A fuzzy-based Bayesian Belief Network approach for railway bridge condition monitoring and fault detection

Vagnoli, Matteo and Remenyte-Prescott, Rasa and Andrews, John (2017) A fuzzy-based Bayesian Belief Network approach for railway bridge condition monitoring and fault detection. In: Safety and Reliability – Theory and Application: ESREL 2017. CRC Press. ISBN 9781138629370

[img] PDF - Repository staff only until 25 May 2018. - Requires a PDF viewer such as GSview, Xpdf or Adobe Acrobat Reader
Download (550kB)

Abstract

More than 35% of the European railway bridges are over 100 years old and the increasing traffic loads are pushing the railway infrastructure to its limits. Bridge condition-monitoring strategies can help the railway industry to improve safety, availability and reliability of the network. In this paper, a Bayesian Belief Network method for condition monitoring and fault detection of a truss steel railway bridge is proposed by relying on a fuzzy analytical hierarchy process of expert knowledge. The BBN method is proposed for obtaining the bridge health state and identifying the most degraded bridge elements. A Finite Element model is developed for simulating the bridge behaviour and studying a degradation mechanism. The proposed approach originally captures the interactions existing between the health state of different bridge elements and, furthermore, when the evidence about the displacement is introduced in the BBN, the health state of the bridge is updated.

Item Type: Book Section
Additional Information: Papers presented at ESREL 2017 will be published in the conference proceedings issued by Taylor and Francis, CRC Press: Safety and Reliability – Theory and Application: ESREL 2017. https://www.crcpress.com/ESREL-2017-Portoroz-Slovenia-18-22-June-2017/Cepin-Bris/p/book/9781138629370
Schools/Departments: University of Nottingham, UK > Faculty of Engineering
Depositing User: Eprints, Support
Date Deposited: 06 Mar 2017 15:05
Last Modified: 04 Jul 2017 05:40
URI: http://eprints.nottingham.ac.uk/id/eprint/41104

Actions (Archive Staff Only)

Edit View Edit View