Integrated Digital Twin and Physics Informed Machine Learning Model for Real Time Performance Prediction of Industrial Mechanical Systems
DOI:
https://doi.org/10.61132/ijmicse.v2i2.404Keywords:
Digital Twin, Industry 4.0, Machine Monitoring, Physics Informed Learning, Predictive MaintenanceAbstract
Background: The rapid advancement of digital technologies in the Industry 4.0 era has transformed industrial mechanical systems into highly interconnected and data driven environments through the integration of sensors, the Internet of Things (IoT), data analytics, and cyber physical systems. This increasing complexity requires more adaptive and accurate monitoring and prediction methods than conventional simulation approaches, which often face limitations in capturing real time dynamic system behavior. Objective: This study aims to develop a predictive performance model for industrial mechanical systems by integrating Digital Twin technology with Physics Informed Machine Learning in order to improve monitoring accuracy and support predictive maintenance strategies. Methods: This research adopts a data driven modeling and simulation approach by developing a digital representation of an industrial mechanical system that is connected to real time sensor data. The prediction model is constructed using a Physics Informed Neural Network (PINN), which integrates operational data with physical principles governing system dynamics. The research process includes the development of a Digital Twin model, integration of sensor data, training of the PINN model, model validation using experimental data, and evaluation of prediction performance using statistical metrics. Results: The results indicate that the integration of Digital Twin technology and PINN significantly improves the prediction accuracy of industrial mechanical system performance compared with conventional simulation methods and purely data driven machine learning models. The proposed model is capable of representing system dynamics more consistently, accurately following sensor data patterns, and providing strong potential for supporting machine condition monitoring and predictive maintenance strategies in modern industrial environments.
References
Anadkat, D., Dave, A., Sata, A., Shukla, M., & Jarboui, S. (2024). Digital twinning of vertical centrifugal casting. Concurrent Engineering Research and Applications, 32(1-4), 78-89. https://doi.org/10.1177/1063293X241296463
Arwoko, D. S., Baniara, Y., Raharjo, T., & Yossy, E. H. (2023). Development health machine of heavy equipment condition monitoring system. In 2023 IEEE 9th International Conference on Computing, Engineering and Design (ICCED). https://doi.org/10.1109/ICCED60214.2023.10425104
Barreto, N. E. M., & Aoki, A. R. A. (2025). Cyber-physical power system digital twins: A study on the state of the art. Energies, 18(22), 5960. https://doi.org/10.3390/en18225960
Cronrath, C., Ekstrom, L., & Lennartson, B. (2020). Formal properties of the digital twin-Implications for learning, optimization, and control. In IEEE International Conference on Automation Science and Engineering (pp. 679-684). https://doi.org/10.1109/CASE48305.2020.9216822
Doumèche, N., Bach, F., Biau, G., & Boyer, C. (2025). Physics-informed kernel learning. Journal of Machine Learning Research, 26.
Falekas, G., Palaiologou, I., Kolidakis, Z., & Karlis, A. (2024). Digital twin applications in electrical machines diagnostics. In Handbook of Digital Twins (pp. 531-548). CRC Press. https://doi.org/10.1201/9781003425724-37
Feng, H., Hu, P., Wang, Y., Fan, D., Wu, T., & Zhang, Y. (2025). Physics-informed super-resolution and forecasting method based on inaccurate partial differential equations and partial observation. Physics of Fluids, 37(6), 66625. https://doi.org/10.1063/5.0276721
Gandikota, R. A., Chennoufi, N., & Hadad, T. (2024). Digital twins revolutionizing oil and gas industry optimizing drilling operations with physics informed AI. In Society of Petroleum Engineers -- ADIPEC 2024. https://doi.org/10.2118/222587-MS
Gardner, P., Dal Borgo, M., Ruffini, V., Hughes, A. J., Zhu, Y., & Wagg, D. J. (2020). Towards the development of an operational digital twin. Vibration, 3(3), 235-265. https://doi.org/10.3390/vibration3030018
Henriques, J. P. C., et al. (2022). Industrial nonlinear system validation using digital twins. In Proceedings of the 10th International Conference on Control, Mechatronics and Automation (ICCMA) (pp. 266-270). https://doi.org/10.1109/ICCMA56665.2022.10011611
Herrera-Vidal, G., Coronado-Hernández, J. R., & Maheut, J. (2025). Complexity management challenges in the Industry 4.0 era: A systematic review in production systems. Results Engineering, 26, 105329. https://doi.org/10.1016/j.rineng.2025.105329
Karve, P. M., Guo, Y., Kapusuzoglu, B., Mahadevan, S., & Haile, M. A. (2020). Digital twin approach for intelligent operation planning and health management of mechanical systems. In Proceedings of the Annual Conference of the Prognostics and Health Management Society. https://doi.org/10.36001/phmconf.2020.v12i1.1197
Korovin, G. (2022). Digital twins in the industry: Maturity, functions, effects. In Lecture Notes in Information Systems and Organisation, 54 (pp. 1-12). Springer Science and Business Media Deutschland GmbH. https://doi.org/10.1007/978-3-030-94617-3_1
Leong, W. Y. (2025). Digital twin models for real-time failure prediction in industrial machinery. ASM Science Journal, 20(1), 1-8. https://doi.org/10.32802/asmscj.2025.1923
Li, F., et al. (2020). Review of real-time simulation of power electronics. Journal of Modern Power Systems and Clean Energy, 8(4), 796-808. https://doi.org/10.35833/MPCE.2018.000560
Li, H., et al. (2021). Concept, system structure and operating mode of industrial digital twin system. Computational Integration and Manufacturing Systems, 27(12), 3373-3390. https://doi.org/10.13196/j.cims.2021.12.001
Mîndra, T., & Anghel, A. M. (2024). Cyber-physical perception interface for co-simulation applications. Sensors, 24(19), 6412. https://doi.org/10.3390/s24196412
Nghiem, T. X., et al. (2023). Physics-informed machine learning for modeling and control of dynamical systems. In Proceedings of the American Control Conference (pp. 3735-3750). https://doi.org/10.23919/ACC55779.2023.10155901
Nguyen, T. T., Hooshyar, H., & Kadavil, R. (2023). A real-time cyber-physical simulation testbed for cybersecurity assessment of power systems. In IEEE Industry Applications Society Annual Meeting. https://doi.org/10.1109/IAS54024.2023.10406799
Nguyen, T. T., Kadavil, R., & Hooshyar, H. (2024). A real-time cyber-physical simulation testbed for cybersecurity assessment of large-scale power systems. IEEE Transactions on Industry Applications, 60(6), 8329-8340. https://doi.org/10.1109/TIA.2024.3457877
Pateras, J., Rana, P., & Ghosh, P. (2023). A taxonomic survey of physics-informed machine learning. Applied Sciences, 13(12), 6892. https://doi.org/10.3390/app13126892
Peralta, M. E. (2022). Sustainable and fractal manufacturing systems: Complexity minimization when sustainability and Industry 4.0 interact. In Innovation and Sustainable Manufacturing: Research and Development (pp. 1-27). Elsevier. https://doi.org/10.1016/B978-0-12-819513-0.00008-1
Rojas, L., Yepes, V., & Garcia, J. (2025). Complex dynamics and intelligent control: Advances, challenges, and applications in mining and industrial processes. Mathematics, 13(6), 961. https://doi.org/10.3390/math13060961
Roquemen-Echeverri, V., & Mosquera-Lopez, C. (2025). Recent advancements and applications of physics-informed machine learning in biomedical research. Current Opinion in Biomedical Engineering, 35, 100612. https://doi.org/10.1016/j.cobme.2025.100612
Rosen, K. M., & Pattipati, K. R. (2023). Operating digital twins within an enterprise process. In The Digital Twin (pp. 599-659). Springer International Publishing. https://doi.org/10.1007/978-3-031-21343-4_22
Shukla, K., Xu, M., Trask, N., & Karniadakis, G. E. (2022). Scalable algorithms for physics-informed neural and graph networks. Data-Centric Engineering, 3, e24. https://doi.org/10.1017/dce.2022.24
Srilalitha, T. S., Gavekar, V. S., Lahoti, Y., Selvakumar, P., Gupta, P. K., & Manjunath, T. C. (2025). The role of artificial intelligence and machine learning in simulations. In Navigating Simulations in Marketing for Strategic Success (pp. 349-376). IGI Global. https://doi.org/10.4018/979-8-3373-3141-6.ch012
Sun, P., Liu, K., & Qi, D. (2020). Cyber security simulation based on real-time simulation platform of cyber-physical power system. Electrical Power Construction, 41(2), 40-46.
Tronci, E. M., Downey, A. R. J., Mehrjoo, A., Chowdhury, P., & Coble, D. (2025). Physics-informed machine learning part I: Different strategies to incorporate physics into engineering problems. In Conference Proceedings of the Society for Experimental Mechanics Series (pp. 1-6). https://doi.org/10.1007/978-3-031-68142-4_1
Vidyalakshmi, G., Gopikrishnan, S., Boulila, W., Koubaa, A., & Srivastava, G. (2025). Digital twins and cyber-physical systems: A new frontier in computer modeling. Computational Model Engineering Science, 143(1), 51-113. https://doi.org/10.32604/cmes.2025.057788
Wu, Z., Wang, H., He, C., Zhang, B., Xu, T., & Chen, Q. (2023). The application of physics-informed machine learning in multiphysics modeling in chemical engineering. Industrial Engineering and Chemistry Research, 62(44), 18178-18204. https://doi.org/10.1021/acs.iecr.3c02383
Xu, Y., Qamsane, Y., Puchala, S., Januszczak, A., Tilbury, D. M., & Barton, K. (2024). A data-driven approach toward a machine- and system-level performance monitoring digital twin for production lines. Computers in Industry, 157-158, 104086. https://doi.org/10.1016/j.compind.2024.104086
Ye, Y., & Lu, H. (2021). Research on the monitoring of the industrial robot motion based on digital twins. In Proceedings of the 2021 International Conference on Networking, Communications and Information Technology (NetCIT) (pp. 377-381). https://doi.org/10.1109/NetCIT54147.2021.00082
Zia, M. S., Houpert, C., Anjum, A., Liu, L., Conway, A., & Peña-Rios, A. (2025). Physics encoded blocks in residual neural network architectures for digital twin models. Machine Learning, 114(8), Article 180. https://doi.org/10.1007/s10994-025-06808-y
Published
How to Cite
Issue
Section
License
Copyright (c) 2025 International Journal of Mechanical, Industrial and Control Systems Engineering
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
