Using artificial neural networks for GNSS observations analysis and displacement prediction of suspension highway bridge

Abstract

Bridges are playing a major role in the socio-economic development of any country over the world. Suspension highway bridges are one of the most sensitive structures to various external influences and loads. Therefore, the need for structural monitoring system, maintenance, and deformation prediction for these structures is important and vital. One of the main objectives of monitoring the structural deformation is predicting the deformation values, which will help to avoid sudden failure and accidents in the future. Artificial neural networks (ANNs) and adaptive neuro-fuzzy inference systems (ANFIS) have proven successful solution in many engineering applications and problems. This paper investigates an integrated monitoring system using GNSS observations for studying the deformation behavior and displacement prediction for suspension highway bridge, taking into consideration the effect of wind, temperature, humidity and traffic loads during the operational and short-term measurements. Due to the complexity of the mathematical processing of large GNSS monitoring data for obtaining reliable results, adequate model of several alternatives should be chosen. One of the main objectives of this paper is to investigate the optimum predictive model for analysis of GNSS observations and displacement prediction. Several models are applied and compared for prediction of suspension bridge displacement for both kinematic and dynamic models. The resulting predicted displacement values by applying artificial neural networks (ANNs) and ANFIS provide a significant improvement for predicting the structure deformation values for suspension highway bridges from GNSS observations.