新型电力系统与综合能源

基于数据驱动的核电设备状态评估研究综述

展开
  • 1.上海交通大学 自动化系,上海 200240
    2.福建福清核电有限公司,福建 福清 350318
    3.上海交通大学 系统控制与信息处理教育部重点实验室; 上海工业智能管控工程技术研究中心,上海 200240
许 勇(1983-),男,福建省莆田市人,博士生,现从事核电设备故障诊断研究.

收稿日期: 2021-12-08

  网络出版日期: 2022-04-01

基金资助

国家自然科学基金(61627810);国家科技重大专项(2018YFB1305003)

Review of Research on Condition Assessment of Nuclear Power Plant Equipment Based on Data-Driven

Expand
  • 1. Department of Automation, Shanghai Jiao Tong University, Shanghai 200240, China
    2. Fujian Fuqing Nuclear Power Co., Ltd., Fuqing 350318, Fujian, China
    3. Key Laboratory of System Control and Information Processing of the Ministry of Education; Shanghai Engineering Research Center of Intelligent Control and Management, Shanghai Jiao Tong University, Shanghai 200240, China

Received date: 2021-12-08

  Online published: 2022-04-01

摘要

核电设备全生命周期的状态评估对提高核电厂安全性、经济性影响重大.以往国内核电厂对系统、设备、构筑物的运维评估手段多依赖于设备自身报警机制、简单阈值判断或者现场工程师经验.随着在线监测系统在核电厂的应用实施和海量设备运行数据的积累,利用数据驱动技术进行设备健康状态评估已经成为行业关注重点.对此,介绍核电在线监测系统现状,分析主要核电设备存在的常见故障,并将核电设备的状态评估归纳为异常检测、寿命预测和故障诊断共3大问题,分别综述其研究和应用现状,重点阐述深度学习技术在该领域的应用潜力.在此基础上,进一步分析核电厂设备状态评估面临的挑战和可能的解决方案.

本文引用格式

许勇, 蔡云泽, 宋林 . 基于数据驱动的核电设备状态评估研究综述[J]. 上海交通大学学报, 2022 , 56(3) : 267 -278 . DOI: 10.16183/j.cnki.jsjtu.2021.502

Abstract

The condition assessment of the entire life cycle of nuclear power equipment has a significant impact on improving the safety and economy of nuclear power plants. In the past, operation and maintenance of systems, equipment, and structures of domestic nuclear power plants, mostly relied on the alarm mechanism of equipments, the simple threshold judgments of parameters, or the empirical judgments of engineers. With the implementation of online monitoring system in nuclear power plants, a large number of equipment operation data have been accumulated, and the use of data-driven technology to assess the health of equipment has become the focus of attention in the industry. In this paper, the current situation of the online monitoring system of nuclear power equipment was introduced and the common malfunction of nuclear power equipment was analyzed. The condition assessment of nuclear power equipment were categorized into three major problems (i.e., anomaly detection, life prediction, and fault diagnosis), the situation of research and application were summarized respectively, and the application potential of deep learning technology in this field was emphasized. Based on this, the challenges and possible solutions to the condition assessment of nuclear power plant equipment were further analyzed.

参考文献

[1] 中华人民共和国国家质量监督检查检疫总局, 中国国家标准管理委员会. 核电厂安全系统定期试验和监测: GB/T 5204—2008[S]. 北京: 中国标准出版社, 2008.
[1] General Administration of Quality Supervision, Inspection and Quarantine of the People’s Republic of China, Standardization Administration of the People’s Republic of China. Periodic tests monitoring of the safety system of nuclear power plant: GB/T 5204—2008[S]. Beijing: Standards Press of China, 2008.
[2] 周东华, 魏慕恒, 司小胜. 工业过程异常检测、寿命预测与维修决策的研究进展[J]. 自动化学报, 2013, 39(6):711-722.
[2] ZHOU Donghua, WEI Muheng, SI Xiaosheng. A survey on anomaly detection, life prediction and maintenance decision for industrial processes[J]. Acta Automatica Sinica, 2013, 39(6):711-722.
[3] WANG H, PENG M J, WESLEY HINES J, et al. A hybrid fault diagnosis methodology with support vector machine and improved particle swarm optimization for nuclear power plants[J]. ISA Transactions, 2019, 95:358-371.
[4] WANG H, PENG M J, YU Y, et al. Fault identification and diagnosis based on KPCA and similarity clustering for nuclear power plants[J]. Annals of Nuclear Energy, 2021, 150:107786.
[5] WANG H, PENG M J, XU R Y, et al. Remaining useful life prediction based on improved temporal convolutional network for nuclear power plant valves[J]. Frontiers in Energy Research, 2020, 8:584463.
[6] ZHAO Y, DI MAIO F, ZIO E, et al. Optimization of a dynamic uncertain causality graph for fault diagnosis in nuclear power plant[J]. Nuclear Science and Techniques, 2017, 28(3):1-9.
[7] LI W, PENG M J, WANG Q Z. False alarm reducing in PCA method for sensor fault detection in a nuclear power plant[J]. Annals of Nuclear Energy, 2018, 118:131-139.
[8] LI W, PENG M J, WANG Q Z. Fault detectability analysis in PCA method during condition monitoring of sensors in a nuclear power plant[J]. Annals of Nuclear Energy, 2018, 119:342-351.
[9] LI W, PENG M J, WANG Q Z. Improved PCA method for sensor fault detection and isolation in a nuclear power plant[J]. Nuclear Engineering and Technology, 2019, 51(1):146-154.
[10] LI W, PENG M J, WANG Q Z. Fault identification in PCA method during sensor condition monitoring in a nuclear power plant[J]. Annals of Nuclear Energy, 2018, 121:135-145.
[11] 陈玉昇, 杨燕华, 林萌, 等. 基于深度学习神经网络的核电厂故障诊断技术[J]. 上海交通大学学报, 2018, 52(Sup.1):58-61.
[11] CHEN Yusheng, YANG Yanhua, LIN Meng, et al. Fault diagnosis technology of nuclear power plant based on deep learning neural network[J]. Journal of Shanghai Jiao Tong University, 2018, 52(Sup.1):58-61.
[12] TAMAOKI T, SONODA Y, SATO M, et al. Model-based temperature noise monitoring methods for LMFBR core anomaly detection[J]. Journal of Nuclear Science and Technology, 1994, 31(3):189-203.
[13] KOZMA R, NABESHIMA K. Studies on the detection of incipient coolant boiling in nuclear reactors using artificial neural networks[J]. Annals of Nuclear Energy, 1995, 22(7):483-496.
[14] NABESHIMA K, SUZUDO T, SUZUKI K, et al. Real-time nuclear power plant monitoring with neural network[J]. Journal of Nuclear Science and Technology, 1998, 35(2):93-100.
[15] NABESHIMA K, SUZUDO T, SEKER S, et al. On-line neuro-expert monitoring system for Borssele Nuclear Power Plant[J]. Progress in Nuclear Energy, 2003, 43(1/2/3/4):397-404.
[16] AYAZ E. Component-wide and plant-wide monitoring by neural networks for Borssele nuclear power plant[J]. Energy Conversion and Management, 2008, 49(12):3721-3728.
[17] STEPHEN B, WEST G M, GALLOWAY S, et al. The use of hidden Markov models for anomaly detection in nuclear core condition monitoring[J]. IEEE Transactions on Nuclear Science, 2009, 56(2):453-461.
[18] JIN X, GUO Y, SARKAR S, et al. Anomaly detection in nuclear power plants via symbolic dynamic filtering[J]. IEEE Transactions on Nuclear Science, 2011, 58(1):277-288.
[19] CÓZAR J, PUERTA J M, GÁMEZ J A. An application of dynamic Bayesian networks to condition monitoring and fault prediction in a sensored system: A case study[J]. International Journal of Computational Intelligence Systems, 2017, 10(1):176.
[20] ROCCO S C M, ZIO E. A support vector machine integrated system for the classification of operation anomalies in nuclear components and systems[J]. Reliability Engineering & System Safety, 2007, 92(5):593-600.
[21] AYODEJI A, LIU Y K. Support vector ensemble for incipient fault diagnosis in nuclear plant components[J]. Nuclear Engineering and Technology, 2018, 50(8):1306-1313.
[22] UPADHYAYA B R, ZHAO K, LU B. Fault monitoring of nuclear power plant sensors and field devices[J]. Progress in Nuclear Energy, 2003, 43(1/2/3/4):337-342.
[23] HADAD K, MORTAZAVI M, MASTALI M, et al. Enhanced neural network based fault detection of a VVER nuclear power plant with the aid of principal component analysis[J]. IEEE Transactions on Nuclear Science, 2008, 55(6):3611-3619.
[24] PENG B S, XIA H, MA X T, et al. A mixed intelligent condition monitoring method for nuclear power plant[J]. Annals of Nuclear Energy, 2020, 140:107307.
[25] KUNDU P, DARPE A K, KULKARNI M S. Weibull accelerated failure time regression model for remaining useful life prediction of bearing working under multiple operating conditions[J]. Mechanical Systems and Signal Processing, 2019, 134:106302.
[26] PENG K X, JIAO R H, DONG J, et al. A deep belief network based health indicator construction and remaining useful life prediction using improved particle filter[J]. Neurocomputing, 2019, 361:19-28.
[27] WANG H, MA X B, ZHAO Y. An improved Wiener process model with adaptive drift and diffusion for online remaining useful life prediction[J]. Mechanical Systems and Signal Processing, 2019, 127:370-387.
[28] SATO M, MOURA L S, GALVIS A F, et al. Analy-sis of two-dimensional fatigue crack propagation in thin aluminum plates using the Paris law modified by a closure concept[J]. Engineering Analysis With Boundary Elements, 2019, 106:513-527.
[29] DOWNEY A, LUI Y H, HU C, et al. Physics-based prognostics of lithium-ion battery using non-linear least squares with dynamic bounds[J]. Reliability Engineering & System Safety, 2019, 182:1-12.
[30] MADAR E, KLEIN R, BORTMAN J. Contribution of dynamic modeling to prognostics of rotating machinery[J]. Mechanical Systems and Signal Processing, 2019, 123:496-512.
[31] AIZPURUA J I, MCARTHUR S D J, STEWART B G, et al. Adaptive power transformer lifetime predictions through machine learning and uncertainty mo-deling in nuclear power plants[J]. IEEE Transactions on Industrial Electronics, 2019, 66(6):4726-4737.
[32] ELMASHTOLY A M, CHANG C K. Prognostics health management system for power transformer with IEC61850 and Internet of Things[J]. Journal of Electrical Engineering & Technology, 2020, 15(2):673-683.
[33] OLUWASEGUN A, JUNG J C. The application of machine learning for the prognostics and health ma-nagement of control element drive system[J]. Nuclear Engineering and Technology, 2020, 52(10):2262-2273.
[34] LIU J. First-order uncertain hidden semi-Markov process for failure prognostics with scarce data[J]. IEEE Access, 2020, 8:104099-104108.
[35] UTAH M N, JUNG J C. Fault state detection and remaining useful life prediction in AC powered solenoid operated valves based on traditional machine learning and deep neural networks[J]. Nuclear Engineering and Technology, 2020, 52(9):1998-2008.
[36] WANG H, PENG M J, LIU Y K, et al. Remaining useful life prediction techniques of electric valves for nuclear power plants with convolution kernel and LSTM[J]. Science and Technology of Nuclear Installations, 2020(16):1-13.
[37] HOLBERT K E, UPADHYAYA B R. Empirical process modeling technique for signal validation[J]. Annals of Nuclear Energy, 1994, 21(7):387-403.
[38] WU G H, TONG J J, ZHANG L G, et al. Framework for fault diagnosis with multi-source sensor nodes in nuclear power plants based on a Bayesian network[J]. Annals of Nuclear Energy, 2018, 122:297-308.
[39] MANDAL S, SAIRAM N, SRIDHAR S, et al. Nuclear power plant sensor fault detection using singular value decomposition-based method[J]. Sādhanā, 2017, 42(9):1473-1480.
[40] MANDAL S, SANTHI B, SRIDHAR S, et al. Sensor fault detection in Nuclear Power Plant using statistical methods[J]. Nuclear Engineering and Design, 2017, 324:103-110.
[41] MANDAL S, SANTHI B, SRIDHAR S, et al. A novel approach for fault detection and classification of the thermocouple sensor in Nuclear Power Plant using Singular Value Decomposition and Symbolic Dynamic Filter[J]. Annals of Nuclear Energy, 2017, 103:440-453.
[42] CHO S, JIANG J. Optimal fault classification using fisher discriminant analysis in the parity space for applications to NPPs[J]. IEEE Transactions on Nuclear Science, 2018, 65(3):856-865.
[43] MESSAI A, MELLIT A, ABDELLANI I, et al. On-line fault detection of a fuel rod temperature measurement sensor in a nuclear reactor core using ANNs[J]. Progress in Nuclear Energy, 2015, 79:8-21.
[44] LIN T H, WU S C, CHEN K Y, et al. Feature extraction and sensor selection for NPP initiating event identification[J]. Annals of Nuclear Energy, 2017, 103:384-392.
[45] JAMIL F, ABID M, ADIL M, et al. Kernel approaches for fault detection and classification in PARR-2[J]. Journal of Process Control, 2018, 64:1-6.
[46] LIU Y K, ABIODUN A, WEN Z B, et al. A cascade intelligent fault diagnostic technique for nuclear power plants[J]. Journal of Nuclear Science and Technology, 2018, 55(3):254-266.
[47] MANDAL S, SANTHI B, SRIDHAR S, et al. Nuclear power plant thermocouple sensor-fault detection and classification using deep learning and generalized likelihood ratio test[J]. IEEE Transactions on Nuclear Science, 2017, 64(6):1526-1534.
[48] PENG B S, XIA H, LIU Y K, et al. Research on intelligent fault diagnosis method for nuclear power plant based on correlation analysis and deep belief network[J]. Progress in Nuclear Energy, 2018, 108:419-427.
[49] LEE C K, CHANG S J. Fault detection in multi-core C&I cable via machine learning based time-frequency domain reflectometry[J]. Applied Sciences, 2019, 10(1):158.
[50] BANG S S, SHIN Y J. Classification of faults in multicore cable via time-frequency domain reflectometry[J]. IEEE Transactions on Industrial Electronics, 2020, 67(5):4163-4171.
[51] SAEED H A, WANG H, PENG M J, et al. Online fault monitoring based on deep neural network & sliding window technique[J]. Progress in Nuclear Energy, 2020, 121:103236.
[52] KIM T K, PARK J K, LEE B H, et al. Deep-learning-based alarm system for accident diagnosis and reactor state classification with probability value[J]. Annals of Nuclear Energy, 2019, 133:723-731.
[53] YANG J, KIM J. An accident diagnosis algorithm using long short-term memory[J]. Nuclear Engineering and Technology, 2018, 50(4):582-588.
[54] CHOI J, LEE S J. Consistency index-based sensor fault detection system for nuclear power plant emergency situations using an LSTM network[J]. Sensors, 2020, 20(6):1651.
[55] YANG J, KIM J. Accident diagnosis algorithm with untrained accident identification during power-increasing operation[J]. Reliability Engineering & System Safety, 2020, 202:107032.
[56] ARORA A, SHANTANU. A review on application of GANs in cybersecurity domain[J]. IETE Technical Review, 2020: 1-9.
[57] ZHANG L W, LIN J, LIU B, et al. A review on deep learning applications in prognostics and health management[J]. IEEE Access, 2019, 7:162415-162438.
[58] KOIZUMI Y, YASUDA M, MURATA S, et al. SPIDERnet: Attention network for one-shot anomaly detection in sounds[C]// ICASSP 2020-2020 IEEE International Conference on Acoustics, Speech and Signal Processing. Barcelona, Spain: IEEE, 2020: 281-285.
[59] KOIZUMI Y, MURATA S, HARADA N, et al. SNIPER: Few-shot learning for anomaly detection to minimize false-negative rate with ensured true-positive rate[C]// ICASSP 2019-2019 IEEE International Conference on Acoustics, Speech and Signal Processing. Brighton, UK: IEEE, 2019: 915-919.
文章导航

/