Deep Learning–Based Real-Time Fault Detection in Networked Cyber-Physical Systems Using Embedded Edge Devices
DOI:
https://doi.org/10.63503/j.ijcma.2026.256Keywords:
Cyber-Physical Systems, Fault Detection, Deep Learning, Edge Computing, Real-Time Monitoring, Adaptive SystemsAbstract
The paper proposes a deep learning-based framework for real-time fault detection in the networked structure of cyber-physical systems (CPS), using embedded edge devices. The suggested method combines multi-modal sensor data fusion with lightweight neural models and an adaptive feedback mechanism, enabling efficient on-device inference in dynamic situations. According to the experimental analysis of CPS benchmarks for detection accuracy, latency, and energy consumption, there is a +19.3 % improvement in detection accuracy, a -18.6 % decrease in latency, and a -13.1 % decrease in energy consumption relative to the baseline models. Moreover, there are system reliability gains of +21.8%, giving it resilience in the noisy and time-sensitive environment. Scalable deployment in industrial automation, smart grids, and autonomous systems is supported by the architecture, which has low computational overhead. These findings substantiate the claim that deep learning with edge computing can be significantly more responsive, flexible and energy-efficient for real-time CPS fault detection.
References
[1] Zhang, K., Shi, Y., Karnouskos, S., Sauter, T., Fang, H., & Colombo, A. W. (2022). Advancements in industrial cyber-physical systems: An overview and perspectives. IEEE Transactions on Industrial Informatics, 19(1), 716-729. https://doi.org/10.1109/TII.2022.3199481
[2] Boi-Ukeme, J., Ruiz-Martin, C., & Wainer, G. (2020, December). Real-time fault detection and diagnosis of CPS faults in DEVS. In 2020 IEEE 6th International Conference on Dependability in Sensor, Cloud and Big Data Systems and Application (DependSys) (pp. 57-64). IEEE. https://doi.org/10.1109/DependSys51298.2020.00017
[3] Kathiravelu, P., Van Roy, P., & Veiga, L. (2019). SD-CPS: software-defined cyber-physical systems. Taming the challenges of CPS with workflows at the edge. Cluster Computing, 22(3), 661-677.doi: 10.1007/s10586-018-2874-8
[4] Zhou, X., Yang, Z., Ni, M., Lin, H., Li, M., & Tang, Y. (2020). Analysis of the impact of combined information-physical-failure on distribution network CPS. IEEE Access, 8, 44140-44152. https://doi.org/10.1109/ACCESS.2020.2978113
[5] Zhao, H., Liu, H., Hu, W., & Yan, X. (2018). Anomaly detection and fault analysis of wind turbine components based on deep learning network. Renewable energy, 127, 825-834. https://doi.org/10.1016/j.renene.2018.05.024
[6] Sheela, K. S., Pavithra, A., Jeevanandham, S., Sundarrajan, M., & Choudhry, M. D. (2025, December). Multi-Sensor Data Fusion with Explainable AI for Anomaly Detection in Industrial CPS. In 2025 First International Conference of Advances in Engineering and Computing Technologies for Sustainable Development (AECTSD) (pp. 1-6). IEEE. https://doi.org/10.1109/AECTSD65988.2025.11410609
[7] Zhang, J., Yang, S., Yang, Y., Yuan, Y., & Wang, X. (2026). A Hybrid Forecasting Framework with Adaptive Parameter Optimization and Multi-Scale Feature Fusion for Non-Stationary Power Grid CPS Time Series. Journal of Electrical Engineering & Technology, 1-22.doi: 10.1007/s42835-025-02580-0
[8] Zhang, N. (2021). A cloud-based platform for big data-driven cps modeling of robots. IEEE Access, 9, 34667-34680. https://doi.org/10.1109/ACCESS.2021.3061477
[9] Funchal, G., Pedrosa, T., De la Prieta, F., & Leitão, P. (2026). A Cloud-Driven Support Layer for Enhancing Distributed IDS in IoT Networks. SN Computer Science, 7(2), 186.doi: 10.1007/s42979-026-04750-x
[10] Cao, K., Hu, S., Shi, Y., Colombo, A. W., Karnouskos, S., & Li, X. (2021). A survey on edge and edge-cloud computing assisted cyber-physical systems. IEEE Transactions on Industrial Informatics, 17(11), 7806-7819. https://doi.org/10.1109/TII.2021.3073066
[11] Selvi, G. V., & Kumari, V. S. (2026). Edge AI: Transforming Real-Time Decision-Making in the Internet of Energy. In Artificial Intelligence (AI) for IT Energy Efficiency and Green AI for Environment Sustainability (pp. 539-564). Cham: Springer Nature Switzerland.doi: 10.1007/978-3-031-89420-6_26
[12] Elsayed, R., Ismail, M. I., Ashour, A. F., Sakr, H. A., Ibrahem, M. I., & Fouda, M. M. (2025, September). A Review of Smart Building Management Systems: CPS Applications for Energy-Efficient Monitoring and Control. In 2025 3rd International Conference on Artificial Intelligence, Blockchain and Internet of Things (AIBThings) (pp. 1-6). IEEE. https://doi.org/10.1109/AIBThings66987.2025.11296174
[13] Fezai, R., Dhibi, K., Mansouri, M., Trabelsi, M., Hajji, M., Bouzrara, K., ... & Nounou, M. (2020). Effective random forest-based fault detection and diagnosis for wind energy conversion systems. IEEE Sensors Journal, 21(5), 6914-6921. https://doi.org/10.1109/JSEN.2020.3037237
[14] Ruan, H., Dorneanu, B., Arellano-Garcia, H., Xiao, P., & Zhang, L. (2022). Deep learning-based fault prediction in wireless sensor network embedded cyber-physical systems for industrial processes. Ieee Access, 10, 10867-10879. https://doi.org/10.1109/ACCESS.2022.3144333
[15] Cui, J., Long, J., Min, E., Liu, Q., & Li, Q. (2018, June). Comparative study of CNN and RNN for deep learning based intrusion detection system. In International Conference on Cloud Computing and Security (pp. 159-170). Cham: Springer International Publishing.doi: 10.1007/978-3-030-00018-9_15
[16] Qiu, T., Chi, J., Zhou, X., Ning, Z., Atiquzzaman, M., & Wu, D. O. (2020). Edge computing in the industrial internet of things: Architecture, advances and challenges. IEEE communications surveys & tutorials, 22(4), 2462-2488. https://doi.org/10.1109/COMST.2020.3009103
[17] Mittal, P. (2024). A comprehensive survey of deep learning-based lightweight object detection models for edge devices. Artificial Intelligence Review, 57(9), 242.doi: 10.1007/s10462-024-10877-1
[18] Malaraju, S. K., & Madishetty, S. K. (2025, November). AI-Augmented Compiler Optimization for Energy Efficient Software Execution on Embedded Systems. In 2025 14th International Conference on System Modeling & Advancement in Research Trends (SMART) (pp. 1-6). IEEE. https://doi.org/10.1109/SMART66937.2025.11389313
[19] Lilhore, U. K., Simaiya, S., Sharma, Y. K., Rai, A. K., Padmaja, S. M., Nabilal, K. V., ... & Alsufyani, H. (2025). Cloud-edge hybrid deep learning framework for scalable IoT resource optimization. Journal of Cloud Computing, 14(1), 5.doi: 10.1186/s13677-025-00729-w
[20] Olowononi, F. O., Rawat, D. B., & Liu, C. (2020). Resilient machine learning for networked cyber physical systems: A survey for machine learning security to securing machine learning for CPS. IEEE Communications Surveys & Tutorials, 23(1), 524-552.doi: https://doi.org/10.1109/COMST.2020.3036778
[21] Tumkur, S. D., Iyer, J., & Kurra, S. B. (2025, November). Explainable Multi-Modal Deep Learning Framework for Enhancing Cyber-Physical Systems Security. In 2025 IEEE 12th International Conference on Cyber Security and Cloud Computing (CSCloud) (pp. 48-55). IEEE. https://doi.org/10.1109/CSCloud66326.2025.00015
[22] Marino, R., Wisultschew, C., Otero, A., Lanza-Gutierrez, J. M., Portilla, J., & De la Torre, E. (2020). A machine-learning-based distributed system for fault diagnosis with scalable detection quality in industrial IoT. IEEE Internet of Things Journal, 8(6), 4339-4352. https://doi.org/10.1109/JIOT.2020.3026211
