Development of an Integrated Digital Twin Framework for Online Monitoring and Anomaly Detection
##plugins.themes.bootstrap3.article.main##
##plugins.themes.bootstrap3.article.sidebar##
Abstract
Digital Twins (DTs) are emerging as an important enabling technology in the nuclear field, as their development leverages the ongoing digitalization of nuclear systems and offers many advantages for optimizing nuclear operations. Nuclear DTs can be used for predictive maintenance, enhanced operations, improved scheduling, cradle-to-grave lifecycle management, decision support, and more. While the advantages are clear, continued DT development is needed, as many gaps remain, including technological and regulatory standardization, validation and verification, and digital-to-physical communication. To help close these gaps, a forced-water-flow experimental system at the University of Tennessee, Knoxville (UTK) was used to develop a complete, integrated DT, offering an end-to-end use case in the nuclear sector and related disciplines. For this work, a Long Short-Term Memory (LSTM) network was used for forecasting, and an interquartile range (IQR) LSTM hybrid method was used for anomaly detection. This was all interfaced with LabVIEW, enabling real-time data analysis and forecasting. A GUI was then created to provide the operator with a clear indication when a system anomaly is detected, enabling better insights during operation. The resulting platform demonstrates an end-to-end proof of concept for integrating data acquisition, machine learning-based forecasting and anomaly detection, and operator interaction within an experimental DT for various nuclear and related engineering systems.
##plugins.themes.bootstrap3.article.details##
anomaly detection, nuclear digital twin, time series forecasting, long short term memory network, digital twin framework
Attaran, M., & Celik, B. G. (2023). Digital Twin: Benefits, use cases, challenges, and opportunities. Decision Analytics Journal, 6, 100165. https://doi.org/10.1016/j.dajour.2023.100165
Bailey, L., Barr, R., Carnal, J., Clark, A., Copley, B., Petersen, J., Coble, J., & Zhao, X. (2025). Machine Learning for Time-Series Forecasting with Quantile Regression and Anomaly Detection. Transactions of the American Nuclear Society, 133 (Winter Meeting). https://doi.org/https://doi.org/10.13182/T133-49266
Bailey, L., Carnal, J., Coble, J., & Zhao, X. (2026). Correlation-Informed Time-Series Forecasting and Anomaly Detection. 2026 IEEE Aerospace Conference, 1–11. https://doi.org/10.1109/AERO66936.2026.11519810
Bandala, M., Chard, P., Cockbain, N., Dunphy, D., Eaves, D., Hutchinson, D., Lee, D., Ma, X., Marshall, S., Murray, P., Parker, A., Stirzaker, P., Taylor, C. J., Zabalza, J., & Joyce, M. J. (2024). Digital twin challenges and opportunities for nuclear fuel manufacturing applications. Nuclear Engineering and Design, 420, 113013. https://doi.org/10.1016/j.nucengdes.2024.113013
Barr, R., Bailey, L., & Zhao, X. (2026). Development of a Modelica-Based Physics Model for Digital Twin Implementation of a Three-Loop Flow System. ANS Student Conference.
Barricelli, B. R., Casiraghi, E., & Fogli, D. (2019). A Survey on Digital Twin: Definitions, Characteristics, Applications, and Design Implications. IEEE Access, 7, 167653–167671. https://doi.org/10.1109/ACCESS.2019.2953499
Bengio, Y., Simard, P., & Frasconi, P. (1994). Learning long-term dependencies with gradient descent is difficult. IEEE Transactions on Neural Networks, 5(2), 157–166. https://doi.org/10.1109/72.279181
Bowman, D., Dwyer, L., Levers, A., Patterson, E. A., Purdie, S., & Vikhorev, K. (2022). A Unified Approach to Digital Twin Architecture—Proof-of-Concept Activity in the Nuclear Sector. IEEE Access, 10, 44691–44709. https://doi.org/10.1109/ACCESS.2022.3161626
Crespi, N., Drobot, A. T., & Minerva, R. (Eds.). (2023). The Digital Twin. Springer International Publishing. https://doi.org/10.1007/978-3-031-21343-4
Dhee, K. (2023). Understanding the evolution of GPT: From encoder decoder to llms. Medium.
Gregory, C., Rabah, S., Chapurlat, V., Burčiar, F., & Herchlová, M. (2026). Leveraging model-based systems and software engineering for digital twin engineering: Methods and digital thread opportunities. Journal of Industrial Information Integration, 50, 101023. https://doi.org/10.1016/j.jii.2025.101023
Hochreiter, S., & Schmidhuber, J. (1997). Long Short-Term Memory. Neural Computation, 9(8), 1735–1780. https://doi.org/10.1162/neco.1997.9.8.1735
Huang, Q., Zeng, W., Liu, J., Zhang, Z., Deng, J., Qiu, Z., Xu, L., Wei, Z., Lu, Q., Gong, L., Shi, C., & Zhong, X. (2025). Shaping the future of nuclear reactors with digital twins: Current developments and perspectives. Applied Energy, 402, 126922. https://doi.org/10.1016/j.apenergy.2025.126922
Lussier, J., Hua, E. Y., Ledford, A., Thomas, D., Van Bossuyt, D. L., & Wooley, A. (2025). Differentiating Between Digital Twins and Control Systems for Complex Systems. Journal of Computing and Information Science in Engineering, 25(12), 120807. https://doi.org/10.1115/1.4070329
Martín-Suazo, S., Morón-López, J., Vakaruk, S., Karamchandani, A., Aguilar, J. A. P., Mozo, A., Gómez-Canaval, S., Vinyals, M., & Ortiz, J. M. (2024). Deep learning methods for multi-horizon long-term forecasting of Harmful Algal Blooms. Knowledge-Based Systems, 301, 112279. https://doi.org/10.1016/j.knosys.2024.112279
Mengyan, H., Xueyan, Z., Cuiting, P., Yixuan, Z., & Jun, Y. (2024). Current status of digital twin architecture and application in nuclear energy field. Annals of Nuclear Energy, 202, 110491. https://doi.org/10.1016/j.anucene.2024.110491
Ndum, Z. N., Lim, D., Ford, J., Adu, S., Tao, J., Hassan, Y., & Liu, Y. (2026). Large language model-assisted digital twin for remote monitoring and control of advanced reactors. Progress in Nuclear Energy, 192, 106172. https://doi.org/10.1016/j.pnucene.2025.106172
Nuclear Regulatory Commission (NRC). (2025). Digital Twins. Digital Twins. Nuclear Regulatory Commission. https://www.nrc.gov/reactors/power/digital-twins
Saha, S., Sarkar, J., Dhavala, S., Sarkar, S., & Mota, P. (2024). Quantile LSTM: A Robust LSTM for Anomaly Detection In Time Series Data. IEEE Transactions on Artificial Intelligence, 5(8), 3939–3950. https://doi.org/10.1109/TAI.2024.3353163
Zio, E., & Miqueles, L. (2024). Digital twins in safety analysis, risk assessment and emergency management. Reliability Engineering & System Safety, 246, 110040. https://doi.org/10.1016/j.ress.2024.110040