A rule-based approach for establishing states in a Markov process applied to maintenance modelling

Abstract

The deterioration of technical systems can often be classified into discrete states, and the transitions between these states can be modelled using a Markov process. Instead of using an exponential distribution, it may be more realistic to assume that a general probability distribution describes the sojourn time in one of these states. The resultant model is a semi-Markov process, which may be difficult to treat analytically. This paper therefore presents an approach where the sojourn times in these states are gamma distributed and where the gamma distribution is transformed into a Markov process with a sequence of states that have exponentially distributed sojourn times. This means that the gamma distribution is approximated by a Markov process, which simplifies maintenance modelling. The approach presented is based on a simple rule such that it can easily be implemented in a maintenance model. It is shown that the approach yields good results compared with available alternatives.

Keywords

gamma distribution maintenance model Markov process phase-type distribution

Get full access to this article

View all access options for this article.

References

van Winden

Dekker

‘Rationalisation of building maintenance by Markov decision models: A pilot case study’

J. Opl Res. Soc. 49 (9) (1998): 928–935

Endrenyi

Anders

G. J

Leite da Silva

A. M

‘Probabilistic evaluation of the effect of maintenance on reliability. An application’

IEEE Trans. Power Syst. 13 (2) (1998): 576–583

Welte

T. M

Vatn

Heggset

‘Markov state model for optimization of maintenance and renewal of hydro power components’. In Proceedings of the IEEE International Conference on Probabilistic Methods Applied to Power Systems (PMAPS), Stockholm, 2006, CD-ROM, pp. 1–7.

Kallen

M. J.

van Noortwijk

J. M.

‘Optimal periodic inspection of a deterioration process with sequential condition states’

Int. J. Pres. Ves. Pip. 83 (2006): 249–255

Jayakumar

Asgapoor

‘Maintenance optimization of equipment by linear programming’

Prob. Engng Inf. Sci. 20 (2006): 183–193

Jirutitijaroen

Singh

‘The effect of transformer maintenance parameters on reliability and cost: A probabilistic model’

Electric Power Syst. Res. 72 (3) (2004): 213–224

Anders

G. J

Endrenyi

Yung

‘Risk-based planner for asset management’

IEEE Comput. Applic. Power 14 (4) (2001): 20–26

Montoro-Cazorla

Pérez-Ocón

‘Maintenance of systems by means of replacements and repairs: the case of phase-type distributions’

Asia–Pacif. J. Opl Res. 24 (3) (2007): 421–434

Neuts

M. F

Neuts

M. F

(Eds.) In Matrix-geometric solutions in stochastic models (Baltimore: Johns Hopkins University Press 1981): pp. 41–80 Probability distributions of phase type.

10.

Asmussen

Nerman

Olsson

‘Fitting phase type distributions via the EM algorithm’

Scand. J. Statists 23 (1996): 419–441

11.

Horváth

Telek

Field

Harrison

P. G

Bradley

Harder

(Eds.) ‘PhFit: A general phase-type fitting tool’ Computer performance evaluation: modelling techniques and tools (Berlin: Springer 2002): pp. 82–91

12.

Lang

Arthur

J. L

Chakravarty

S. R

Alfa

A. S

(Eds.) ‘Parameter approximation for phase type-distributions’ Matrix-analytic methods in stochastic models (New York: Marcel Dekker 1996): pp. 151–206

13.

Montoro-Cazorla

Pérez-Ocón

‘A deteriorating two-system with two repair modes and sojourn times phase-type distributed’

Reliab. Engng Syst. Saf. 91 (2006): 1–9

14.

Olsson

‘EMpht. A program for fitting phase-type distributions’. (1998) http://home.imf.au.dk/asmus/pspapers.html.

15.

Olsson

‘EM estimation in phase type models, Department of Mathematics’ (Gøteborg, Sweden: Chalmers Technical University 1995) PhD thesis.

16.

Olsson

‘The EMpht-programme. User guide for the EMpht-programme’. (1998) http://home.imf.au.dk/asmus/dl/EMusersguide.ps.

17.

Meeker

W. Q

Escobar

L. A

Statistical methods for reliability data (New York: Wiley 1998)

18.

Sim

S. H

Endrenyi

‘Optimal preventive maintenance with repair’

IEEE Trans. Reliab. 37 (1) (1988): 92–96

19.

Dekker

Smeitink

‘A simple approximation to the renewal function’

IEEE Trans. Reliab. 39 (1) (1990): 71–75

20.

Welte

T. M

Aven

Vinnem

J. E

(Eds.) ‘A theoretical study of the impact of different distribution classes in a Markov model’ Risk, reliability and societal safety: Proceedings ESREL 2007 (London: Taylor & Francis 2007): pp. 1143–1151

21.

Horváth

Telek

Latouche

Taylor

(Eds.) ‘Approximating heavy tailed behavior with phase type distributions’ Advances in algorithmic methods for stochastic methods (New Jersey: Notable Publications 2000): pp. 191–214

22.

Kullback

Leibler

R. A

‘On information and sufficiency’

Ann. Math. Statists 22 (1) (1951): 79–86

23.

EBL. Condition monitoring handbooks: Generator/ Turbine/ Waterway, cooling water and drainage equipment/ Control system (four books, in Norwegian), 1993–2007 (EBL – Norwegian Electricity Industry Association, Oslo, Norway).