PSI - Issue 64

Francesco Pentassuglia et al. / Procedia Structural Integrity 64 (2024) 254–261 F. Pentassuglia et al./ Structural Integrity Procedia 00 (2019) 000 – 000

259

6

Fig.1 Framework of the proposed methodology

3. Conclusions The paper emphasises the importance of enhancing existing methodologies for detecting the damage state of bridges, particularly through the utilisation of ML techniques. By focusing on bridge deck deflections and incorporating advanced technologies like Finite Element (FE) model updating, researchers aim to improve the reliability and effectiveness of bridge damage identification across various bridge types and scenarios. The validation and expansion of the ML k-NN (k-Nearest Neighbor) methodology represent crucial steps in ensuring that the approach is not only applicable but also robust for asset decision-makers in the field of bridge engineering. This validation process serves to confirm the methodology's effectiveness and reliability in accurately identifying and assessing damage states in concrete bridges.