This study presents a tri-state modeling-based FTA-BN hybrid diagnostic framework for assessing the reliability of diesel powertrains in heavy-duty railway maintenance machinery. Recognizing the critical role of these power units in project timeline control and construction efficiency, the framework addresses the challenge of multi-phase fault evolution under harsh operating conditions. A tri-state model—comprising fully operational, performance degradation, and functional failure states—is introduced to enable dynamic, quantitative evaluation of system degradation, overcoming the limitations of traditional binary-state models in characterizing performance degradation processes. The methodology employs a modular failure decomposition strategy and constructs a multi-level fault tree model based on the functional topology of the Deutz BF12L513C powertrain. By integrating a Dynamic Bayesian Network (DBN), the framework achieves three objectives: (1) probabilistic fusion of long-term operational data, (2) quantification of expert-based conditional probabilities using the Delphi method, and (3) uncertainty propagation among coupled failure modes. Analysis of 3 years of field data yields a system reliability of 0.9330, with a 6.25% probability of performance degradation and a 0.44% probability of functional failure. Fault path analysis identifies hydraulic circuit integrity (node X67) and the exhaust energy recovery subsystem (node X73) as key reliability bottlenecks. This framework offers a scalable approach for preventive maintenance and life-cycle reliability management in complex engineering systems.
AddepalliSKPammingerMScarcelliR, et al. Modeling the impact of the fuel injection strategy on the combustion and performance characteristics of a heavy-duty GCI engine. Int J Engine Res2024; 25(1): 24–46.
2.
KulahSForraiARentmeesterF, et al. Robust cylinder pressure estimation in heavy-duty diesel engines. Int J Engine Res2017; 19(2): 179–188.
3.
TaoJYeBLiW, et al. An electromechanical coupling model for performance enhancement in diesel generator sets. Int J Engine Res2025; 26(8): 1269–1286.
4.
LeeDKwonH-JChoiK.Risk-based maintenance optimization of aircraft gas turbine engine component. Proc Inst Mech Eng2024; 238(2): 429–445.
5.
LiuY.Analysis of causes of black smoke failure in diesel vehicles. Int Combust Eng Parts2024; 24(11): 94–96.
6.
ZhaoR.Common faults and treatments of diesel engines for internal combustion locomotives. Int Combust Eng Parts2022; 22(3): 124–126.
7.
YanF.Discussion on diesel engine failures of large-scale road maintenance machines: tamping cars. Mod Business Trade Ind2013; 25(24): 187.
8.
MuJ.Design and implementation of diesel engine fault diagnosis system for railway locomotives. PhD Thesis, Beijing Jiaotong University, Beijing, China, 2023.
9.
LiuY.Fault diagnosis and health management of diesel engine fuel systems. PhD Thesis, Dalian University of Technology, Dalian, China, 2021.
10.
XiongGMaWZhaoN, et al. Multi-type diesel engines operating condition recognition method based on stacked auto-encoder and feature transfer learning. IEEE Access2021; 9: 31043–31052.
11.
WangQ.Design and research of embedded diesel engine fault diagnosis system based on ARM. PhD Thesis, North University of China, Taiyuan, China, 2013.
12.
LiHYinXHeW, et al. A new fault diagnosis method based on belief rule base with attribute reliability considering multi-fault features. IEEE Access2023; 11: 92766–92774.
HuangTChenGYangZ, et al. Reliability analysis method for multi-state systems considering performance degradation and variable working conditions. Sci Technol Eng2018; 18(30): 160–165.
15.
MaD.Research on the method of constructing reliability analysis models based on Bayesian network and multi-source information. PhD Thesis, Harbin University of Science and Technology, Harbin, China, 2015.
16.
LvRSunL.Complex system fault diagnosis method based on multi-source information fusion fault tree and fuzzy petri net. Comput Integr Manuf Syst2017; 23(8): 1817–1831.
17.
HarisOKurniawanMAAliAY.Analysis of cooling system radiator fault on diesel engine using fault tree analysis (FTA) method. In: Proc. 2021 IEEE 7th Int. Conf. Computing, Engineering and Design (ICCED), Sukabumi, Indonesia, 2021, pp. 1–6.
18.
ZhaoZQiJ. Reliability analysis of emu traction drive system based on FTA method. In: 2022 14th International Conference on Measuring Technology and Mechatronics Automation (ICMTMA), Changsha, China, 2022, pp. 408–412.
19.
LiuSPuYZhangG, et al. Fault diagnosis expert system for top drive system based on FTA. In: 2021 40th Chinese Control Conference (CCC), Shanghai, China, 2021, pp. 4642–4646.
20.
DongZLiCTangS, et al. Reliability analysis method for ship equipment based on multi-state fault tree. Fire Control Command Control2023; 48(4): 59–64.
21.
LiuY.Research and application of fault diagnosis method for water pump turbines based on fault tree analysis. PhD Thesis, Huazhong University of Science and Technology, Wuhan, China, 2019.
22.
WangCWangLChenH, et al. Fault diagnosis of train network control management system based on dynamic fault tree and Bayesian network. IEEE Access2021; 9: 2618–2632.
23.
ChenHZhaoALiT, et al. Fault diagnosis of complex equipment based on fuzzy Bayesian network inference with fault tree. Syst Eng Electron2021; 43(5): 1248–1261.
24.
GhadhabMJungesSKatoenJP, et al. Safety analysis for vehicle guidance systems with dynamic fault trees. Reliab Eng Syst Saf2019; 186: 37–50.
25.
ChuJWangFWangY, et al. Fault diagnosis method of wind turbines based on fault tree and probabilistic neural networks. Acta Energiae Solaris Sinica2018; 39(10): 2901–2907.
26.
YaoCChenDWangB.Fuzzy reliability assessment method based on t-s fault tree and Bayesian network. J Mech Eng2014; 50(2): 193–201.
27.
LiuXWuJ.Application of Bayesian network in fault diagnosis. J Beijing Union Univ2014; 28(2): 60–63.
28.
ZhengYZhaoFWangZ.Fault diagnosis system of bridge crane equipment based on fault tree and Bayesian network. Int J Adv Manuf Technol2019; 105(9): 3605–3618.
29.
ZhuH-LLiuS-SQuYY, et al. A new risk assessment method based on belief rule base and fault tree analysis. Proc Inst Mech Eng2022; 236(3): 420–438.
30.
FengJShangJIbrahimANH. Disposal for the pinching people and objects accidents in fully automated operation urban rail transit lines based on fault tree analysis. In: Proceedings of the 7th International Conference on Artificial Intelligence, Medical Engineering and Education, Guangzhou, China, November 2023, pp. 430–438.
31.
LiX.Automobile fault diagnosis method based on fault tree and Bayesian network. Mod Comput2023; 29(10): 9–14.
32.
LiZYangHHouL, et al. Fault analysis and impact weight calculation of marine diesel engine unable to start based on fault tree and analytic hierarchy process. In: Proceedings of the Fourth International Conference on Mechanical Engineering, Intelligent Manufacturing, and Automation Technology, Part Two, Guilin, China, October 2023, Pp. 130822Q.1–130822Q.7.
33.
ToloSAndrewsJ.Fault tree analysis including component dependencies. IEEE Trans Reliab2024; 73(1): 413–421.
34.
RoozbahaniAGhanianT.Risk assessment of inter-basin water transfer plans through integration of fault tree analysis and Bayesian network modelling approaches. J Environ Manag2024; 356: 120703.1–120703.14.
QiuCHuangQPanG, et al. Framework for a variational Bayesian convolutional network for velocity field prediction and uncertainty quantification of a pump-jet propulsor. Phys Fluids2022; 34(7): 077109.1–077109.23.
37.
ShiXGuHYaoB.Fuzzy Bayesian network fault diagnosis method based on fault tree for coal mine drainage system. IEEE Sens J2024; 24(6): 7537–7547.
38.
WangLFanHKongH.From undirected dependence to directed causality: A novel Bayesian learning approach. Intell Data Anal2022; 26(5): 1275–1302.
39.
WuXHuangHYuW, et al. Accident analysis and risk prediction of tank farm based on Bayesian network method. Proc Inst Mech Eng2024; 238(2): 366–386.
40.
YangKLeeD.Quantitative analysis of uncertainty in field data and calibration method for estimating life distribution parameters. Proc Inst Mech Eng2025; 239(5): 1024–1040.
41.
TongWLinHLiuY, et al. Reliability analysis of complex systems based on fuzzy Bayesian networks. Manuf Autom2023; 45(6): 148–153.
42.
GuoRWangZ.A framework for modeling fault propagation paths in air turbine starter based on Bayesian network. Proc Inst Mech Eng2022; 236(6): 1078–1095.
43.
WangLWangLGuoL, et al. Exploring complex multivariate probability distributions with simple and robust Bayesian network topology for classification. Appl Intell2023; 53(24): 29799–29817.
44.
ChenXMaXJiaL, et al. Causative analysis of freight railway accident in specific scenes using a data-driven Bayesian network. Reliab Eng Syst Saf2024; 243: 109781.1–109781.10.
45.
DuttweilerLThurstonSWAlmudevarA.Spectral Bayesian network theory. Linear Algebra Appl2023; 674: 282–303.
46.
YuKLingZLiuL, et al. Feature selection for efficient local-to-global Bayesian network structure learning. ACM Trans Knowl Discov Data2024; 18(2): 1–37.27.
47.
LiGZhouQ.Bayesian multi-task variable selection with an application to differential DAG analysis. J Comput Graph Stat2024; 33(1): 35–46.
48.
HuangYZhuH.Application research on fault attribute reduction of large-scale track maintenance machinery based on rough set. Electron Test2019; 11: 69–70.
49.
GengJHanG.Discussion on the use, maintenance, and servicing of Deutz BF12L513C air-cooled diesel engine. Int Combust Eng Parts2023; 4: 64–66.
50.
LvYYangXLiY, et al. Fault detection and diagnosis of marine diesel engines: a systematic review. Ocean Eng2024; 294: 1.1–1.16.
51.
BoYWuHCheW, et al. Methodology and application of digital twin-driven diesel engine fault diagnosis and virtual fault model acquisition. Eng Appl Artif Intell2024; 131: 107853.1–107853.13.
52.
ZhaoQWangJLiQ, et al. Brief analysis of abnormal damage of bearing bush in DEUTZ diesel engines. Diesel Eng2013; 35(1): 56–57.
53.
FontanesiSShamsudheenFAGonzalezEG, et al. Impact of fuel surrogate formulation on the prediction of knock statistics in a single cylinder GDI engine. Int J Engine Res2024; 25(3): 405–423.
54.
CurranSOnoratiAPayriR, et al. The future of ship engines: renewable fuels and enabling technologies for decarbonization. Int J Engine Res2024; 25(1): 85–110.
55.
AnBXuPXiaoY.Construction and application of AHP judgment matrix considering spatial factors. Stat Inform Forum2024; 39(4): 3–19.
56.
DingYYangPFengK, et al. Health assessment of UAVs based on node importance and AHP. Control Eng2024; 31(10): 1805–1811.
57.
LinQLiangYChenQ, et al. Application and practice of environmental risk assessment of abandoned mines in karst areas based on AHP. Non-ferrous Metals2024; 76(3): 139–147.
