Research and Application of Transient Satistical Method for Nuclear Power Plant

Bai Xiaoming; Cao Guochang; Cao Hongsheng; Yu Xinyang; Xiong Furui; Jiang He

doi:10.13832/j.jnpe.2024.S1.0001

Volume 45 Issue S1

Jun. 2024

Turn off MathJax

Article Contents

Article Navigation > Nuclear Power Engineering > 2024 > 45(S1): 1-5

Bai Xiaoming, Cao Guochang, Cao Hongsheng, Yu Xinyang, Xiong Furui, Jiang He. Research and Application of Transient Satistical Method for Nuclear Power Plant[J]. Nuclear Power Engineering, 2024, 45(S1): 1-5. doi: 10.13832/j.jnpe.2024.S1.0001

Citation:

Bai Xiaoming, Cao Guochang, Cao Hongsheng, Yu Xinyang, Xiong Furui, Jiang He. Research and Application of Transient Satistical Method for Nuclear Power Plant[J]. Nuclear Power Engineering, 2024, 45(S1): 1-5. doi: 10.13832/j.jnpe.2024.S1.0001

Citation:

PDF( 8411 KB)

Research and Application of Transient Satistical Method for Nuclear Power Plant

doi: 10.13832/j.jnpe.2024.S1.0001

1.
Science and Technology on Reactor System Design Technology Laboratory, Nuclear Power Institute of China, Chengdu, 610213, China
2.
CNNC Nuclear Power Operation Management Co., Ltd., Haiyan, Zhejiang, 314300, China

Received Date: 2023-10-23
Rev Recd Date: 2024-03-14
Publish Date: 2024-06-15

Abstract

Abstract

The number of transient occurrences of nuclear power plants is closely related to the fatigue life of equipment, so transient statistics are of great significance for improving the level of intelligent operation and maintenance of nuclear power plants and the renewal of operation licenses. At present, transient statistical methods at home and abroad have the disadvantages of large training data and poor generalization ability, and are rarely used in engineering. In this paper, a transient classification method based on equivalent distance measurement is established according to the design transient variation law, and the automation of transient classification, segmentation and counting process is realized. The current transient classification method is verified by the operation data of nuclear power plants, and the results show that the current method can effectively realize the statistical work of various operating transients. The application of transient statistical method plays an important role in the improvement of the intelligence level of nuclear power plants and the continuation of operation permits.
- Nuclear power plant,
- Transient statistics,
- Transient classification,
- Transient segmentation,
- Transient identification

FullText(HTML)

References(21)

References

[1]	文静,房永刚,路燕,等. 核安全设备疲劳分析方法与步骤[J]. 原子能科学技术,2014, 48(1): 121-126.
[2]	陈明亚,余伟炜,薛飞,等. 基于三维应力分量的管道热疲劳监测数据分析[J]. 压力容器,2020, 37(1): 20-26,41.
[3]	赵传礼,施少波,栾兴峰,等. 稳压器波动管疲劳状态分析及对策[J]. 核动力工程,2022, 43(S1): 11-15.
[4]	崔怀明,唐传宝,白晓明,等. 华龙一号疲劳监测和瞬态统计系统研制[J]. 核动力工程,2023, 44(5): 80-84.
[5]	姜赫,石文翔,曹国畅,等. 瞬态监督和处理方法在核电厂运行许可证延续中的应用[J]. 核动力工程,2022, 43(S1): 40-43.
[6]	阮良成,俞忠德,陈忠武,等. 秦山第二核电厂2号机组汽轮机误快速降负荷瞬态分析[J]. 核动力工程,2007, 28(2): 82-86.
[7]	刘余,任春明,汤琪芬,等. 核电厂运行瞬态分析软件PANTO的研发[J]. 核技术,2017, 40(5): 050604.
[8]	KWON K C. HMM-based transient identification in dynamic process[J]. Transactions on Control, Automation and Systems Engineering, 2000, 2(1): 40-46.
[9]	KWON K C, KIM J H. Accident identification in nuclear power plants using hidden Markov models[J]. Engineering Applications of Artificial Intelligence, 1999, 12(4): 491-501. doi: 10.1016/S0952-1976(99)00011-1
[10]	KWON K C, KIM J H, SEONG P H. Hidden Markov model-based real-time transient identifications in nuclear power plants[J]. International Journal of Intelligent Systems, 2002, 17(8): 791-811. doi: 10.1002/int.10050
[11]	GOTTLIEB C, ARZHANOV V, GUDOWSKI W, et al. Feasibility study on transient identification in nuclear power plants using support vector machines[J]. Nuclear Technology, 2006, 155(1): 67-77. doi: 10.13182/NT06-A3746
[12]	MO K, LEE S J, SEONG P H. A dynamic neural network aggregation model for transient diagnosis in nuclear power plants[J]. Progress in Nuclear Energy, 2007, 49(3): 262-272. doi: 10.1016/j.pnucene.2007.01.002
[13]	MEDEIROS J A C C, SCHIRRU R. Identification of nuclear power plant transients using the particle swarm optimization algorithm[J]. Annals of Nuclear Energy, 2008, 35(4): 576-582. doi: 10.1016/j.anucene.2007.08.013
[14]	DE A MOL A, MARTINEZ A S, SCHIRRU R. A neural model for transient identification in dynamic processes with “don’t know” response[J]. Annals of Nuclear Energy, 2003, 30(13): 1365-1381. doi: 10.1016/S0306-4549(03)00072-0
[15]	MOL A C A, ALMEIDA J C S, PEREIRA C M N A, et al. Neural and genetic-based approaches to nuclear transient identification including ‘don’t know’ response[J]. Progress in Nuclear Energy, 2006, 48(3): 268-282. doi: 10.1016/j.pnucene.2005.07.002
[16]	常远,黄晓津,李春文,等. 基于模糊距离的核电厂瞬态分段识别方法[J]. 核动力工程,2014, 35(1): 106-109.
[17]	常远,郝轶,黄晓津,等. 基于模糊熵的核电站瞬态识别方法[J]. 原子能科学技术,2014, 48(9): 1640-1645.
[18]	GRUBBS F E. Sample criteria for testing outlying observations[J]. The Annals of Mathematical Statistics, 1950, 21(1): 27-58. doi: 10.1214/aoms/1177729885
[19]	白晓明,郑连纲,艾红雷,等. 基于趋势滤波的瞬态曲线协同分段线性化方法研究[J]. 核动力工程,2018, 39(2): 72-75.
[20]	李旭芳,段春林,张冬波,等. 遥测数据时间序列滑动窗口动态分割技术[J]. 飞行器测控学报,2015, 34(4): 345-349.
[21]	SAKOE H, CHIBA S. Dynamic programming algorithm optimization for spoken word recognition[J]. IEEE Transactions on Acoustics, Speech, and Signal Processing, 1978, 26(1): 43-49. doi: 10.1109/TASSP.1978.1163055