Towards Open-Set Fault Diagnosis for Reactor Coolant Pumps under Unknown Fault Conditions
##plugins.themes.bootstrap3.article.main##
##plugins.themes.bootstrap3.article.sidebar##
Abstract
The reactor coolant pump – vibration monitoring system (RCP-VMS) ensures the safe operation of nuclear power plants by detecting anomalies in the shaft and bearing components of reactor coolant pumps. While effective for known fault modes, conventional AI-based diagnostic models often fail to detect unseen faults, especially when labeled data are limited. To address this limitation, an open-set recognition approach is proposed based on class-specific semantic reconstruction. Vibration signals collected from RCP-VMS are processed into orbit plot and recurrence plots, which serve as multi-channel image inputs to the model. The reconstruction errors are then used to distinguish both known and unknown fault conditions. Experimental results demonstrate that the proposed method achieves competitive closed-set accuracy while significantly enhancing open-set fault detection performance compared to baseline models. This approach enhances the reliability and robustness of fault diagnosis in safety-critical rotating machinery such as RCPs.
##plugins.themes.bootstrap3.article.details##
Open-Set Recognition (OSR), Class-Specific Semantic Reconstruction (CSSR), Reactor Coolant Pump Vibration Monitoring System (RCP-VMS), Orbit Plot and Recurrence Plots (RPs), Unknown Fault Detection
Hwang, M., Choi, M., & Oh, H. (2025). Frequency-enhanced neural networks with a hybrid spall-size estimator for bearing fault diagnosis. Journal of Computational Design and Engineering, 12(5), 1–20. https://doi.org/10.1093/jcde/qwaf040.
Choi, M., Lee, C., Park, S., Hwang, M., & Oh, H. (2025). Frequency-enhanced network with self-supervised learning for anomaly detection of hydraulic piston pumps. Expert Systems with Applications, 282, 127662. https://doi.org/10.1016/j.eswa.2025.127662.
Hu, M., Luo, C., Wang, C., & Qiang, Z. (2025). Compound fault recognition and diagnosis of rolling bearing in open-set-recognition setting. Measurement, 242(Part D), 116132. https://doi.org/10.1016/j.measurement.2024.116132.
Li, J., Lin, M., Wang, B., Tian, R., Tan, S., Li, Y., & Chen, J. (2024). Open set recognition fault diagnosis framework based on convolutional prototype learning network for nuclear power plants. Energy, 290, 130101. https://doi.org/10.1016/j.energy.2023.130101.
Scheirer, W. J., de Rezende Rocha, A., Sapkota, A., & Boult, T. E. (2013). Toward open set recognition. IEEE Transactions on Pattern Analysis and Machine Intelligence, 35(7), 1757–1772. https://doi.org/10.1109/TPAMI.2012.256.
Bendale, A., & Boult, T. E. (2016). Towards open set deep networks. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 1563–1572. https://doi.org/10.1109/CVPR.2016.173.
Huang, H., Wang, Y., Hu, Q., & Cheng, M. M. (2022). Class-specific semantic reconstruction for open set recognition. IEEE transactions on pattern analysis and machine intelligence, 45(4), 4214-4228.
Lee, D., Lee, J. G., Choi, M., Park, C., Kim, C. W., Niu, G., & Oh, H. (2025). Multi-fidelity sub-label-guided transfer network with physically interpretable synthetic datasets for rotor fault diagnosis. Engineering Applications of Artificial Intelligence, 148, 110467. https://doi.org/10.1016/j.engappai.2025.110467.
Eckmann, J.-P., Kamphorst, S. O., & Ruelle, D. (1987). Recurrence plots of dynamical systems. Europhysics Letters, 4(9), 973. https://doi.org/10.1209/0295-5075/4/9/004.
He, K., Zhang, X., Ren, S., & Sun, J. (2016). Deep residual learning for image recognition. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 770-778).
This work is licensed under a Creative Commons Attribution 3.0 Unported License.