Seminal
The magazine and atlas of EU-funded researchA new publication from the web and AI team at Scott Charnley

Atlas / United Kingdom

Marie Skłodowska-Curie Action · Running

AIESHM Artificial Intelligence Enhanced Structural Health Monitoring for Evaluation of Time-dependent Structural Performance of Ageing Railway Bridges

Coordinator
University of Southampton, United Kingdom
Runs
1 August 2025 to 31 July 2027
Status
Running
EU funding
€276k
Total cost
—
Partners
1 organisations in 1 countries
Type
Marie Skłodowska-Curie Action
Grant agreement
101203887

What the project is doing

In the project's own words, from its summary on CORDIS.

The aim of the present proposal is to develop an innovative Artificial Intelligence Enhanced Structural Health Monitoring (AIESHM) for evaluation of time-dependent structural performance of ageing railway bridges. This includes a sustainability and resilient-based asset management framework, which leads to significantly reducing the CO2 emission. The proposed AIESHM system, is used to identify the damages in order to prevent the failure or temporary closure, which could lead to loss of lives and additional costs namely construction of new bridge, slow down transportation rate and heavy traffic.

This monitoring system will be (a) cost-effective, timely and accurate, (b) detectable for various types of damages, (c) reducing the CO2 emission (d) implemented to a new sustainability and resilient-based asset management framework. The combination of updating finite element model (FEM), which involves calibrating the FEM parameters using the measured responses of a bridge, data extraction of sensors and visual inspection integrated with machine learning (ML) will help us to get different damages in the best time.

Then they are implemented in a new asset management framework which helps to select the best repair/maintenance strategy by an improved decision making process so that the green house gas emission reduces. The FEM updating technique employs optimization algorithms to minimize the difference between the predicted and measured responses, resulting to enhance the accuracy of SHM. By training ML algorithms on data, this model can capture the complex behavior of bridges and identify damage states.

Furthermore, the new approach will be capable to predict the time-dependent residual capacity under railway and seismic loading in order to make the best decision to use or repair the bridge.

Topics

Who is involved

OrganisationCityCountryRole
University of SouthamptonSouthamptonUnited KingdomCoordinator

Source: CORDIS, European Commission. Data of 5 Nov 2026, reused under the Commission's reuse policy. View on CORDIS · Grant DOI