Human-Centric Smart Manufacturing under Industry 5.0:IIoT-Enabled Machine Learning for Real-Time Fault Identification and Adaptive Workforce Scheduling
DOI:
https://doi.org/10.4108/eetsis.13326Keywords:
rapid fault identification, XGBoost, personnel scheduling, manufacturing resilience, Industrial Internet of ThingsAbstract
This study addresses Industry 5.0's demand for human-machine collaboration and manufacturing resilience by developing machine learning models for rapid fault identification and adaptive personnel scheduling. When a production-line fault occurs, the proposed approach uses IIoT data to identify the fault category quickly, support targeted intervention, and facilitate the restoration of normal production. XGBoost achieved near-perfect fault identification accuracy in model evaluation and accuracy and recall of 1.0 in validation, significantly outperforming the Random Forest baseline. Analysis revealed that experienced operators increased product qualification rates by 15% but reduced output by 10% due to physical factors. Decision tree regression minimized scheduling errors with an MSE of 0.49 and an R2 of 0.83. These results demonstrate that integrating IIoT-driven rapid fault identification with intelligent staffing provides a practical basis for shortening the response cycle, improving recovery capability after disruptions, and strengthening the resilience of human-centric manufacturing systems.
References
[1] Paolanti M, Romeo L, Felicetti A, Mancini A, Frontoni E, Loncarski J. Machine learning approach for predictive maintenance in Industry 4.0. In: IEEE/ASME International Conference on Mechatronic and Embedded Systems and Applications; 2018. p. 1–6.
[2] Crespino AM, Corallo A, Lazoi M, Barbagallo D, Appice A, Malerba D. Anomaly detection in aerospace product manufacturing: Initial remarks. In: IEEE 2nd International Forum on Research and Technologies for Society and Industry Leveraging a Better Tomorrow; 2016. p. 1–4.
[3] Proto S, di Corso E, Apiletti D, Cagliero L, Cerquitelli T, Malnati G, mazzucchi D. REDTag: A predictive maintenance framework for parcel delivery services. IEEE Access. 2020;8:14953–14964.
[4] Stojanović D, Joković J, Tomašević I, et al. Algorithmic approach for the confluence of lean methodology and industry 4.0 technologies: Challenges, benefits, and practical applications. Journal of Industrial Intelligence. 2023;1(2):125–135.
[5] Gunasegaram DR, Barnard AS, Matthews MJ, Jared BH, Andreaco AM, Bartsch K, Murphy AB. Machine learning-assisted in-situ adaptive strategies for the control of defects and anomalies in metal additive manufacturing. Additive Manufacturing. 2024;82:104105.
[6] Kang Z, Catal C, Tekinerdogan B. Machine learning applications in production lines: A systematic literature review. Computers & Industrial Engineering. 2020;149:106773.
[7] Nakazawa T, Kulkarni DV. Anomaly detection and segmentation for wafer defect patterns using deep convolutional encoder-decoder neural network architectures in semiconductor manufacturing. IEEE Transactions on Semiconductor Manufacturing. 2019;32(2):250–256.
[8] Scime L, Siddel D, Baird S, Paquit V. Layer-wise anomaly detection and classification for powder bed additive manufacturing processes: A machine-agnostic algorithm for real-time pixel-wise semantic segmentation. Additive Manufacturing. 2020;36:101453.
[9] Aydemir G, Paynabar K. Image-based prognostics using deep learning approach. IEEE Transactions on Industrial Informatics. 2020;16(9):5956–5964.
[10] Liu W, Chen Z, Hu Y. XGBoost algorithm-based prediction of safety assessment for pipelines. Journal of Natural Gas Science and Engineering. 2020;73:103377.
[11] Zhang S, Zhu X, Anduv B, et al. Fault detection and diagnosis for the screw chillers using multi-region XGBoost model. Science and Technology for the Built Environment. 2021;27(5):608–623.
[12] Zhang C, Wang D, Song C, et al. Interpretable learning algorithm based on XGBoost for fault prediction in optical network. In: Optical Fiber Communications Conference and Exhibition; 2020. p. 1–3.
[13] Lu L, Zhang Y, Si Z, Dou Z. Research on anomaly detection of parts in workshop production line based on BO-XGBoostLSS. In: Advanced Intelligent Computing Technology and Applications; 2024. p. 282–291.
[14] Henriques J, Caldeira F, Cruz T, Simões P. Combining k-means and XGBoost models for anomaly detection using log datasets. Electronics. 2020;9(7):1164.
[15] Yu W, Dillon T, Mostafa F, Rahayu W, Liu Y. A global manufacturing big data ecosystem for fault detection in predictive maintenance. IEEE Transactions on Industrial Informatics. 2020;16(1):183–192.
[16] Sharma A, Aslekar A. IOT based predictive maintenance in Industry 4.0. In: International Interdisciplinary Humanitarian Conference for Sustainability; 2022. p. 143–145.
[17] Weber C, Reimann P. MMP - A platform to manage machine learning models in Industry 4.0 environments. In: IEEE 24th International Enterprise Distributed Object Computing Workshop; 2020. p. 91–94.
[18] Mrazovac B, Ilian V, Hulea M. Beyond Industry 4.0: Leveraging AI-powered anomalous sound detection for smart maintenance. In: Zooming Innovation in Consumer Technologies Conference; 2021. p. 43–47.
[19] Bozcan I, Korndorfer C, Madsen MW, Kayacan E. Score-based anomaly detection for smart manufacturing systems. IEEE/ASME Transactions on Mechatronics. 2022;27(6):5233–5242.
[20] Jeon K, Yoo D, Park J, Lee KD, Lee JJ, Kim CW. Reliability-based robust design optimization for maximizing the output torque of brushless direct current motors considering manufacturing uncertainty. Machines. 2022;10(9):797.
[21] Pang JL. Adaptive Fault Prediction and Maintenance in Production Lines Using Deep Learning. International Journal of Simulation Modelling. 2023;22(4):734–745.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Yaocong Xie, Ning Wang
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
This is an open access article distributed under the terms of the CC BY-NC-SA 4.0, which permits copying, redistributing, remixing, transformation, and building upon the material in any medium so long as the original work is properly cited.
