Abstract
This paper presents a health-state assessment (HSA) approach based on unsupervised feature selection and fault severity evaluation steps for nuclear power plant (NPP) water screen cleaner condition monitoring. Firstly, different features are extracted from raw accelerometer data acquired from the physical system. Then, different feature selection methods such as between-feature and within-feature selection techniques have been investigated. Next to feature selection step, the coefficient-of-variations (CoV) technique has been utilized to measure the severity levels of multiple fault types. The proposed approach is validated on different fault types acquired from in-field NPP water screen cleaner accelerometer data. The results show that the proposed approach can be effectively used for health-state assessment of NPP water screen cleaners.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Coble, J.B., Ramuhalli, P., Bond, L.J., Hines, W., Upadhyaya, B.: A review of prognostics and health management applications in nuclear power plants. Int. J. Progn. Heal. Manag. 6(SP3), 1–22 (2015)
Agarwal, V., Lybeck, N., Pham, B.T., Rusaw, R., Bickford, R.: Prognostic and health management of active assets in nuclear power plants. Int. J. Prog. Health Manage. 1–17 (2015)
Ribeiro, F.D.S., et al.: Towards a deep unified framework for nuclear reactor perturbation analysis. In Proceedings of the 2018 IEEE Symposium Series on Computational Intelligence, SSCI 2018, pp. 120–127 (2019)
Calivá, F., et al.: A deep learning approach to anomaly detection in nuclear reactors. In Proceedings of the International Joint Conference on Neural Networks, vol. 2018 (2018)
Peng, M., Wang, H., Chen, S., Xia, G., Liu, Y.: An intelligent hybrid methodology of on-line system-level fault diagnosis for nuclear power plant. Nucl. Eng. Technol. 50(3), 396–410 (2018)
Peng, B., Xia, H., Liu, Y., Yang, B., Guo, D., Zhu, S.: Progress in nuclear energy research on intelligent fault diagnosis method for nuclear power plant based on correlation analysis and deep belief network. Prog. Nucl. Energy 108(July), 419–427 (2018)
Mandal, S., Santhi, B., Sridhar, S., Vinolia, K., Swaminathan, P.: Sensor fault detection in nuclear power plant using statistical methods. Nucl. Eng. Des. 324(October 2016) 103–110, 2017
Camci, F., Medjaher, K., Zerhouni, N., Nectoux, P.: Feature evaluation for effective bearing prognostics. Qual. Reliab. Eng. Int. 29(4), 477–486 (2013)
Liao, L.: Discovering prognostic features using genetic programming in remaining useful life prediction. IEEE Trans. Ind. Electron. 61(5), 2464–2472 (2014)
Atamuradov, V., Medjaher, K., Camci, F.: Railway point machine prognostics based on feature fusion and health state assessment. IEEE Trans. Instrum. Meas. 1–14 (2018)
Wang, Z., Jia, L., Qin, Y.: An integrated feature extraction algorithm for condition monitoring of railway point machine. In 2016 Prognostics and System Health Management Conference (PHM-Chengdu), pp. 1–5 (2016)
Bechhoefer, E., Li, R., He, D.: Quantification of condition indicator performance on a split torque gearbox. J. Intell. Manuf. 23(2), 213–220 (2012)
Al-atat, H., Siegel, D., Lee, J.: A systematic methodology for gearbox health assessment and fault classification. Int. J. Prog. Health Manage. (February), 1–16 (2011)
Benkedjouh, T., Medjaher, K., Zerhouni, N., Rechak, S.: Remaining useful life estimation based on nonlinear feature reduction and support vector regression. Eng. Appl. Artif. Intell. 26(7), 1751–1760 (2013)
Atamuradov, V., Camci, F.: Segmentation based feature evaluation and fusion for prognostics feature selection based on segment evaluation. Int. J. Progn. Health Manage. 8, 1–14 (2017)
Eker, U.K.O.F., Camci, F.: SVM based diagnostic on railway turnouts. Int. J. Performability Eng. (2012)
Atamuradov, V., Medjaher, K., Camci, F., Dersin, P., Zerhouni, N.: Degradation-level assessment and online prognostics for sliding chair failure on point machines. IFAC-PapersOnLine 51(24), 208–213 (2018)
Atamuradov Vepa, L.B., Medjaher, K., Camci, F., Zerhouni, N., Dersin, P.: Feature selection and fault‐severity classification–based machine health assessment methodology for point machine sliding‐chair degradation. Qual. Reliab. Eng. Int. (2018)
Chandrashekar, G., Sahin, F.: A survey on feature selection methods. Comput. Electr. Eng. 40(1), 16–28 (2014)
Acknowledgements
The authors acknowledge that all data collection procedure was funded by ASSYSTEM E&I and therefore the dataset used in this research remains the property of ASSYSTEM E&I. However, we would like to thank EDF (Électricité de France) for supporting this research and cooperating with us by giving a full access to their sites to build an experimental test bench on the nuclear power plant (NPP) system.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 Springer Nature Switzerland AG
About this paper
Cite this paper
Deleplace, A. et al. (2022). Health-State Assessment Approach Based on Unsupervised Feature Selection with Application to Nuclear Power Plant Water Screens. In: Zattoni, E., Simani, S., Conte, G. (eds) 15th European Workshop on Advanced Control and Diagnosis (ACD 2019). ACD 2019 2018. Lecture Notes in Control and Information Sciences - Proceedings. Springer, Cham. https://doi.org/10.1007/978-3-030-85318-1_33
Download citation
DOI: https://doi.org/10.1007/978-3-030-85318-1_33
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-85317-4
Online ISBN: 978-3-030-85318-1
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)