A fuzzy-based Bayesian belief network approach for railway bridge condition monitoring and fault detection

Vagnoli, Matteo; Remenyte‐Prescott, Rasa; Andrews, John

doi:10.1201/9781315210469-341

Cited by 4 publications

(7 citation statements)

References 15 publications

(22 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…where E l is the number of years of experience of the expert l; β is a parameter employed to adequately weigh the analysis of each expert, and needs to be optimised to guarantee a group judgment. 33…”

Section: The Proposed Bayesian Belief Network Methods For Bridge Degradation Detectionmentioning

confidence: 99%

“…In what follows, only the main output of the FAHP is described; an interested reader can find further details in Loughney and Wang 22 and Wang and Elhag. 33 The FAHP aims to assess the importance weight vector ( w h ) of each parent node on its child nodes, that is, the influence of each parent node on the health state of its child node:…”

Section: The Proposed Bayesian Belief Network Methods For Bridge Degradation Detectionmentioning

confidence: 99%

“…The elements of the bridge are modelled by considering grade S355 steel, as this steel is commonly used in Europe to build steel railway bridges. 33 The reference system, depicted in Figure 3, is defined as follows: the right-hand side of the bridge is considered as the side of the bridge at y = 0 m, the left-hand side is considered to be at y = 7 m.…”

Section: Application Of the Bbn Methods To Detection Of Bridge Degradationmentioning

confidence: 99%

See 2 more Smart Citations

A Bayesian Belief Network method for bridge deterioration detection

Vagnoli

Remenyte‐Prescott

Andrews

2020

Proceedings of the Institution of Mechanical Engineers, Part O:

Self Cite

View full text Add to dashboard Cite

Bridges are one of the most important assets of transportation networks. A closure of a bridge can increase the vulnerability of the geographic area served by such networks, as it reduces the number of available routes. Condition monitoring and deterioration detection methods can be used to monitor the health state of a bridge and enable detection of early signs of deterioration. In this paper, a novel Bayesian Belief Network (BBN) methodology for bridge deterioration detection is proposed. A method to build a BBN structure and to define the Conditional Probability Tables (CPTs) is presented first. Then evidence of the bridge behaviour (such as bridge displacement or acceleration due to traffic) is used as an input to the BBN model, the probability of the health state of whole bridge and its elements is updated and the levels of deterioration are detected. The methodology is illustrated using a Finite Element Model (FEM) of a steel truss bridge, and for an in-field post-tensioned concrete bridge.

show abstract

Section: The Proposed Bayesian Belief Network Methods For Bridge Degradation Detectionmentioning

confidence: 99%

Section: The Proposed Bayesian Belief Network Methods For Bridge Degradation Detectionmentioning

confidence: 99%

Section: Application Of the Bbn Methods To Detection Of Bridge Degradationmentioning

confidence: 99%

See 1 more Smart Citation

A Bayesian Belief Network method for bridge deterioration detection

Vagnoli

Remenyte‐Prescott

Andrews

2020

Proceedings of the Institution of Mechanical Engineers, Part O:

Self Cite

View full text Add to dashboard Cite

show abstract

“…At the same time, a more reliable pdf of the bridge behaviour can help to enhance the reliability of the BBN results in terms of damage detection and diagnostics. Further pdfs have been investigated in [Vagnoli, 2019] In what follows, the CDFs of sensor A and B, shown in Table 3-4, are used to update the CPTs of node E_4_1 and E_5_1, respectively. It should be noted that the proposed method allows to update the CPTs when new evidence of the bridge behaviour is available, and thus the CPTs, which were originally defined by relying on expert elicitation process only, are updated by taking account of both the current and past evidence of the bridge behaviour.…”

Section: The Assessment Of Aicc and Q-q Plotmentioning

confidence: 99%

Updating conditional probabilities of Bayesian belief networks by merging expert knowledge and system monitoring data

Vagnoli

Remenyte‐Prescott

2022

Automation in Construction

View full text Add to dashboard Cite

“…Fatigue is one of many assessments that can be conducted to seek for the security of old bridges. However, many assessments also can be done by measuring all related parameters directly in the field, for example using fiber optic distributed as a sensor to read the strain indicator [7] and even the detection of fault and monitoring can involve artificial intelligence (AI) with fuzzy-based network [8]. After the assessment, the future action from the result has to be considered as well.…”

Section: Introductionmentioning

confidence: 99%

Structural Evaluation of Railway Warren Steel Truss Bridge with Span Length of 42 Meter According to SNI 2833:2016 and Earthquake Hazard Map 2017

Soebandono¹,

Maulana²,

Ismayana³

et al. 2019

Proceedings of the Third International Conference on Sustainable Innovation 2019 – Technology and Engineering (IcoSITE 2019)

View full text Add to dashboard Cite

Railway bridge with the warren type truss structure in the Sumatera region is an infrastructure has existed since the Dutch colonial era. Bridge is used as a mode transportation for natural resources of coal. The construction of railway bridge must always be monitored and evaluated for the feasibility of the structure, especially for earthquake load. This is due to change the latest of earthquake hazard maps and regulations regarding earthquake load. The research used SNI 2833:2016 regulations, about bridge planning for earthquake load and 2017 earthquake hazard maps, by modelling the 42 meter warren type of truss structure using SAP2000 V.21 software. The results of the research indicate that, the largest of mode shape value occurs UZ point with the 6 mode number of 0,82536 displacement unit and a period value of 0,075276 second. The largest of period (T) value occurs in 1 mode number of 0,37002 second. The maximum displacement occurs U3 point at the joint 25 of 36,437377 mm opposites the axis. The value of displacement in the direction of U3 is smaller than the value of allowed deflection of 52,5 mm. Then, at the stress control, there are 13 frames that have overstressed and the maximum stressed of frame occurs on the pressure frame, the IWF150.150.7.10 frame has the Pu value of 22,462 tons with a nominal compressive capacity (Pn) of 12,612 tons. Based on the 3 reviews, it can be concluded that, the bridge structure requires structural reinforcement on cross girder 1 (IWF1100.400.16.28), 2(IWF1100.400.16.28) and 7(IWF1100.400.16.28) frames and on wind bracing 13 to 22 (IWF150.150.7.10) frames.

show abstract

A fuzzy-based Bayesian belief network approach for railway bridge condition monitoring and fault detection

Cited by 4 publications

References 15 publications

A Bayesian Belief Network method for bridge deterioration detection

A Bayesian Belief Network method for bridge deterioration detection

Updating conditional probabilities of Bayesian belief networks by merging expert knowledge and system monitoring data

Structural Evaluation of Railway Warren Steel Truss Bridge with Span Length of 42 Meter According to SNI 2833:2016 and Earthquake Hazard Map 2017

Contact Info

Product

Resources

About