Engineering and Technology
| Open Access | An Edge-AI-Based Anomaly Detection Framework for Securing Industrial IoT and Cyber-Physical Manufacturing Systems
Abstract
The convergence of Industrial Internet of Things (IIoT), artificial intelligence, automation, and cyber-physical systems (CPS) is transforming manufacturing into highly connected and intelligent production environments. However, increased connectivity also expands the attack surface and creates a requirement for security mechanisms capable of identifying anomalous behavior with low latency. Conventional centralized security architectures may introduce communication overhead, delayed responses, and dependency on continuous connectivity with cloud infrastructure. This paper proposes an Edge-AI-Based Anomaly Detection Framework for securing IIoT and cyber-physical manufacturing systems. The proposed framework places lightweight artificial intelligence inference capabilities close to industrial data sources, enabling continuous analysis of sensor, machine, process, and network observations. A layered architecture comprising data acquisition, preprocessing, edge intelligence, anomaly scoring, decision enforcement, and centralized coordination is developed conceptually. The methodology integrates contextual process behavior with machine-learning-based anomaly identification to distinguish operational deviations from potentially malicious activities. The literature synthesis demonstrates that intelligent agriculture, computational intelligence, and IoT-enabled management systems provide useful foundations for distributed sensing, intelligent decision-making, and real-time analytics, although these studies do not directly address the security requirements of industrial CPS. The proposed framework therefore extends these principles toward security-oriented edge intelligence. Findings indicate that edge-based detection can improve responsiveness, reduce unnecessary data transmission, and support localized decision-making, while introducing challenges related to resource constraints, model maintenance, false positives, and heterogeneous industrial environments. The framework provides a research-oriented foundation for deploying explainable, low-latency anomaly detection in next-generation smart manufacturing environments.
Keywords
Edge AI, Industrial IoT, anomaly detection, cyber-physical systems
References
Cainthus. (2019). Combining Computer Vision and Arti cial Intelli gence. Accessed: Aug. 21, 2019. [Online]. Available: https://www. cainthus.com/technology
J. Deere. (2019). AutoTrac Agricultural Management Solutions (AMS). Accessed: Aug. 21, 2019. [Online]. Available: https://www.deere.co.uk/en/ agricultural management-solutions/guidance automation/autotrac/
Y. Chen and Y. Li, Computational Intelligence Assisted Design (In Industrial Revolution 4.0). Boca Raton, FL, USA: CRC Press, 2018. [Online]. Available: 60676 https://www.taylorfrancis.com/books/97814987
L.Karthikeyan,I.Chawla,andA.K.Mishra,‘‘Areviewofremotesensing applications in agriculture for food security: Crop growth and yield, irri gation, and crop losses,’’ J. Hydrol., vol. 586, Jul. 2020, Art. no. 124905, doi:10.1016/j.jhydrol.2020.124905.
G.S. Nagaraja,A.B. Soppimath,T .Soumya ,and A. Abhinith, IoTbased smart agriculture management system, in Proc. 4th Int. Conf. Comput. Syst. Inf. Technol. Sustain. Solution (CSITSS), Dec. 2019, pp. 1 5, doi: 10.1109/CSITSS47250.2019.9031025.
M. M. Tahat, K. M. Alananbeh, Y. A. Othman, and D. I. Leskovar, ‘‘Soil health and sustainable agriculture,’’ Sustainability, vol. 12, no. 12, p. 4859, Jun. 2020, doi: 10.3390/su12124859.
E. Siddhartha and M. C. Lakkannavar, Smart irrigation and crop health prediction, in Proc. Int. Conf. Recent Trends Electron., Inf., Com mun. Technol. (RTEICT), Aug. 2021, pp. 739742, doi: 10.1109/RTE ICT52294.2021.9573542.
United Nation Global Population Growth and Sustainable Development. Accessed: Apr. 11, 2022. [Online]. Available: https://www.un.org/ development/desa/pd/sites/www.un.org.development.desa.pd/ les/ undesa_pd_2022_global_population_growth
PwC. Arti cial Intelligence Could Add 232bn to UK GDP by 2030. Accessed: Jun. 28, 2017. [Online]. Available: https://www.pwc.co.uk/ press-room/press-releases/arti cial-intelligence could-add-232bn-to-UK gdp.html
WIPO Technology Trends 2019: Arti cial Intelligence, World Intellectual Property Org., Geneva, Switzerland, 2019.
Govindarajan, V., Ahmed, F., Faheem, Z. B., Bilal, M., Ayadi, M., & Ali, J. (2026). Aegis-5: A Hybrid Ensemble Framework for Intrusion Detection in Industry 5.0 Driven Smart Manufacturing Environment. ACM Transactions on Autonomous and Adaptive Systems.
Ramamurthy, K., Gumber, S., Abdelfattah, W.M. et al. Human AI trust modeling in cognitive systems via ensemble learning and advanced feature engineering. Discov Artif Intell 6, 366 (2026). https://doi.org/10.1007/s44163-026-01255-7
Geo Philip, Paulson, Robotics-Enabled Sustainable Construction Management: A Socio-Technical Framework for Operational Efficiency, Digital Integration, and Sustainability Performance. Available at SSRN: https://ssrn.com/abstract=6845167 or http://dx.doi.org/10.2139/ssrn.6845167
Download and View Statistics
Copyright License
Copyright (c) 2026 Dr. Aditya Pratama, Dr. Siti Rahmawati
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors retain the copyright of their manuscripts, and all Open Access articles are disseminated under the terms of the Creative Commons Attribution License 4.0 (CC-BY), which licenses unrestricted use, distribution, and reproduction in any medium, provided that the original work is appropriately cited. The use of general descriptive names, trade names, trademarks, and so forth in this publication, even if not specifically identified, does not imply that these names are not protected by the relevant laws and regulations.