Methodologies for predicting natural frequency variation of a suspension bridge

• Published in: Engineering structures 2014-12, Vol.80, p.211-221
• Main Authors: Laory, Irwanda, Trinh, Thanh N., Smith, Ian F.C., Brownjohn, James M.W.
• Format: Article
• Language: English
• Subjects: Applied sciences; Artificial neural network; Bridges; Buildings. Public works; Environmental effect; Exact sciences and technology; Random forest; Regression tree; Stresses. Safety; Structural analysis. Stresses; Support vector regression; Suspension bridge; Suspension bridges. Stayed girder bridges. Bascule bridges. Swing bridges; Variable importance
• ISSN: 0141-0296; 1873-7323
• DOI: 10.1016/j.engstruct.2014.09.001

•We compare five regression methods to predict natural frequencies of a bridge.•Random forest and support vector regression are the most appropriate methods.•The relative importance of variables is useful to evaluate environmental effects.•Traffic loading and temperature are the most influential parameters.•Obtaining these parameters should be a priority. In vibration-based structural health monitoring, changes in the natural frequency of a structure are used to identify changes in the structural conditions due to damage and deterioration. However, natural frequency values also vary with changes in environmental factors such as temperature and wind. Therefore, it is important to differentiate between the effects due to environmental variations and those resulting from structural damage. In this paper, this task is accomplished by predicting the natural frequency of a structure using measurements of environmental conditions. Five methodologies – multiple linear regression, artificial neural networks, support vector regression, regression tree and random forest – are implemented to predict the natural frequencies of the Tamar Suspension Bridge (UK) using measurements taken from 3 years of continuous monitoring. The effects of environmental factors and traffic loading on natural frequencies are also evaluated by measuring the relative importance of input variables in regression analysis. Results show that support vector regression and random forest are the most suitable methods for predicting variations in natural frequencies. In addition, traffic loading and temperature are found to be two important parameters that need to be measured. Results show potential for application to continuously monitored structures that have complex relationships between natural frequencies and parameters such as loading and environmental factors.