A new review article co-authored by Professor Stergios-Aristoteles Mitoulis (University College London, Bartlett School of Sustainable Construction), Francesco Pentassuglia, and Dr.Ivan Izonin, has been published in Results in Engineering (Elsevier).
The article, titled “Bridge damage characterisation using machine learning: methods and advances”, presents a state-of-the-art overview of global bridge damage detection and highlights how machine learning (ML) can transform structural health monitoring through deck deflection analysis.
Key highlights include:
- A comprehensive review of bridge damage characterisation methods worldwide.
- A scalable ML approach that reduces modelling effort and improves explainability.
- A physics-based framework linking deflection patterns to actionable damage states.
This collaborative work showcases how AI and engineering can converge to enhance the resilience and reliability of bridge infrastructure.
Read the article: ScienceDirect link
