Domain Adaptation for Fault Detection in Civil Nuclear Plants

##plugins.themes.bootstrap3.article.main##

##plugins.themes.bootstrap3.article.sidebar##

Published Jun 27, 2024
Henry Wood Felipe Montana Visakan Kadirkamanathan Andy Mills Will Jacobs

Abstract

Recent domain adaptation approaches have been shown to generalise well between distant data domains achieving high performance in machine fault detection through time series classification. An interesting aspect of this transfer-learning inspired approach, is that the algorithm need not be exposed to fault data from the target domain during training. This promotes the application of these methods to environments in which fault data is unfeasible to obtain, such as the detection of loss-of-coolant accidents (LOCA) in nuclear power plants (NPPs). A LOCA is a failure mode of a nuclear reactor in which coolant is lost due to a physical break in the primary coolant circuit. If undetected, or not managed effectively, a LOCA can result in reactor core damage. Three high-fidelity physics based models were created with divergent behaviour that represent different data domains. The first model is used to generate source domain data by simulating labelled training data under both nominal and LOCA conditions. The second and third models act as surrogates of real plants and are used to generate target domain data, i.e. to simulate nominal data for training and LOCA condition data for validation. Several deep-learning feature encoders (with varying levels of connectivity) were applied to this LOCA detection problem. Among these, a ’Baseline’ encoder was used to quantify the improvement that domain adaptation techniques make to LOCA detection performance under large domain divergences. Classification accuracy for each model is explored within the context of LOCA break size and location within each plant model. The proposed method for LOCA detection demonstrates how the dependence upon sparse accident-specific data can be alleviated through the use of domain adaptation. Detection capability of the LOCA condition is maintained even when no data examples are available in the target domain.

How to Cite

Wood, H., Montana, F., Kadirkamanathan, V., Mills, A., & Jacobs, W. (2024). Domain Adaptation for Fault Detection in Civil Nuclear Plants. PHM Society European Conference, 8(1), 11. https://doi.org/10.36001/phme.2024.v8i1.4076
Abstract 177 | PDF Downloads 91

##plugins.themes.bootstrap3.article.details##

Keywords

Domain Adaptation, Transfer Learning, Fault Detection, Time-series classification, Nuclear Power Plants, Loss Of Coolant Accident

References
Aldemir, T. (2013). A survey of dynamic methodologies for probabilistic safety assessment of nuclear power plants. Annals of Nuclear Energy, 52, 113-124. (Nuclear Reactor Safety Simulation and Uncertainty Analysis)
Chen, J., Wang, J., Zhu, J., Lee, T. H., & de Silva, C. W. (2021). Unsupervised cross-domain fault diagnosis using feature representation alignment networks for rotating machinery. IEEE/ASME Transactions on Mechatronics, 26(5), 2770-2781.
Farber, J. A., & Cole, D. G. (2020). Detecting loss-of-coolant accidents without accident-specific data. Progress in Nuclear Energy, 128, 103469.
Gomez-Fernandez, M., Higley, K., Tokuhiro, A., Welter, K., Wong, W.-K., & Yang, H. (2020). Status of research and development of learning-based approaches in nuclear science and engineering: A review. Nuclear Engineering and Design, 359, 110479.
Ismail Fawaz, H., Forestier, G., Weber, J., Idoumghar, L., & Muller, P.-A. (2019, March). Deep learning for time series classification: a review. Data Mining and Knowledge Discovery, 33(4), 917–963.
Lee, G., Lee, S. J., & Lee, C. (2021). A convolutional neural network model for abnormality diagnosis in a nuclear power plant. Applied Soft Computing, 99, 106874.
Mahmoodi, R., Shahriari, M., Zolfaghari, A., & Minuchehr, A. (2011). An advanced method for determination of loss of coolant accident in nuclear power plants. Nuclear Engineering and Design, 241(6), 2013-2019. ((W3MDM) University of Leeds International Symposium: What Where When? Multi-dimensional Advances for Industrial Process Monitoring)
Qian, Q., Qin, Y., Luo, J., Wang, Y., & Wu, F. (2023). Deep discriminative transfer learning network for cross-machine fault diagnosis. Mechanical Systems and Signal Processing, 186, 109884.
Rivas, A., Delipei, G. K., Davis, I., Bhongale, S., & Hou, J. (2024). A system diagnostic and prognostic framework based on deep learning for advanced reactors. Progress in Nuclear Energy, 170, 105114.
Sakurahara, T., O’Shea, N., Cheng, W.-C., Zhang, S., Reihani, S., Kee, E., & Mohaghegh, Z. (2019). Integrating renewal process modeling with probabilistic physics-of-failure: Application to loss of coolant accident (loca) frequency estimations in nuclear power plants. Reliability Engineering & System Safety, 190, 106479.
Wang, H., jun Peng, M., Ayodeji, A., Xia, H., kun Wang, X., & kang Li, Z. (2021). Advanced fault diagnosis method for nuclear power plant based on convolutional gated recurrent network and enhanced particle swarm optimization. Annals of Nuclear Energy, 151, 107934.
Wei, L., & Keogh, E. (2006). Semi-supervised time series classification. In Proceedings of the 12th acm sigkdd international conference on knowledge discovery and data mining (p. 748–753). New York, NY, USA: Association for Computing Machinery.
Zhang, J., Li, X., Tian, J., Jiang, Y., Luo, H., & Yin, S. (2023). A variational local weighted deep sub-domain adaptation network for remaining useful life prediction facing cross-domain condition. Reliability Engineering & System Safety, 231, 108986.
Zhang, Y., Ren, Z., Feng, K., Yu, K., Beer, M., & Liu, Z. (2023). Universal source-free domain adaptation method for cross-domain fault diagnosis of machines. Mechanical Systems and Signal Processing, 191, 110159.
Section
Technical Papers