Abstract

Industry 4.0 has been advancing smart manufacturing through data-driven decision-making and the integration of autonomous systems. It is in this context that this research paper investigates how intelligent agents, used here as agentic AI, can be utilized to achieve significantly greater equipment reliability and working efficiency through predictive maintenance in the smart manufacturing environment. The emphasis is placed on predicting near-failure equipment and then optimizing the maintenance calendar accordingly. Intelligent agents, through constant monitoring of machine health, can filter large amounts of sensor telemetry data, identify anomalous patterns to failure, and propose automatic repairs. Early fixes eliminate unexpected downtime, reduce maintenance expenses, and extend the lifespan of critical machinery. The study utilizes an artificial data stream comprising sensor measures (temperature, vibration, current, and pressure), machine health, and failure over time. The dataset simulates a real smart factory scenario with various types of devices and their corresponding failure patterns. The program utilizes Python, the CrewAI library for agent development, Scikit-learn for machine learning training, and Pandas for data handling. The agents are developed to select from historical failure data and output operating parameters to predict remaining useful life (RUL) and trigger maintenance alerts with high precision. The study validates how agentic AI transforms traditional reactive maintenance into predictive, high-performance, and intelligent systems, making a significant contribution to the resilience and efficiency of new-generation manufacturing facilities.

References

• Y. Rizk, M. Awad, and E. W. Tunstel, "Decision Making in Multi-Agent Systems: A Survey," IEEE Trans. Cogn. Dev. Syst., vol. 11, pp. 1–13, 2018.
• M. Zouai, O. Kazar, B. Haba, H. Saouli, and H. Benfenati, "IoT Approach Using Multi-Agent System for Ambient Intelligence," Int. J. Softw. Eng. Its Appl., vol. 11, pp. 15–32, 2017.
• S. Mohamed, K. Sethom, and A. J. Obaid, "IoT-based personalized products recommendation system," J. Phys. Conf. Ser., vol. 1963, pp. 012–088, 2021.
• O. K. Pal, S. H. Shovon, M. F. Mridha, and J. Shin, "In-Depth Review of AI-Enabled Unmanned Aerial Vehicles: Trends, Vision, and Challenges," Discov. Artif. Intell., vol. 4, p. 209, 2024.
• Y.-C. Huang, T.-Y. Cheng, and B.-T. Chie, "The Effect of Dishonest Sellers on E-commerce: An Agent-Based Modeling Approach," Adv. Manag. Appl. Econ., vol. 12, pp. 93–108, 2022.
• J. Zhang, L. Jin, and C. Yang, "Distributed Cooperative Kinematic Control of Multiple Robotic Manipulators with Improved Communication Efficiency," IEEE/ASME Trans. Mechatron., vol. 26, pp. 2433–2444, 2021.
• S. Forouzandeh, A. Rezaei Aghdam, M. Barkhordari, S. A. Fahimi, M. K. Vayqan, S. Forouzandeh, and E. G. Khani, "Recommender system for users of internet of things (IoT)," Int. J. Comput. Sci. Netw. Secur., vol. 17, pp. 46–51, 2017.
• L. A. Silva, H. Sanchez San Blas, D. Peral García, A. Sales Mendes, and G. Villarubia González, "An Architectural Multi-Agent System for a Pavement Monitoring System with Pothole Recognition in UAV Images," Sensors, vol. 20, p. 6205, 2020.
• J. Park, H. A. Rahman, J. Suh, and H. Hussin, "A study of integrative bargaining model with argumentation-based negotiation," Sustainability, vol. 11, p. 6832, 2019.
• J. Johnson, "Artificial Intelligence, Drone Swarming and Escalation Risks in Future Warfare," J. Strateg. Stud., vol. 43, pp. 547–563, 2020.
• T. H. Noor, A. M. Almars, A. El-Sayed, and A. Noor, "Deep learning model for predicting consumers’ interests of IoT recommendation system," Int. J. Adv. Comput. Sci. Appl., vol. 13, pp. 161–170, 2022.
• N. Luo, "Innovation of E-Commerce Development Model under the Background of Artificial Intelligence and Wireless Communication," Wirel. Commun. Mob. Comput., vol. 1, p. 8572911, 2022.
• K. Telli, O. Kraa, Y. Himeur, A. Ouamane, M. Boumehraz, S. Atalla, and W. Mansoor, "A Comprehensive Review of Recent Research Trends on Unmanned Aerial Vehicles (UAVs)," Syst. J., vol. 11, p. 400, 2023.