Using a dynamic Bayesian network (DBN) to estimate the failure risk of a component or system that deteriorates with time has several advantages. A DBN discretizes the probability distribution of variables and thereby increases the efficiency of computing resources and reduces computation time. However, it is important to devise an optimal discretization scheme because the size of the model grows exponentially as the number of discretized intervals increases. In this paper, we propose an optimal discretization scheme for a DBN used to model the time-varying deterioration of a turbine blade component. The results of estimating the reliability indices with the DBN were verified by comparing them with the results of a Monte Carlo simulation. In addition, compared with a log-transformed discretization method, our DBN discretization method shows a significantly increased computation speed.
Gorjian JolfaeiNRameezdeenRGorjianN, et al. Prognostic modelling for industrial asset health management. Saf Reliab2022; 41(1): 45–97.
2.
HuangLCaiGYuanH, et al. A hybrid approach for identifying the structure of a Bayesian network model. Expert Syst Appl2019; 131: 308–320.
3.
ZhangGThaiVVExpert elicitation and Bayesian Network modeling for shipping accidents: a literature reviewSaf Sci2016; 87: 53–62.
4.
Saraygord AfshariSEnayatollahiFXuX, et al. Machine learning-based methods in structural reliability analysis: a review. Reliab Eng Syst Saf2022; 219: 1–31.
5.
MisuriAKhakzadNReniersG, et al. A Bayesian network methodology for optimal security management of critical infrastructures. Reliab Eng Syst Saf2019; 191: 106112.
6.
LiCQMelchersRE. Time-dependent_risk_assessment of structural deterioration caused by reinforcement corrosion. ACI Struct J2005; 102(5): 754–762.
7.
StraubD. Stochastic modeling of deterioration processes through dynamic Bayesian networks. J Eng Mech2009; 135(10): 1089–1099.
8.
FentonNNeilM. Risk assessment and decision analysis with Bayesian networks. 2nd ed.. Boca Raton, FL: CRC Press, 2019.
9.
CobbBRShenoyPP. Inference in hybrid Bayesian networks with mixtures of truncated exponentials. Int J Approx Reason2006; 41(3): 257–286.
10.
CobbBRShenoyPP. Nonlinear deterministic relationships in Bayesian networks. In 8th European conference on symbolic and quantitative approaches to reasoning and uncertainty (ed GodoL), July2005, pp.27–38. Berlin, Heidelberg: Springer.
11.
MorrisseyRJMcdowellDLNicholasT. Frequency and stress ratio effects in high cycle fatigue of Ti-6Al-4V. Int J Fatigue1999; 21: 679–685, 1999.
12.
LiuYMahadevanS. Probabilistic fatigue life prediction using an equivalent initial flaw size distribution. Int J Fatigue2009; 31(3): 476–487.
13.
ZhuJColletteM. A dynamic discretization method for reliability inference in dynamic Bayesian networks. Reliab Eng Syst Saf2015; 138: 242–252.
14.
ZwirglmaierKStraubD. A discretization procedure for rare events in Bayesian networks. Reliab Eng Syst Saf2016; 153: 96–109.
15.
NojavanFQianSSStowCA. Comparative analysis of discretization methods in Bayesian networks. Environ Model Softw2017; 87: 64–71.
16.
RitchieROBoyceBLCampbellJP, et al. Thresholds for high-cycle fatigue in a turbine engine Ti-6Al-4V alloy. Int J Fatigue1999; 21: 653–662.
17.
AnDChoiJHKimNH. Identification of correlated damage parameters under noise and bias using Bayesian inference. Struct Health Monit2012; 11(3): 293–303.
18.
LeeDKwonK. Dynamic Bayesian network model for comprehensive risk analysis of fatigue-critical structural details. Reliab Eng Syst Saf2023; 229: 108834.
19.
SureshS. Fatigue of materials. 2nd ed.Cambridge: Cambridge University Press, 1998.
20.
LeeDKimNKimM-S. Dynamic Bayesian network for fatigue-crack-related risk assessment of aerospace bolts. J Aerosp Info Syst2022; 19(6): 1–10.
21.
KozlovAVKollerD. Nonuniform dynamic discretization in hybrid networks. In The 13th conference on uncertainty in artificial intelligence, Providence Rhode Island, 1 August 1997, pp. 314–325. ACM Digital Library, Morgan-Kaufman, San Francisco.
22.
NeilMTailorMMarquezD. Inference in hybrid Bayesian networks using dynamic discretization. Stat Comput2007; 17(3): 219–233.
23.
LeeDYangSParkJ, et al. Investigation of detectable crack length in a bolt hole using eddy current inspection. Trans Korean Soc Mech Eng A2017; 41(8): 729–736.
24.
ZhaoZHaldarA. Bridge fatigue damage evaluation and updating using non-destructive inspections. Eng Fract Mech1996; 53(5): 775–788.
25.
LeeDLimDKimH, et al. Bayesian method for estimating initial crack size distribution for probabilistic risk analysis of repairable structural details. Fatigue Fract Eng Mater Struct2022; 45(8): 2356–2370.
26.
LeeDAchenbachJD. Analysis of the reliability of a jet engine compressor rotor blade containing a fatigue crack. J Appl Mech Trans ASME2016; 83(4): 2016.
