Integrating multivariate techniques in bridge management systems


Hanley, Ciarán; Matos, José C.; Kelliher, Denis; Pakrashi, Vikram

Bridge management systems; Principal component analysis; multivariate analysis; condition ratings

The use of bridge management systems (BMS) by infrastructure stakeholders has led to the collectionand retention of large quantities of data concerning the condition states of bridges throughout nationaland regional networks. The database for the BMS is often populated by the results of routine visualinspections, based on a prescribed scale for defining the condition state of the bridge’s individualelements, and of the bridge structure as a whole. The populating of the database also leads tothe storage of large quantities of so-called metadata; which can describe the physical parametersof the bridge. The availability of this data allows the assessment of the BMS using multivariatetechniques to enhance the life-cycle assessment of bridge networks, through advanced descriptiveand predictive techniques applied to deteriorating network assets. Multivariate techniques such asprincipal component analysis have been demonstrated by the authors to be effectively applied as adescriptive tool to an existing BMS, and the results of a case study of a large dataset of bridges indicateits viability to be integrated into data-based approaches to infrastructural asset management.