基于神经网络方法的LOCA事故诊断

doi:10.11889/j.0253-3219.2017.hjs.40.080604

Nuclear Techniques ›› 2017, Vol. 40 ›› Issue (8): 80604-080604.doi: 10.11889/j.0253-3219.2017.hjs.40.080604

• NUCLEAR ENERGY SCIENCE AND ENGINEERING • Previous Articles

Fault diagnosis of LOCA based on ANN methods

LI Shixian¹, LIU Jingquan¹, SHEN Yonggang²

1. Department of Engineering Physics, Tsinghua University, Beijing 100084, China;
2. China Nuclear Power Technology Research Institute, Shenzhen 518000, China

Received:2017-02-27 Revised:2017-04-19 Online:2017-08-10 Published:2017-08-11

Abstract

Abstract: Background: Loss of coolant accident (LOCA) is one of the typical accidents in safety analysis of nuclear power plant and the location and the size of break will affect its treatment and consequences directly. Purpose:This study aims to diagnose the location and the size of break by using artificial neural network (ANN) based pattern recognition approach. Methods: CATHARE program was used to model and simulate different location and size of break in LOCA for the CPR1000 nuclear power system. Six types of thermal-hydraulic parameters were extracted to train four types of ANN methods (back propagation (BP) neural network, Elman neural network, radial basis function (RBF) neural network and support vector machine) and the trained ANNs were utilized to diagnose the location and the size of break. Results: The optimized support vector machine (SVM) is best method in terms of diagnosis accuracy and stability among 4 ANNs. Conclusion: The operators can obtain more detailed information about break by SVM to deal with the accident efficiently, when a LOCA happens.

Key words: Artificial neural network, LOCA, CPR1000

CLC Number:

TL364⁺.4

LI Shixian, LIU Jingquan, SHEN Yonggang. Fault diagnosis of LOCA based on ANN methods[J].Nuclear Techniques, 2017, 40(8): 80604-080604.

References

1 林支康, 殷煜皓, 梁国兴. AP1000核电厂RELAP5 SB-LOCA分析模式建立与应用[J]. 电力与能源, 2011, 6:457-461. LIN Zhikang, YIN Yuhao, LIANG Guoxing. Establishing and application of AP1000 nuclear power plant RELAPS-code SB-LOCA model[J]. Power & Energy, 2011, 6:457-461.
2 中广核工程有限公司. 中国百万千瓦级核电自主化依托工程[M]. 北京:中国原子能出版社, 2013. China Nuclear Power Engineering Co., Ltd. China's million kilowatt class nuclear power self-reliance project[M]. Beijing:China Atomic Energy Press, 2013.
3 Santosh T V, Vinod G, Saraf A K, et al. Application of artificial neural networks to nuclear power plant transient diagnosis[J]. Reliability Engineering and System Safety, 2007, 92:1468-1472. DOI:10.1016/j.ress.2006.10.009.
4 Cheon S W,Chang S H, Chung H Y, et al. Application of neural networks to multiple alarm processing and diagnosis in nuclear power plants[J]. IEEE Transactions on Nuclear Science, 1993, 40(1):11-20.
5 赵云飞, 张立国, 童节娟, 等. BP神经网络在AP1000核电站事故诊断应用中的初步研究[J]. 原子能科学技术, 2014, 48(S1):480-484. DOI:10.7539/YZK.2014.48. S0.0480. ZHAO Yunfei, ZHANG Liguo, TONG Jiejuan, et al. Preliminary study on application of BP neural network in AP1000 nuclear power plant accident diagnosis[J]. Atomic Energy Science and Technology, 2014, 48(S1):480-484. DOI:10.7539/YZK.2014.48.S0.0480.
6 蔡猛, 张大发, 张宇声. 基于遗传算法的核动力设备实时故障诊断系统[J]. 核动力工程, 2009, 30(3):111-114, 130. CAI Meng, ZHANG Dafa, ZHANG Yusheng. Nuclear power plant real-time fault diagnosis system based on genetic algorithm[J]. Nuclear Power Engineering, 2009, 30(3):111-114, 130.
7 刘永阔, 夏虹, 谢春丽, 等. BP-RBF神经网络在核电厂故障诊断中的应用[J]. 原子能科学技术, 2008, 42(3):193-199. LIU Yongkuo, XIA Hong, XIE Chunli, et al. Application of BP-RBF neural network to fault diagnosis of nuclear power plant[J]. Atomic Energy Science and Technology, 2008, 42(3):193-199.
8 肖岷, 郝思雄, 韩庆浩, 等. 中广核CPR1000核岛堆芯概念设计和安全裕度评估初探[J]. 核动力工程, 2005, (S1):11-18. XIAO Min, HAO Sixiong, HAN Qinghao, et al. Primary study on core concept design and safety margin of CPR1000[J]. Nuclear Power Engineering, 2005, (S1):11-18.
9 谢春丽, 夏虹, 刘永阔, 等. BP神经网络改进算法在核电设备故障诊断中的应用[J]. 核动力工程, 2007, 28(4):85-90. XIE Chunli, XIA Hong, LIU Yongkuo, et al. Application of improved BP algorithm in fault diagnosis of nuclear power equipment[J]. Nuclear Power Engineering, 2007, 28(4):85-90.
10 熊晋魁, 谢春玲, 施小成, 等. RBF人工神经网络在核电厂故障诊断中的应用[J]. 核动力工程, 2006, 27(3):57-60, 96. XIONG Jinkui, XIE Chunling, SHI Xiaocheng, et al. Application of RBF artificial neural network to fault diagnose in nuclear power plant[J]. Nuclear Power Engineering, 2006, 27(3):57-60, 96.
11 Seker S, Ayaz E, Türkcan E. Elman's recurrent neural network applications to condition monitoring in nuclear power plant and rotating machinery[J]. Engineering Applications of Artificial Intelligence, 2003, 16:647-656.
12 汤宝平, 习建民, 李锋. 基于Elman神经网络的旋转机械故障诊断[J]. 计算机集成制造系统, 2010, 10:2148-2152. TANG Baoping, XI Jianmin, LI Feng. Fault diagnosis for rotating machinery based on Elman neural network[J]. Computer Integrated Manufacturing Systems, 2010, 10:2148-2152.
13 Zhang X G. Introduction to statistical learning theory and support vector machines[J]. Acta Automatica Sinica, 2000, 26(1):33-41.
14 袁胜发, 褚福磊. 支持向量机及其在机械故障诊断中的应用[J]. 振动与冲击, 2007, 11:29-35, 58, 181. YUAN Shengfa, CHU Fulei. Support vector machines and its applications in machine fault diagnosis[J]. Journal of Vibration and Shock, 2007, 11:29-35, 58, 181.
15 宋梅村, 蔡琦. 基于支持向量回归的设备故障趋势预测[J]. 原子能科学技术, 2011, 45(8):972-976. SONG Meicun, CAI Qi. Fault trend prediction of device based on support vector regression[J]. Atomic Energy Science and Technology, 2011, 45(8):972-976.
16 黄彦平, 曹念, 文彦, 等. CATHARE程序的主要特征及应用[J]. 核动力工程, 2003, 24(6):540-544. HUANG Yanping, CAO Nian, WEN Yan, et al. Main features of CATHARE code and its application[J]. Nuclear Power Engineering, 2003, 24(6):540-544.
17 陈明. MATLAB神经网络原理与实例精解[M]. 北京:清华大学出版社, 2013. CHEN Ming. MATLAB neural network theory and examples[M]. Beijing:Tsinghua University Press, 2013.
18 李坤, 刘鹏, 吕雅洁, 等. 基于Spark的LIBSVM参数优选并行化算法[J]. 南京大学学报(自然科学), 2016, 52(2):343-352. LI Kun, LIU Peng, LYU Yajie, et al. The parallel algorithms for LIBSVM parameter optimization based on Spark[J]. Journal of Nanjing University (Natural Sciences), 2016, 52(2):343-352.
19 王小川. MATLAB神经网络43个案例分析[M]. 北京:北京航空航天大学出版社, 2013. WANG Xiaochuan. MATLAB neural network analysis of 43 cases[M]. Beijing:Beijing University of Aeronautics and Astronautics Press, 2013.

[1]	Xinyuan ZHANG Aimin SHANG. Study on LOCA accident of fuel rod with SiCf/SiC cladding [J]. Nuclear Techniques, 2019, 42(8): 80601-080601.
[2]	Yang ZHAO Yue ZHANG Zhenchao YAO Xinsen ZUO Guoping ZHOU. Radiation-source localization based on three NaI(Tl) crystal detectors [J]. Nuclear Techniques, 2019, 42(8): 80401-080401.
[3]	Hanjie CAO,Hongliang BAO,Haisheng YU,Yuying HUANG,Jianqiang WANG. Lattice modification of U₃O₈ matrix induced by cerium substitution [J]. Nuclear Techniques, 2019, 42(7): 0-070101-7.
[4]	Peiqi LIU, Pengcheng ZHAO, Tao YU, Jinsen XIE, Zhenping CHEN, Chao XIE, Zijing LIU, Wenjie ZENG. Analysis of LOCA with different break sizes in PWR [J]. Nuclear Science and Techniques, 2019, 42(2): 20601-020601.
[5]	LUO Jianbing, ZHANG Peng, ZHU Te, CAO Xingzhong, ZHANG Huaiqiang, JIN Shuoxue, YU Runsheng, WANG Baoyi. Study of hydrogen induced defects in Fe-1.0%Cu alloy by positron annihilation spectroscopy [J]. Nuclear Techniques, 2018, 41(2): 20501-020501.
[6]	ZHANG Zhenchao, ZUO Guoping, TAN Junwen, ZHOU Yang, ZHANG Fan. Locating radioactive source based on three coupled-crystals directional detector of γ rays [J]. Nuclear Techniques, 2017, 40(10): 100402-100402.
[7]	WANG Weiwei, CAO Kemei, QI Zhanfei. Calculation and analysis of jet-impact influence zone in GSI-191 issue [J]. Nuclear Techniques, 2016, 39(2): 20604-020604.
[8]	ZHAO Juan, GAO Zhengming. Location method of a single gamma source based on the detectors array [J]. Nuclear Techniques, 2016, 39(1): 10402-010402.
[9]	YU Jianhui, ZHANG Jingyu, ZHENG Limin. Study on ASTRUM optimization for large break LOCA analysis [J]. Nuclear Techniques, 2014, 37(09): 90606-090606.
[10]	LIU Min,LU Yangling,ZHOU Xingtai. Investigation on microstructure of Hastelloy N after irradiation by 30 keV He ions [J]. Nuclear Techniques, 2013, 36(5): 50205-050205.

Fault diagnosis of LOCA based on ANN methods

PDF (PC)

Like

Knowledge

Abstract

Cite this article

share this article

References

Related Articles 10

Metrics

Comments

Recommended 10