Low-Latency Industrial ML Models for Real-Time Digital Twin Synchronization

  • Authors

    • Dr. Rohit Malhotra Professor, University of Mumbai, India. Author
    • Dr. Sneha Banerjee Assistant Professor, Jadavpur University, India. Author

    DOI:

    https://doi.org/10.67228/3142788X/IJMLPA-2020PI1V4T

    Published 05-04-2020

  • Digital Twin, Low Latency, Real-Time Synchronization, Edge AI, Industrial IoT (IIoT), Machine Learning, Time-Series Forecasting, Lightweight Models, Predictive Maintenance, Cyber-Physical Systems

    Issue

    Vol. 3 No. 1 (2020)

    Section

    Articles

    How to Cite

    [1]
    R. Malhotra and S. Banerjee, “Low-Latency Industrial ML Models for Real-Time Digital Twin Synchronization”, IJMLPA, vol. 3, no. 1, pp. 01–11, May 2020, doi: 10.67228/3142788X/IJMLPA-2020PI1V4T.

  • Abstract

    Real-time synchronization between physical assets and their digital twins is crucial in Industry 4.0 for predictive maintenance, anomaly detection, and operational optimization. However, latency and model complexity often limit the efficacy of conventional machine learning approaches in high-frequency industrial settings. This paper proposes a framework for low-latency machine learning models optimized for real-time digital twin synchronization. By integrating edge computing, lightweight model architectures, and temporal data fusion techniques, we demonstrate significant improvements in synchronization fidelity and response time. We evaluate our approach across multiple industrial scenarios, including smart manufacturing and autonomous process control. Results show up to a 40% reduction in latency and improved predictive accuracy compared to baseline models, establishing a path forward for scalable, responsive, and resilient digital twin implementations.

  • References

    [1] Tao, F., Qi, Q., Liu, A., & Kusiak, A. (2018). Data-driven smart manufacturing. Journal of Manufacturing Systems, 48, 157–169. https://doi.org/10.1016/j.jmsy.2018.01.006

    [2] Lee, J., Bagheri, B., & Kao, H. A. (2015). A cyber-physical systems architecture for industry 4.0-based manufacturing systems. Manufacturing Letters, 3, 18–23. https://doi.org/10.1016/j.mfglet.2014.12.001

    [3] Zhang, H., Liu, Y., Tao, F., & Nee, A. Y. C. (2019). Digital twin in manufacturing: A review. Journal of Manufacturing Systems, 48, 34–60. https://doi.org/10.1016/j.jmsy.2019.01.003

    [4] Susto, G. A., Schirru, A., Pampuri, S., McLoone, S., & Beghi, A. (2015). Machine learning for predictive maintenance: A multiple classifier approach. IEEE Transactions on Industrial Informatics, 11(3), 812–820. https://doi.org/10.1109/TII.2014.2349359

    [5] Pfrommer, J., Hartmann, M., & Haneke, R. (2020). Towards low-latency edge intelligence: Combining microservices and TinyML. Procedia CIRP, 93, 501–506. https://doi.org/10.1016/j.procir.2020.04.087

    [6] Deng, L., Li, Z., & Han, S. (2020). Model compression and hardware acceleration for neural networks: A comprehensive survey. Proceedings of the IEEE, 108(4), 485–532. https://doi.org/10.1109/JPROC.2020.2976475

    [7] Shi, W., Cao, J., Zhang, Q., Li, Y., & Xu, L. (2016). Edge computing: Vision and challenges. IEEE Internet of Things Journal, 3(5), 637–646. https://doi.org/10.1109/JIOT.2016.2579198

    [8] Satyanarayanan, M. (2017). The emergence of edge computing. Computer, 50(1), 30–39. https://doi.org/10.1109/MC.2017.9

    [9] Lu, Y., & Xu, X. (2019). A semantic agent-based approach for manufacturing system reconfiguration. Robotics and Computer-Integrated Manufacturing, 57, 49–59. https://doi.org/10.1016/j.rcim.2018.11.007

    [10] Wang, S., Wan, J., Li, D., & Zhang, C. (2016). Implementing smart factory of Industrie 4.0: An outlook. International Journal of Distributed Sensor Networks, 12(1). https://doi.org/10.1155/2016/3159805.

  • Downloads