AI-Driven Predictive Maintenance for Packaging Automation
DOI:
https://doi.org/10.63503/acset.94Keywords:
Predictive Maintenance, Real-Time Fault Detection, Prediction Accuracy, Sensor Data Integration, Data Quality, ScalabilityAbstract
Predictive maintenance is beneficial across a variety of industries, including manufacturing, automotive, packaging and energy. In addition, this research provides an empirically based approach to predictive maintenance that combines new artificial intelligence technologies with traditional technologies. The new hybrid method combining XGBoost and DNN achieved the best performance, with an accuracy of 98.3%. This result is very innovative, as the XGBoost portion contains a lot of interaction structure-type data, while the DNN portion generates a deep learning, non-linear representation based on multiple datasets between both parts, able to fuse structured/and unstructured data based on the process of implicit fusion. This paper presents and tests a combined approach that leverages the strength of the XGBoost and DNN classifiers. The main new idea is to use XGBoost leaf embeddings rather than probability predictions, thereby providing rich structural information about decision paths within the ensemble.
References
[1] H. Wang, W. Zhang, D. Yang, and Y. Xiang, "Deep-Learning-Enabled Predictive Maintenance in Industrial Internet of Things: Methods, Applications, and Challenges," IEEE Syst J, vol. 17, no. 2, pp. 2602–2615, Jun. 2023, doi: 10.1109/JSYST.2022.3193200.
[2] H. M. Hashemian and W. C. Bean, "State-of-the-art predictive maintenance techniques," in IEEE Transactions on Instrumentation and Measurement, Oct. 2011, pp. 3480–3492. doi: 10.1109/TIM.2009.2036347.
[3]K. Shukla, S. Nefti-Meziani, and S. Davis, "A heuristic approach on predictive maintenance techniques: Limitations and scope," Jun. 01, 2022, SAGE Publications Inc. doi: 10.1177/16878132221101009.
[4]M. Sisode and M. Devare, "A Review on Machine Learning Techniques for Predictive Maintenance in Industry 4.0," 2023, pp. 774–783. doi: 10.2991/978-94-6463-136-4_67.
[5]2019 International Symposium on Systems Engineering (ISSE). IEEE, 2019.
[6]M. A. Amrani, M. Alhomdi, B. Aswaidy M, A. M. Ghaleb, M. Al-Qubati, and M. Shameeri, "Implementing an integrated maintenance management system for monitoring production lines: a case study for biscuit industry," J Qual Maint Eng, vol. 28, no. 1, pp. 180–196, Feb. 2022, doi: 10.1108/JQME-06-2020-0049.
[7]M. Achouch et al., "On Predictive Maintenance in Industry 4.0: Overview, Models, and Challenges," Aug. 01, 2022, MDPI. doi: 10.3390/app12168081.
[8]Z. M. Çinar, A. A. Nuhu, Q. Zeeshan, O. Korhan, M. Asmael, and B. Safaei, "Machine learning in predictive maintenance towards sustainable smart manufacturing in industry 4.0," Sustainability (Switzerland), vol. 12, no. 19, Oct. 2020, doi: 10.3390/su12198211.
[9]J. M. Fordal, P. Schjølberg, H. Helgetun, T. Ø. Skjermo, Y. Wang, and C. Wang, "Application of sensor data based predictive maintenance and artificial neural networks to enable Industry 4.0," Adv Manuf, vol. 11, no. 2, pp. 248–263, Jun. 2023, doi: 10.1007/s40436-022-00433-x.
[10]A. H. Juliet, "AI-Driven Predictive Maintenance for Industrial IoT with Real-Time Fault Detection and Prediction," in 2025 8th International Conference on Electronics, Materials Engineering and Nanotechnology, IEMENTech 2025, Institute of Electrical and Electronics Engineers Inc., 2025. doi: 10.1109/IEMENTech65115.2025.10959502.
[11]D. Zhong, Z. Xia, Y. Zhu, and J. Duan, "Overview of predictive maintenance based on digital twin technology," Apr. 01, 2023, Elsevier Ltd. doi: 10.1016/j.heliyon. 2023.e14534.
[12] S. Ma, K. A. Flanigan, and M. Bergés, "State-of-the-Art Review: The Use of Digital Twins to Support Artificial Intelligence-Guided Predictive Maintenance," Jun. 2024, [Online].
[13]E. Cinar, S. Kalay, and I. Saricicek, "A Predictive Maintenance System Design and Implementation for Intelligent Manufacturing," Machines, vol. 10, no. 11, Nov. 2022, doi: 10.3390/machines10111006.
[14]O. Motaghare, A. S. Pillai, and K. I. Ramachandran, "Predictive Maintenance Architecture," in 2018 IEEE International Conference on Computational Intelligence and Computing Research, ICCIC 2018, Institute of Electrical and Electronics Engineers Inc., Dec. 2018. doi: 10.1109/ICCIC.2018.8782406.
[15]T. Zhu, Y. Ran, X. Zhou, and Y. Wen, "A Survey of Predictive Maintenance: Systems, Purposes and Approaches," Mar. 2024, doi: 10.1109/COMST.2025.3567802.
[16]P. Nunes, J. Santos, and E. Rocha, "Challenges in predictive maintenance – A review," Feb. 01, 2023, Elsevier Ltd. doi: 10.1016/j.cirpj.2022.11.004
Downloads
Published
Conference Proceedings Volume
Section
License
Copyright (c) 2026 Adroid Conference Series: Engineering and Technology
This work is licensed under a Creative Commons Attribution 4.0 International License.
