Generic Bayesian network models for making maintenance decisions from available data and expert knowledge

Abstract

To maximise asset reliability cost-effectively, maintenance should be scheduled based on the likely deterioration of an asset. Various statistical models have been proposed for predicting this, but they have important practical limitations. We present a Bayesian network model that can be used for maintenance decision support to overcome these limitations. The model extends an existing statistical model of asset deterioration, but shows how (1) data on the condition of assets available from their periodic inspection can be used, (2) failure data from related groups of asset can be combined using judgement from experts and (3) expert knowledge of the deterioration’s causes can be combined with statistical data to adjust predictions. A case study of bridges on the rail network in Great Britain (GB) is presented, showing how the model could be used for the maintenance decision problem, given typical data likely to be available in practice.

Keywords

Bayesian network available data expert knowledge maintenance modelling deterioration GB rail bridges

Get full access to this article

View all access options for this article.

References

Dhillon

. Engineering maintenance: a modern approach. Boca Raton, FL: CRC Press, 2002.

Agrawal

Kawaguchi

Chen

. Bridge element deterioration rates. New York: New York State Department of Transportation, 2009.

Jiang

Saito

Sinha

. Bridge performance prediction model using the Markov chain. Transportation Research Record 1180, 1988. Washington, DC: Transportation Research Board.

Cesare

Santamarina

Turkstra

et al . Modelling bridge deterioration with Markov chains. J Transp Eng 1992; 118: 820–833.

Shafahi

Hakhamaneshi

. Application of a maintenance management model for Iranian railways based on the Markov chain and probabilistic dynamic programming. Int J Sci Technol Trans A: Civil Eng 2009; 16: 87–97.

Audley

Andrews

. A Petri-net modelling approach to rail track geometry maintenance and inspection. In: Advances in risk and reliability technology symposium, Loughborough, 21–23 May 2013, pp.230–243. Loughborough: Loughborough University.

Rama

Andrews

. A system-wide modelling approach to railway infrastructure asset management. In: Advances in risk and reliability technology symposium, Loughborough, 21–23 May 2013, pp.7–22. Loughborough: Loughborough University.

Lauritzen

Jensen

. Stable local computation with conditional Gaussian distributions. Stat Comput 2001; 11: 191–203.

Fenton

Neil

. Risk assessment and decision analysis with Bayesian networks. Boca Raton, FL: CRC Press, 2012.

10.

Kozlov

Koller

. Nonuniform dynamic discretization in hybrid networks. In: Proceedings of the thirteenth conference on uncertainty in artificial intelligence, Providence, RI, 1–3 August 1997, pp.314–325. San Francisco, CA: Morgan Kaufmann Publishers.

11.

Marquez

Neil

Fenton

. Improved reliability modeling using Bayesian networks and dynamic discretization. Reliab Eng Syst Safe 2006; 95: 412–425.

12.

Birtles

Fenton

Neil

et al . AgenaRisk manual (version 6.1) computer software, 2014, http://www.agenarisk.com/

13.

Fink

. A compendium of conjugate priors. Technical Report, Montana State University, Bozeman, MT, May 1997.

14.

Gyftodimos

Flach

. Hierarchical Bayesian networks: a probabilistic reasoning model for structured domains. In: Proceedings of the ICML-2002 workshop on development of representations, Sydney, NSW, Australia, 8–12 July 2002, pp.23–30. Sydney, NSW, Australia: University of New South Wales.

15.

Cooke

. Experts in uncertainty: opinion and subjective probability in science. Oxford: Oxford University Press, 1991.

16.

Zhai

Lin

. Bayesian networks application in multi-state system reliability analysis. Appl Mech Mater 2013; 347: 2590–2595.

17.

Boudali

Dugan

. A continuous-time Bayesian network reliability modelling, and analysis framework. IEEE T Reliab 2006; 55: 86–97.

18.

Weber

Suhner

M-C

Iung

. System approach-based Bayesian network to aid maintenance of manufacturing processes. IFAC Proc Vol 2001; 34: 15–21.

19.

Kang

Golay

. A Bayesian belief network-based advisory system for operational availability focused diagnosis of complex nuclear power systems. Expert Syst Appl 1999; 17: 21–32.

20.

Celeux

Corset

Lannoy

et al . Designing a Bayesian network for preventive maintenance from expert opinions in a rapid and reliable way. Reliab Eng Syst Safe 2006; 91: 849–856.

21.

De Melo

Sanchez

. Software maintenance project delays prediction using Bayesian networks. Expert Syst Appl 2008; 34: 908–919.

22.

Weber

Medina-Oliva

Simon

et al . Overview on Bayesian networks applications for dependability, risk analysis and maintenance areas. Eng Appl Artif Intel 2012; 25: 671–682.

23.

Langseth

Portinale

. Bayesian networks in reliability. Reliab Eng Syst Safe 2007; 92: 92–108.

24.

Mengshoel

Darwiche

Uckun

. Sensor validation using Bayesian networks. In: Proceedings of the 9th international symposium on artificial intelligence, robotics, and automation in space (ISAIRAS-08), Los Angeles, CA, 26–29 February 2008. Pasadena, CA: Jet Propulsion Laboratory.

25.

Kuo

Yang

. Bayesian computation of software reliability. J Comput Graph Stat 1995; 4: 65–82.

26.

Coolen

. On Bayesian reliability analysis with informative priors and censoring. Reliab Eng Syst Safe 1996; 53: 91–98.

27.

Bhattacharjya

et al . Railway track geometry defect modeling: deterioration, derailment risk and optimal repair. In: Proceedings of the 92nd annual meeting transportation research board, Washington, DC, 13–17 January 2013. Washington, DC: Transportation Research Board.

28.

Edirisinghe

Setunge

Zhang

. Application of Gamma process for deterioration prediction of buildings from discrete condition data. Sri Lankan J Appl Stat 2012; 12: 13–26.

29.

Andrews

. A modelling approach to railway track asset management. Proc IMechE, Part F: J Rail and Rapid Transit 2013; 227(1): 56–73.

30.

. Modelling railway bridge asset management. PhD Thesis, University of Nottingham, Nottingham, 2014.

31.

Scholten

Scheidegger

Reichert

et al . Combining expert knowledge and local data for improved service life modelling of water supply networks. Environ Model Softw 2013; 42: 1–16.

32.

Yianni

Neves

Rama

et al . Incorporating local environmental factors into railway bridge asset management. Eng Struct 2016; 128: 362–373.

33.

Marsh

DWR

Nur

Yet

et al . Using operational data for decision making: a feasibility study in rail maintenance. Safe Reliab 2016; 36(1): 35–47.

34.

Jun

C-H

Balamurali

Lee

S-H

. Variables sampling plans for Weibull distributed lifetimes under sudden death testing. IEEE T Reliab 2006; 55: 53–58.

35.

Network Rail. Asset management policy: justification for civil engineering policy. London: Network Rail, 2015.

36.

Rafiq

Chryssanthopoulos

Sathananthan

. Bridge condition modelling and prediction using dynamic Bayesian belief networks. Struct Infrast Eng 2015; 11: 38–50.

37.

NR/SP/CIV/080. Management of existing bridges and culverts.

38.

McMahon

Woodward

. Development of risk-based examination intervals for network rail bridges. Report RSSB T569, 2006. London: RSSB.

39.

Arshad

Cook

. Bridges and structures. In: Vickers

(ed.) Cost-effective maintenance of railway track. London: Thomas Telford Publishing, 1992, pp.89–103.

40.

AASHTO. The manual for bridge evaluation. Washington, DC: American Association of State Highway and Transportation Officials, 2011.

41.

Tapan

Aboutaha

. Strength evaluation of deteriorated RC bridge columns. J Bridge Eng 2008; 13: 226–236.

42.

Wang

Shi

Nakano

. Strength degradation analysis of an aging RC girder bridge using FE crack analysis and simple capacity-evaluation equations. Eng Fract Mech 2013; 108: 209–221.

43.

Von Winterfeldt

Edwards

. Decision analysis and behavioral research. Cambridge: Cambridge University Press, 1986.