Design and Development of Intelligent Visual Simulator for Fault Detection, Identification and Diagnosis in PWR Nuclear Power Plant
DOI:
https://doi.org/10.53560/PPASA(62-1)875Keywords:
Automated System, Fault Detection and Diagnosis, Unsupervised Machine Learning, AP600, Abnormal Operation, PWRAbstract
In this research, the AP600 Pressurized Water Reactor (PWR)-type Nuclear Power Plant (NPP) is studied due to its large number of components and complex, diversified systems. Operating a reliable and economical PWR NPP without malfunctions is desirable, with maximum safety as the primary goal. A Personal Computer Transient Analyzer (PCTRAN) is used as a data-driven source for AP600 PWR NPP, enabling simulations of both normal and abnormal operations. A state-of-the-art, fully automated, intelligent fault detection, identification, and diagnosis software (AI-FDID-PCTRAN) is designed and developed in Visual Basic to address various safety concerns and enhance the reliability and availability of AP600 PWR NPP systems. AI-FDID-PCTRAN is formulated, programmed, and configured based on unsupervised machine learning using Principal Component Analysis (PCA), a fully Automated Multivariate Statistical Process Control Technique (AMSPCT). The proposed PCA-based technique is a purely software-driven, systematically structured, and fully automated approach, developed specifically for the AP600 PWR nuclear industry. This specialized software offers capabilities not found in highly expensive, commercially available alternatives. FDD-PCTRAN has been tested against benchmark normal and abnormal transients available in AP600 PCTRAN and has proven to be highly reliable and accurate in fault detection and diagnosis.
References
J. Ma and J. Jiang. Application of fault detection and diagnosis methods in nuclear power plants: A Review. Progress in Nuclear Energy 53: 255-266 (2011).
G. Hu, T. Zhou, and Q. Liu. Data-Driven Machine Learning for Fault Detection and Diagnosis in Nuclear Power Plants: A Review. Frontiers in Energy Research 9: 663296 (2021).
F.D. Maio, P. Baraldi, E. Zio, and R. Seraoui. Fault Detection in Nuclear Power Plants Components by a Combination of Statistical Methods. IEEE Transactions on Reliability 62(4): 833-845 (2013).
V.S. Yellapu, V. Vajpayee, Akhilan, and P. Tiwari. Online Fault Detection and Isolation in Advanced Heavy Water Reactor using Multiscale Principal Component Analysis. IEEE Transactions on Nuclear Science 66(7): 1790-1803 (2019).
J. Ma and J. Jiang. Detection and Identification of Faults in NPP Instruments using Kernel Principal Component Analysis. Journal of Engineering for Gas Turbines and Power 134: 103990 (2012).
Y. Yu, M. Peng, H. Wang, Z. Maa, and W. Li. Improved PCA Model for Multiple Fault Detection, Isolation and Reconstruction of Sensors in Nuclear Power Plant. Annals of Nuclear Energy 148: 107662 (2020).
C. Lai, I. Ahmed, E. Zio, Wei. Li, Y. Zhang, W. Yao, and J. Chen. A Multistage Physics-Informed Neural Network for Fault Detection in Regulating Valves of Nuclear Power Plants. Energies 17: 2647 (2024).
C. Gallo and V. Capozzi. Feature Selection with Non-Linear PCA: A Neural Network Approach. Journal of Applied Mathematics and Physics 7: 2537-2554 (2019).
P. Kazemi, A. Masoumain, and P. Martin. Fault Detection and Isolation for Time Varying processes using Neural based Principal Component Analysis. Processes 12(6): 1218 (2024).
E.A.M.B. Ihrayz. PCTRAN Westinghouse AP1000 Power Control of Pressurized Water Reactor using Simulink of MATLAB. Open Journal of Energy Efficiency 12: 25-35 (2023).
B. Liu, J. Lei, J. Xie, and J. Zhou. Development and Validation of a Nuclear Power Plant Fault Diagnosis System based on Deep Learning. Energies 15: 8629 (2022).
C. Ren, H. Li, J. Lei, J. Liu, W. Li, K. Gao, G. Huang, X. Yang, and T. Yu. A CNN-LSTM based Model to FAULT Diagnosis for CPR1000. Nuclear Technology 209(9): 1365-1372 (2023).
C. Zhang, P. Chen, F. Jiang, J. Xie, and T. Yu. Fault Diagnosis of Nuclear Power Plant based on Sparrow Search Algorithm Optimized CNN-LSTM Neural Network. Energies 16: 2934 (2023).
M. Xin, W. Jiao, and L. Da-zi. Fault Diagnosis of Nuclear Power Plant based on Simplified Signed Directed Graph with Principal Component Analysis and Support Vector Machine. Chinese Automation Congress, 22nd–24th November 2019, Hangzhou, China (2009).
Y. Liu, F. Xie, C. Xie, M. Peng, G. Wua, and H. Xia. Prediction of Time Series of NPP Operating Parameters using Dynamic Model based on BP Neural Network. Annals of Nuclear Energy 85: 566-575 (2015).
L. Yong-kuo, A. Abiodun, W. Zhi-bin, W. Mao-pu, P. Min-jun, and Y. Wei-feng. Rajesh. A Cascade Intelligent Fault Diagnosis Technique for Nuclear Power Plants. Journal of Nuclear Science and Technology 55(3): 254-266 (2018).
L.M. Elshenawy, M.A. Halawa, T.A. Mahmoud, H.A. Awad, and M.I. Abdo. Unsupervised Machine Learning Techniques for Fault Detection and Diagnosis in Nuclear Power Plants. Progress in Nuclear Energy 142: 103990 (2021).
