dc.contributor.author | Laory, I | |
dc.contributor.author | Trinh, TN | |
dc.contributor.author | Smith, Ian F.C, | |
dc.contributor.author | Brownjohn, James | |
dc.date.accessioned | 2016-01-29T15:31:43Z | |
dc.date.issued | 2014-09-22 | |
dc.description.abstract | 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. | en_GB |
dc.identifier.citation | Vol. 80, No. 1, pp. 211-221 | en_GB |
dc.identifier.doi | 10.1016/j.engstruct.2014.09.001 | |
dc.identifier.other | S0141029614005240 | |
dc.identifier.uri | http://hdl.handle.net/10871/19430 | |
dc.language.iso | en | en_GB |
dc.publisher | Elsevier Ltd | en_GB |
dc.relation.url | http://www.sciencedirect.com/science/article/pii/S0141029614005240 | en_GB |
dc.rights.embargoreason | Publisher's policy | en_GB |
dc.rights | © Elsevier Ltd, 2014. This manuscript version is made available under the CC-BY-NC-ND 4.0 license http://creativecommons.org/licenses/by-nc-nd/4.0/ | en_GB |
dc.subject | Artificial neural network | en_GB |
dc.subject | Environmental effect | en_GB |
dc.subject | Random forest | en_GB |
dc.subject | Regression tree | en_GB |
dc.subject | Support vector regression | en_GB |
dc.subject | Suspension bridge | en_GB |
dc.subject | Variable importance | en_GB |
dc.title | Methodologies for predicting natural frequency variation of a suspension bridge | en_GB |
dc.type | Article | en_GB |
dc.identifier.issn | 0141-0296 | |
dc.description | Journal Article | en_GB |
dc.description | This is the accepted version of an article published in Engineering Structures, 80 (1) pp. 211–221. The Version of Record is available online at http://dx.doi.org/10.1016/j.engstruct.2014.09.001. | en_GB |
dc.identifier.journal | Engineering Structures | en_GB |