A HYBRID PROBABILISTIC AND FMEA-BASED MODEL FOR RELIABILITY AND FAULT TOLERANCE ASSESSMENT OF AI-BASED SECURITY SYSTEMS
DOI:
https://doi.org/10.68302/std2026.vol1.136Keywords:
Artificial intelligence, Fault tolerance, FMEA analysis, Intelligent security systemsAbstract
This study presents a hybrid approach that integrates probabilistic modeling and Failure Mode and Effects Analysis (FMEA) for the analysis and optimization of reliability and fault tolerance in AI-driven integrated security systems. With the increasing complexity of modern intelligent systems—incorporating video analytics, Internet of Digital Things (IoDT) sensors, autonomous drones, and distributed computing infrastructures—there is a growing need for comprehensive methods to evaluate system risk and resilience. A mathematical model based on stochastic processes and Markov chains is developed, enabling quantitative evaluation of failure probabilities and transitions between key system states, including normal operation, degraded mode, and complete failure. In parallel, an FMEA analysis is applied to identify critical components, assess the consequences of potential failures, and calculate Risk Priority Numbers (RPN). The proposed hybrid model integrates probabilistic assessments with expert-driven engineering analysis, resulting in improved accuracy in reliability evaluation. A system-level analysis is conducted across the main subsystems, including the sensing layer, AI processing modules, communication infrastructure, and robotic response units. The results indicate that the communication network and AI modules represent the most critical elements in terms of failure risk. The proposed methodology can be applied in the design, optimization, and management of intelligent security systems, contributing to enhanced robustness, reliability, and operational efficiency under real-world conditions.
Supporting Agencies
The authors would like to express their sincere gratitude to their colleagues from the Faculty of Technical Sciences at Konstantin Preslavsky University of Shumen for their valuable support, professional advice, scientific discussions, motivation, and cooperation during the preparation of this research. Their recommendations and constructive feedback contributed significantly to the development and improvement of the present study. This publication is funded by the fund “Support for Publishing Publications in Journals with Impact Factor (IF) and Impact Rank (SJR)” of Konstantin Preslavsky University of Shumen, Republic of Bulgaria.Downloads
References
[1] R. Kumar, J. Singh, and Y. K. Dwivedi, “Application of IoT and AI in smart surveillance systems: A systematic review,” Sustainable Cities and Society, vol. 70, 102889, 2021.
[2] X. Xu et al., “Edge–cloud collaborative intelligence for IoT systems,” Future Generation Computer Systems, vol. 128, pp. 1–12, 2022.
[3] C. Alcaraz and J. Lopez, “Cybersecurity in IoT-based smart systems: A review,” Computer Networks, vol. 185, 107731, 2021.
[4] V. Stoyanova, “Analysis of the public communication channels for transmission of hidden information,” in Proc. Int. Conf. Advanced Research and Technology for Defence (ARTDef), 2021, ISSN 2815-2581.
[5] Z. Chen, K. Zhang, and H. Li, “Reliability modeling of distributed AI systems in edge-cloud environments,” IEEE Internet of Things Journal, vol. 9, no. 8, pp. 5678–5690, 2022.
[6] S. Park and J. Kim, “Fault-tolerant architecture for AI-based surveillance systems using edge computing,” Future Generation Computer Systems, vol. 144, pp. 12–25, 2023.
[7] P. Singh and V. Sharma, “Fault tolerance in distributed IoT systems: A survey,” Computer Communications, vol. 182, pp. 1–15, 2022.
[8] Y. Zhang, M. Xie, and P. Wang, “Reliability analysis of complex systems using Bayesian networks and AI techniques,” Reliability Engineering & System Safety, vol. 210, 107530, 2021.
[9] X. Li, H. Chen, and L. Xu, “A hybrid reliability assessment method combining FMEA and Bayesian networks for intelligent systems,” IEEE Access, vol. 10, pp. 34567–34580, 2022.
[10] Y. Liu and X. Zhao, “Hybrid probabilistic models for reliability optimization in smart systems,” IEEE Systems Journal, vol. 17, no. 2, pp. 3456–3467, 2023.
[11] Q. Zhou et al., “Integrated FMEA and probabilistic risk analysis for intelligent systems,” Reliability Engineering & System Safety, vol. 232, 109054, 2023.
[12] Z. Wang and X. Chen, “Hybrid FMEA and Bayesian network for reliability assessment,” Safety Science, vol. 139, 105239, 2021.
[13] A. Gupta and S. Srivastava, “Failure mode and effect analysis in cyber-physical systems: A review,” Microprocessors and Microsystems, vol. 90, 104450, 2022.
[14] H. Liu et al., “A novel fuzzy FMEA approach for risk assessment in complex systems,” Applied Soft Computing, vol. 86, 105899, 2020.
[15] F. Alqahtani and A. Kumar, “Risk assessment of IoT-based smart systems using FMEA and machine learning,” Sensors, vol. 23, no. 4, 2156, 2023.
[16] T. Wang, Y. Zhao, and L. Sun, “A Markov-based reliability evaluation method for intelligent monitoring systems,” Applied Mathematical Modelling, vol. 89, pp. 1102–1115, 2021.
[17] B. Sun et al., “Reliability analysis of AI-enabled cyber–physical systems,” IEEE Systems Journal, vol. 16, no. 4, pp. 5890–5901, 2022.
[18] L. Zhang, X. Wu, and Y. Zhao, “Deep learning-based reliability modeling for complex systems,” IEEE Transactions on Reliability, vol. 72, no. 2, pp. 456–468, 2023.
[19] D. Kim and S. Lee, “Edge AI for real-time surveillance: Reliability and performance analysis,” IEEE Access, vol. 11, pp. 22345–22360, 2023.
[20] M. Hassan and S. Ali, “Integrated risk management in smart security systems using hybrid models,” Safety Science, vol. 147, 105621, 2022.
[21] T. Nguyen and B. Tran, “Reliability and availability analysis of cloud-based AI services,” Journal of Cloud Computing, vol. 10, no. 1, 45, 2021.
[22] M. Rahman, S. Islam, and M. Rahman, “AI-driven predictive maintenance for industrial IoT systems,” Computers in Industry, vol. 137, 103594, 2022.
[23] J. Torres and L. Martinez, “Reliability engineering in autonomous robotic systems: Challenges and solutions,” Robotics and Autonomous Systems, vol. 142, 103789, 2021.
[24] F. Rossi et al., “Reliability challenges in autonomous robotic systems,” Robotics and Autonomous Systems, vol. 171, 104593, 2024.
[25] S. Kuutti et al., “A survey of deep learning applications to autonomous vehicles,” IEEE Transactions on Intelligent Transportation Systems, vol. 22, no. 2, pp. 712–733, 2021.
[26] E. Zio, “The future of reliability engineering in the era of artificial intelligence,” Reliability Engineering & System Safety, vol. 215, 107849, 2021.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Silvia Nikolova, Tsvetoslav Tsankov
This work is licensed under a Creative Commons Attribution 4.0 International License.
