Machine learning (ML) based predictive maintenance policy for bridges crossing waterways

Scour is one of the major causes for bridge failures. This study established a machine learning based predictive maintenance policy for scour risk mitigation. Data used in this study was provided the French National Railway Company (SNCF). After comparing three commonly used ML algorithms, it is found that the extreme gradient boosting (XGBoost) algorithm outperforms others and achieves very encouraging results. Moreover, the trained classifier was then tested in another 40 bridge piers and the results were compared with a junior engineer's evaluation. Results show that XGBoost classifier had a slightly better performance in terms of accuracy and precision. The proposed methodology in this paper allows engineers to determine scour risk of bridge piers in an accurate yet rapid way.