:
• Crowdsensing: A complete framework for smartphone‑based vibration monitoring, supported by simulations and sensitivity studies.
• Satellite monitoring: A modelling‑assisted approach for InSAR interpretation, with synthetic damage scenarios and automated Sentinel‑1 data processing.
• UAV inspection: An energy‑aware inspection framework combining semantic communication, trajectory optimisation and connectivity management.
• Edge sensing: Lightweight devices performing on‑board feature extraction and anomaly detection, validated in the lab.
• Robotic inspection: Low‑precision, resource‑efficient segmentation models for autonomous visual inspection.
3. Advances in Processing and Sharing Bridge Information (RO2)
Progress focused on converting raw sensor data into interoperable digital information:
• A web platform linking real‑time SHM data with IFC‑based bridge models.
• An adaptive data‑cleaning pipeline for anomaly detection, environmental compensation and ML‑ready preprocessing.
• A conceptual framework for automated visual defect detection based on a review of datasets and computer‑vision methods.
4. Advances in Modelling and Decision Support (RO3)
New methodologies were developed to support predictive maintenance and long‑term resilience:
• Circularity principles analysed and operationalised through regional indicators and a GIS‑based reuse assessment.
• A Bayesian corrosion‑prediction framework extended with reliability‑based deterioration models.
• A system‑level reliability method for climate‑related hazards incorporating climate uncertainties.
• A digital interface linking SHM, BIM and decision scenarios, with emphasis on fatigue‑related deterioration.
During the first reporting period, BRIDGITISE advanced its objectives in sensing, data processing and digital decision‑support for bridge infrastructure. Activities included theoretical work, simulations, algorithm development, laboratory testing, UAV and robotic workflows, satellite monitoring and early field validation. Overall, the project achieved clear progress toward a fully digital bridge information chain.
2. Advances in Bridge Data Collection (RO1)
The project developed new methods to capture accurate and cost‑effective bridge information:
• Crowdsensing: A complete framework for smartphone‑based vibration monitoring, supported by simulations and sensitivity studies.
• Satellite monitoring: A modelling‑assisted approach for InSAR interpretation, with synthetic damage scenarios and automated Sentinel‑1 data processing.
• UAV inspection: An energy‑aware inspection framework combining semantic communication, trajectory optimisation and connectivity management.
• Edge sensing: Lightweight devices performing on‑board feature extraction and anomaly detection, validated in the lab.
• Robotic inspection: Low‑precision, resource‑efficient segmentation models for autonomous visual inspection.
3. Advances in Processing and Sharing Bridge Information (RO2)
Progress focused on converting raw sensor data into interoperable digital information:
• A web platform linking real‑time SHM data with IFC‑based bridge models.
• An adaptive data‑cleaning pipeline for anomaly detection, environmental compensation and ML‑ready preprocessing.
• A conceptual framework for automated visual defect detection based on a review of datasets and computer‑vision methods.
4. Advances in Modelling and Decision Support (RO3)
New methodologies were developed to support predictive maintenance and long‑term resilience:
• Circularity principles analysed and operationalised through regional indicators and a GIS‑based reuse assessment.
• A Bayesian corrosion‑prediction framework extended with reliability‑based deterioration models.
• A system‑level reliability method for climate‑related hazards incorporating climate uncertainties.
• A digital interface linking SHM, BIM and decision scenarios, with emphasis on fatigue‑related deterioration.
Results
The project delivered advances across sensing, data processing and digital modelling. New solutions for data collection (crowdsensing, UAV and robotic inspection, satellite monitoring and edge devices—were developed and tested. Automated pipelines for cleaning, analysing and integrating SHM data with BIM were implemented. Predictive models for corrosion, fatigue, climate hazards and circularity were validated through simulations, lab tests and early field data.
Potential Impacts
The results advance research in SHM, AI‑based inspection and digital twins, while offering industry more efficient, lower‑cost monitoring and better decision support. Societal benefits include earlier detection of deterioration, improved safety and resilience, longer service life and reduced environmental impact.
Key Needs for Further Uptake
Next steps require large‑scale field demonstrations, broader data access, clear paths for IPR and commercialisation, alignment with European standards and continued international collaboration.
The project delivered advances across sensing, data processing and digital modelling. New solutions for data collection (crowdsensing, UAV and robotic inspection, satellite monitoring and edge devices—were developed and tested. Automated pipelines for cleaning, analysing and integrating SHM data with BIM were implemented. Predictive models for corrosion, fatigue, climate hazards and circularity were validated through simulations, lab tests and early field data.
Potential Impacts
The results advance research in SHM, AI‑based inspection and digital twins, while offering industry more efficient, lower‑cost monitoring and better decision support. Societal benefits include earlier detection of deterioration, improved safety and resilience, longer service life and reduced environmental impact.
Key Needs for Further Uptake
Next steps require large‑scale field demonstrations, broader data access, clear paths for IPR and commercialisation, alignment with European standards and continued international collaboration.