1.College of Electrical Engineering and Automation, Fuzhou University, Fuzhou 350108, China
2.The Department of Automation, Shanghai Jiao Tong University, Shanghai 200240, China
3.Fujian Fuqing Nuclear Power Co., Ltd., Fujian 350318, China
xuyongxmu@gmail.com
Scan for full text
Jing Chen, Ze-Shi Liu, Hao Jiang, et al. Anomaly detection of control rod drive mechanism using long short-term memory based autoencoder and extreme gradient boosting. [J]. Nuclear Science and Techniques 33(10):127(2022)
Jing Chen, Ze-Shi Liu, Hao Jiang, et al. Anomaly detection of control rod drive mechanism using long short-term memory based autoencoder and extreme gradient boosting. [J]. Nuclear Science and Techniques 33(10):127(2022) DOI: 10.1007/s41365-022-01111-0.
Anomaly detection for the control rod drive mechanism (CRDM) is key to enhancing the security of nuclear power plant equipment. In CRDM real-time condition-based maintenance, most existing methods cannot deal with long sequences and periodic abnormal events and have poor feature extraction from these data. In this paper, a learning-based anomaly detection method employing a long short-term memory-based autoencoder (LSTM-AE) network and an extreme gradient boosting (XGBoost) algorithm is proposed for the CRDM. The nonlinear and sequential features of the CRDM coil currents can be automatically and efficiently extracted by the LSTM neural units and AE network. The normal behavior LSTM-AE model was established to reconstruct the errors when feeding abnormal coil current signals. The XGBoost algorithm was leveraged to monitor the residuals and identify outliers for the coil currents. The results demonstrate that the proposed anomaly detection method can effectively detect different timing sequence anomalies and provide a more accurate forecasting performance for CRDM coil current signals.
Anomaly detectionCRDMLSTM-AEResidualsXGBoost
J.W. Lee, S.S. Cho, D.O. Kim et al., Dynanic characteristics on the CRDM of SMART reactor. J. Korean Mucl. Soc. 34, 1105-1111 (2010). doi: 10.3795/KSME-A.2010.34.8.1105http://doi.org/10.3795/KSME-A.2010.34.8.1105
A. Qluwasegun, J.C. Jung, The application of machine learning for the prognostics and health management of control element drive system. Nucl. Eng. Technol. 52, 2262-2273 (2020). doi: 10.1016/j.net.2020.03.028http://doi.org/10.1016/j.net.2020.03.028
C. Y. Peng, P. He, X. W. Peng et al., Research on Methods of Failuwre Analysis for ControlRod Drive Mechanism Based on Structure Moise Detecting Technique. Nucl. Power Eng. 41, 214-216 (2020). doi: 10.13832/j.jnpe.2020.03.0214http://doi.org/10.13832/j.jnpe.2020.03.0214
X. Y. Xie, H. Peng, Z. W. Zhang et al., Study on monitoring of action assembly of control rod drive mechanism in nuclear power reactors. Nucl. Power Eng. 40, 90-94 (2019). doi: 10.13832/j.jnpe.2019.02.0090http://doi.org/10.13832/j.jnpe.2019.02.0090
P.E. Huang, P. He, S.Q. He et al., Study on condition Monitoring and fault diagnosis of control rod driving mechanisn. Nucl. Electron. Detect. Technol. 3, 33 (2013). doi: 10.3969/j.issn.0258-0934.2013.03.017http://doi.org/10.3969/j.issn.0258-0934.2013.03.017 (in Chinese)
J.G. Zhang, H.J. Yian, Y.Q. Wu et al., Research on the electromagnetic structure of movable coil electromagnet drive mechanism for reactor control rod. J. Nucl. Sci. Technol. 44, 163-170 (2007). doi: 10.1080/18811248.2007.9711270http://doi.org/10.1080/18811248.2007.9711270
C. Ma, H. L. Bo, S. Y. Jiang et al., Study of maximal load capacity of moveable coil electromagnetic drive for reactor control rod. Nucl. Power Eng. 27, 55-57 (2006). doi: 10.1300/j064v28no110http://doi.org/10.1300/j064v28no110
S.T. Ling, W.Q. Li, C.X. Li et al., Flow field fusion simulation method based on model features and its application in CRDM. Nucl. Sci Tech. 33, 32 (2022). doi: 10.1007/s41365-022-01022-0http://doi.org/10.1007/s41365-022-01022-0
J. L. Chen, P.C. Ai, D. Wang et al., FPGA implementation of neural network accelerator for pulse information extraction in high energy physics. Nucl. Sci. Tech. 31, 46 (2020). doi: 10.1007/s41365-020-00756-zhttp://doi.org/10.1007/s41365-020-00756-z
X.K. Ma, H.Q. Huang, Q.C. Wang et al., Estimation of Gaussian overlapping nuclear pulse parameters based on a deep learning LSTM model. Nucl. Sci. Tech. 30, 171 (2019). doi: 10.1007/s41365-019-0691-2http://doi.org/10.1007/s41365-019-0691-2
A. Stetco, F. Dirnmohannadi, X.Y. Zhao et al., Machine learning methods for wind turbine condition monitoring: A review. Renewable Energy 133, 620-635 (2019). doi: 10.1016/j.renene.2018.10.047http://doi.org/10.1016/j.renene.2018.10.047
T.V. Tung, B.S. Yang, Machine fault diagnosis and prognosis: The state of the art. Intern. J. Fluid Mach. System. 2, 61-71 (2009). doi: 10.5293/IJFMS.2009.2.1.061http://doi.org/10.5293/IJFMS.2009.2.1.061
N. Alghanmi, R. Alotaibi, S.M. Buhari et al., Machine learning approaches for anomaly detection in IoT: An overview and future research directions. Wireless Pers Commun. 122, 2309-2304 (2020). doi: 10.1007/s11277-021-08994-zhttp://doi.org/10.1007/s11277-021-08994-z
M. H. Gu, J. J. Fei, S. L. Sun et al., Online anomaly detection with sparse Gaussian processes. Neurocomputing. 403, 383-399 (2020). doi: 10.1016/j.neucom.2020.04.077http://doi.org/10.1016/j.neucom.2020.04.077
R.K. Pandit, D. Infield, SCADA based wind turbine anomaly detection using Gaussian Process (GP) models for wind turbine condition monitoring purposes. IET Renewable Power Generation 12, 1249-1255 (2018). doi: 10.1049/iet-rpg.2018.0156http://doi.org/10.1049/iet-rpg.2018.0156
J. Song, H. Takakura, Unsupervised anomaly detection based on clustering and multiple one-class SVM. Trans. Inst. Electron. 92, 1981-1990 (2009). doi: 10.1587/transcom.E92.B.1981http://doi.org/10.1587/transcom.E92.B.1981
X. Wang, S.H. Ahn, Real-time prediction and anomaly detection of electrical load in a residential community. Appl. Energ. 259, 114145 (2020). doi: 10.1016/j.apenergy.2019.114145http://doi.org/10.1016/j.apenergy.2019.114145
H. Sarmadi, A. Karamodin, A novel anomaly detection method based on adaptive Mahalanobis-squared distance and one-class kNN rule for structural health monitoring under environmental effects. Mech. Syst. Signal. Proc. 140, 106495 (2020). doi: 10.1016/j.ymssp.2019.106495http://doi.org/10.1016/j.ymssp.2019.106495
M. Ding, T. Hui, PCA-based network traffic anomaly detection. Tsinghua. Sci. Technol. 21, 500-509 (2016). doi: 10.1109/TST.2016.7590319http://doi.org/10.1109/TST.2016.7590319
A. Sheinker, M.B. Moldwin, Magnetic anomaly detection (MAD) of ferromagnetic pipelines using principal component analysis (PCA). Meas. Sci. Technol. 27, 045104 (2016). doi: 10.1088/0957-0233/27/4/045104http://doi.org/10.1088/0957-0233/27/4/045104
C. Li, L. B. Guo, H. Guo et al., Similarity-measured isolation forest: An anomaly detection method for machine monitoring data. IEEE Trans. Instrum. Meas. 70, 3512512 (2021). doi: 10.1109/TIM.2021.3062684http://doi.org/10.1109/TIM.2021.3062684
L. Puggini, S. McLoone, An enhanced variable selection and isolation forest based methodology for anomaly detection with OES data. Eng. Appl. Artif. Intel. 67, 126-135 (2018). doi: 10.1016/j.engappai.2017.09.021http://doi.org/10.1016/j.engappai.2017.09.021
M. Canizo, I. Triguero, A. Conde et al., Multi-head CNN-RNN for multi-time series anomaly detection: An industrial case study. Neurocomputing 363, 246-260 (2019). doi: 10.1016/j.neucom.2019.07.034http://doi.org/10.1016/j.neucom.2019.07.034
Y. Yan, G. Sheng, Y. Chen et al., An method for anomaly detection of state information of power equipment based on big data analysis. Proceeings of the CSEE 35, 52-59 (2015). doi: 10.13334/j.0258-8013.pcsee.2015.01.007http://doi.org/10.13334/j.0258-8013.pcsee.2015.01.007 (in Chinese)
T. Ergen, S. Kozat, Unsupervised anomaly detection with LSTM neural networks. IEEE T. Neur. Net. Lear 31, 3127-3141 (2020). doi: 10.1109/TNNLS.2019.2935975http://doi.org/10.1109/TNNLS.2019.2935975
A. Coluccia, D. Alconzo, F. Ricciato, Distribution-based anomaly detection via generalized likelihood ratio test: A general maximum entropy approach. Comput. Netw 57, 3446-3462 (2013). doi: 10.1016/j.comnet.2013.07.028http://doi.org/10.1016/j.comnet.2013.07.028
D. Zhang, L. Qian, B. Mao et al., A data-driven design for fault detection of wind turbines using random forests and XGBoost. IEEE Access, 21020-21031 (2018). doi: 10.1109/ACCESS.2018.2818678http://doi.org/10.1109/ACCESS.2018.2818678
J. Zeng, C. Peng, P. He et al., Research on Current Monitoring and Fault Diagnosis Technology for Control Rod Drive Mechanism. Nucl. Power Eng. 40, 172-175 (2019). doi: 10.13832/j.jnpe.2019.01.0172http://doi.org/10.13832/j.jnpe.2019.01.0172
0
Views
0
Downloads
0
CSCD
Publicity Resources
Related Articles
Related Author
Related Institution