Data-driven hierarchical decision support for civil aviation maintenance safety risk: A fusion of Bayesian network and system dynamics

Jirong  Duan; Ming  Cheng

doi:10.59400/adecp3774

Data-driven hierarchical decision support for civil aviation maintenance safety risk: A fusion of Bayesian network and system dynamics

Jirong Duan
School of Safety Science and Engineering, Civil Aviation University of China, Tianjin 300300, China
Ming Cheng
School of Safety Science and Engineering, Civil Aviation University of China, Tianjin 300300, China

Article ID: 3774

DOI: https://doi.org/10.59400/adecp3774

Keywords: continuous endurance risk management; Bayesian network; system dynamics; risk analysis; data-driven

Abstract

To enhance the scientificity and precision of risk analysis and management decision-making in aircraft maintenance operations, this study proposes a risk analysis-decision model tailored to maintenance events. Based on actual civil aviation maintenance scenarios, the model employs real data to conduct data-driven analysis and precisely calculates the occurrence probabilities of various risk factors by constructing a Bayesian risk probability network. Meanwhile, it selects three categories of key risk factors: personnel (A), management (B), and organization (C), to build a system dynamics scenario, thereby simulating the long-term implementation effects of different management strategies. The research findings indicate that the existing maintenance management system demonstrates a certain level of risk buffering efficacy under normal operating conditions, effectively preventing risks from evolving into higher severity levels. The combinations of key risk factors at different severity levels exhibit a hierarchical characteristic, specifically manifesting as three tiers dominated by organization and safety barriers, personnel capabilities and behaviors, and daily operations and slow-variable risks, respectively. It is proposed that maintenance safety risk governance should adopt a graded and differentiated management strategy. At the decision-making level, the model is capable of simulating the long-term impacts of different management strategies. The study reveals that increasing management investment can significantly reduce process risks, whereas systemic risks and frontline operational errors require sustained, long-term resource allocation for improvement.

Published

2026-02-05

How to Cite

Duan, J., & Cheng, M. (2026). Data-driven hierarchical decision support for civil aviation maintenance safety risk: A fusion of Bayesian network and system dynamics. Advances in Differential Equations and Control Processes, 33(1). https://doi.org/10.59400/adecp3774

Download Citation

Issue

Vol. 33 No. 1 (2026)

Section

Articles

This work is licensed under a Creative Commons Attribution 4.0 International License.

References

[1]Strengthened profitability expected in 2025 even as supply chain issues persist. Available online: https://www.iata.org/en/pressroom/2024-releases/2024-12-10-01/ (accessed on 16 November 2025).

[2]Esteban A, Zafra A, Ventura S. Data mining in predictive maintenance systems: A taxonomy and systematic review. WIREs Data Mining and Knowledge Discovery. 2022; 12(5): e1471.

[3]Stanton I, Munir K, Ikram A, et al. Predictive maintenance analytics and implementation for aircraft: Challenges and opportunities. Systems Engineering. 2023; 26(2): 216–37.

[4]Bauranov A, Rakas J. Bayesian network model of aviation safety: Impact of new communication technologies on mid-air collisions. Reliability Engineering & System Safety. 2024; 243: 109905.

[5]Wang L, Wang Y, Ding Y. Risk analysis and resilience of humanitarian aviation supply chains: A Bayesian network approach. Applied Sciences. 2025;15(19): 10508.

[6]Pan W, Li Y, Jiang Y, et al. Analysis of controller-caused aviation accidents based on association rule algorithm and Bayesian network. Applied Sciences. 2025; 15(17): 9690.

[7]Zhang X, Mahadevan S. Bayesian network modeling of accident investigation reports for aviation safety assessment. Reliability Engineering & System Safety. 2021; 209: 107371.

[8]Zhou Z, Yu X, Zhu Z, et al. Development and application of a Bayesian network-based model for systematically reducing safety risks in the commercial air transportation system. Safety Science. 2023; 157: 105942.

[9]Guo R, Wu J, Ji F, et al. Analysis of traffic safety in airport aircraft activity areas based on Bayesian networks and fault trees. Digital Transportation and Safety. 2024; 3(1): 8–18.

[10]Liu H, Hu M, Yang L. A new risk level identification model for aviation safety. Engineering Applications of Artificial Intelligence. 2024; 136(Part A): 108901.

[11]Dang X, Shao Y, Liu H, et al. Risk Analysis Method of Aviation Critical System Based on Bayesian Networks and Empirical Information Fusion. Electronics. 2025; 14(12): 2496.

[12]Chen YH, Lin JJ. Determinants of flight delays at East Asian airports from an airport, route and network perspective. Journal of Air Transport Management. 2021; 94: 102064.

[13]Barry DJ. Estimating runway veer-off risk using a Bayesian network with flight data. Transportation Research Part C: Emerging Technologies. 2021; 128: 103180.

[14]Qi X, Liu C, Fan D, et al. Causal modeling and risk assessment of runway excursion events via interpretable machine learning. Reliability Engineering & System Safety. 2025; 269: 112055.

[15]Zhao Y, Hua S, Ren X. Relevance research of threat/error and undesired states in air traffic management based on Bayesian network model. Journal of Air Transport Management. 2017; 60: 45–48.

[16]Arnaldo Valdés RM, Gómez Comendador VF, Perez Sanz L, et al. Prediction of aircraft safety incidents using Bayesian inference and hierarchical structures. Safety Science. 2018; 104: 216–230.

[17]Ifelebuegu AO, Awotu-Ukiri EO, Theophilus SC, et al. The application of Bayesian—Layer of Protection Analysis method for risk assessment of critical subsea gas compression systems. Process Safety and Environmental Protection. 2018; 113: 305–18.

[18]He S, Shi S, Lin Z, et al. Risk assessment of coal mine gas explosion based on cloud model and Bayesian network. Reliability Engineering & System Safety. 2025: 111798.

[19]Wang N, Yuen KF, Li D, et al. A bayesian network approach to ship safety assessment: Integrating machine learning and expert opinions. Reliability Engineering & System Safety. 2025; 111659.

[20]Zhao L, Gao Q, Dong Y, et al. Vision-guided dynamic risk assessment for long-span PC continuous rigid-frame bridge construction through DEMATEL–ISM–DBN modelling. Buildings. 2025; 15(24): 4543.

[21]Li X, Wang G, Gui Y. Enhancing subway fire safety with a symmetric framework: From fault tree analysis to dynamic Bayesian network inference. Symmetry. 2025; 17(12): 2090.

[22]Huang X, Wang Q, Li X, et al. Navigation risk assessment of Arctic shipping routes based on Bayesian networks. Journal of Marine Science and Engineering. 2025; 13(12): 2306.

[23]Zhang J, Wu L, Zhang T, et al. Systemic and dynamic risk analysis of drilling construction based on Bayesian network and system dynamics model. Scientific Reports. 2025; 15(1): 27989.

[24]Bakhtiari S, Najafi MR, Goda K, et al. A dynamic Bayesian network approach to characterize multi-hazard risks and resilience in interconnected critical infrastructures. Reliability Engineering & System Safety. 2025; 257(Part A): 110815.

[25]You Q, Guo J, Zeng S, Che H. A dynamic Bayesian network based reliability assessment method for short-term multi-round situation awareness considering round dependencies. Reliability Engineering & System Safety. 2024; 243: 109838.

[26]Li X, Chen R, Ren Y, Jim CY. Intrinsic drivers of urban flood disasters from the resilience perspective in China. Reliability Engineering & System Safety. 2025; 265(Part B): 111596.

[27]Yuan Z, Cai L, Xie Z, et al. Dynamic evolution and scenario-based prediction of urban flood resilience: A system dynamics modeling approach in Kunming, China. Journal of Environmental Management. 2025; 395: 127740.

[28]Reason, JT. Human Error. Cambridge University Press; 1990.

Early fault signals of the rolling bearing in the rotor are weak and present the characteristics of non-periodic and non-stationary; it is more difficult to carry out fault diagnosis on it. In this regard, this paper proposes a weak rolling bearing fault diagnosis algorithm based on whale optimization algorithm, simplistic geometry mode decomposition, and maximum correlated kurtosis deconvolution (WOA-SGMD-MCKD). Firstly, the vibration signal of the rotor platform is obtained, and the Symmetric Geometric Mode Decomposition (SGMD) is used to reconstruct the vibration signal. To obtain the best decomposition effect of the SGMD and overcome modal aliasing, the Whale Optimization Algorithm (WOA) is used to optimize the embedding dimension. Secondly, for the reconstructed vibration signal, the Maximum Correlated Kurtosis Deconvolution (MCKD) is used to extract its impulse component, and the WOA is used to optimize the filter length and deconvolution period of the MCKD so that the frequency envelope spectrum of the vibration signal can be obtained, which can provide the basis for the fault diagnosis of rolling bearings. Finally, the effectiveness and feasibility of the algorithm proposed are verified by a non-periodic and non-stationary simulation platform and rotor maneuvering platform in this paper.

Numerical solution of a 3D mathematical model for the progression of tumor angiogenic factor in a tissue

In this work, the movement of tumor angiogenic factor in a three-dimensional tissue is obtained by the Method of Lines. This method transforms a partial differential equation into a system of ordinary differential equations together with the initial and boundary conditions. The more the number of lines is increased, the more the accuracy of the method increases. This method results in very accurate numerical solutions for linear and non-linear problems in contrast with other existing methods. We present Matlab-generated figures, which are the movement of tumor angiogenic factor in porous medium and explain the biological importance of this progression. The computer codes are also provided.

Mathematical modelling and controllability analysis of fractional order coal mill pulverizer model

This paper investigates the controllability of nonlinear dynamical systems and their applications, with a focus on fractional-order systems and coal mill models. A novel theorem is proposed, providing sufficient conditions for controllability, including constraints on the steering operator and nonlinear perturbation bounds. The theorem establishes the existence of a contraction mapping for the nonlinear operator, enabling effective control strategies for fractional systems. The methodology is demonstrated through rigorous proof and supported by an iterative algorithm for controller design. Additionally, the controllability of a coal mill system represented as a nonlinear differential system, is analyzed. The findings present new insights into the interplay of fractional dynamics and nonlinear systems, offering practical solutions for real-world control problems.