Analyzing GNSS Measurements to Detect and Predict Bridge Movements Using the Kalman Filter (KF) and Neural Network (NN) Techniques

In this study, we present a data processing framework to apply measurements of the Global Navigation Satellite System (GNSS) technique for analyzing and predicting movements civil structures such as bridges. The proposed approach reduces noise level GNSS using Kalman Filter (KF) enables estimation static, semi-static, dynamic components bridge’s series analyses temporal filtering Least Squares Harmonic Estimation (LS-HE). numerical results indicate that by RTK-GNSS system semi-static component is extracted with Standard Deviation (STD) 0.032, 0.048, 0.06 m in North, East, Up (NEU) directions, while 0.004, 0.003, 0.01 m, respectively. Comparing dominant frequencies bridge from LS-HE those permanent stations provides information about stability. To predict its deflection, Neural Network (NN) tested simulate time-varying components, which are then compared safety limits, known design, assess structural health under usual load.