The service performance of reinforced concrete bridges degrades overtime under environmental and vehicle loads. Accurate bridge deterioration analysis can provide a more scientific suggestion for the formulation of road bridge maintenance, strengthening, and reconstruction plans to ensure the operational safety of road bridges. Combined with bridge inspection data from the bridge database in Henan Province, we propose a prognostic model which is based on the Cox regression model for the service performance of newly operated highway girder bridges based on survival analysis theory. The Cox regression model can not only simultaneously analyze the effects of numerous factors on bridge survival, but also handle the presence of censored data in bridge survival data, which does not require the data to meet a specific distribution type. It shows that the decay rate of the deck system, superstructure, and substructure decreases with time in service, which is consistent with the actual decay pattern of the bridge structure. To further verify the accuracy of the model, the authors built a multilayer perceptron neural network with one hidden layer and used the cross-entropy error as the loss function. It showed that the importance of the deck system, superstructure, and substructure to the decay of the bridge structure gradually decreased. The model proposed in this paper is highly applicable and reliable. Theoretically, bridge decay prediction at regional and network-wide levels can be achieved if sufficient comprehensive bridge inspection data can be collected.

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.