Long‐term bridge performance assessment using clustering and Bayesian linear regression for vehicle load and strain mapping model

Abstract

The weigh-in-motion (WIM) system and the structural health monitoring (SHM) system have been used as two separate modules playing different roles in bridge operation and providing different information for bridge maintenance. This study proposes a novel bridge safety condition assessment method that utilizes long-term monitoring data from the WIM system and the SHM system. The method uses the slope of the established vehicle load and vehicle-induced strain mapping model as the evaluation indicator for bridge condition assessment and early warning by clustering and Bayesian linear regression. The proposed method is verified with the continuous monitoring data of a concrete box girder bridge. The results show that the slope indicator of the mapping model changes with the variation of bridge performance, which is stable and can reflect the bridge state in time. The evaluation method can integrate the WIM system with the SHM system and evaluate the bridge health condition based on the correspondence between the two systems, which can make full use of the data.