Smartphone-Based and Data-Driven Superstructure State Prediction Method for Highway Bridges in Service

Abstract

Survival analysis is a data-driven approach that is widely used in various fields of biomedical prognostic research, and it is highly reliable in the processing of time-event data. This study developed a method for evaluating the service performance of bridge superstructures using the built-in acceleration sensor of smartphones and the prediction of survival analysis theory. It will be used to assist in the daily maintenance and repair of small and medium bridges. The effects of the upper load-bearing structure, upper general structure, bearings, deck paving, expansion joints, and frequency ratio on the deterioration of the bridge superstructure were investigated. The results show that the first-order vibration frequency of the bridge can be effectively detected by the built-in acceleration sensor of the mobile phone, but its low sensitivity and high output noise make it impossible to accurately detect the higher-order frequencies of the bridge. The upper load-bearing members, the upper general structure, the bearing, the deck pavement, and the frequency ratio are all related to the changing trend of the technical condition level of the bridge superstructure.