Research on Multi-source Heterogeneous Fault Characterization Method for Reactor Coolant Pump

Xu Renyi; Wang Yan; Kuang Chengxiao; Wu Kelin; Su Shu; Tan Xin

doi:10.13832/j.jnpe.2025.S1.0066

Volume 46 Issue S1

Jul. 2025

Turn off MathJax

Article Contents

Article Navigation > Nuclear Power Engineering > 2025 > 46(S1): 66-74

Xu Renyi, Wang Yan, Kuang Chengxiao, Wu Kelin, Su Shu, Tan Xin. Research on Multi-source Heterogeneous Fault Characterization Method for Reactor Coolant Pump[J]. Nuclear Power Engineering, 2025, 46(S1): 66-74. doi: 10.13832/j.jnpe.2025.S1.0066

Citation:

Xu Renyi, Wang Yan, Kuang Chengxiao, Wu Kelin, Su Shu, Tan Xin. Research on Multi-source Heterogeneous Fault Characterization Method for Reactor Coolant Pump[J]. Nuclear Power Engineering, 2025, 46(S1): 66-74. doi: 10.13832/j.jnpe.2025.S1.0066

Citation:

PDF( 23406 KB)

Research on Multi-source Heterogeneous Fault Characterization Method for Reactor Coolant Pump

doi: 10.13832/j.jnpe.2025.S1.0066

Xu Renyi^1
,,
Wang Yan^{1, 2
,
,},
Kuang Chengxiao¹,
Wu Kelin³,
Su Shu¹,
Tan Xin¹

1.
National Key Laboratory of Nuclear Reactor Technology, Nuclear Power Institute of China, Chengdu, 610213, China
2.
College of Electronics and Information Engineering, Sichuan University, Chengdu, 610065, China
3.
College of Energy Engineering, Zhejiang University, Hangzhou, 310027, China

Received Date: 2024-08-30
Rev Recd Date: 2025-03-10
Publish Date: 2025-07-09

Abstract

Abstract

Aiming at the problems of high-frequency sensing signal modulation, noise interference, and the low fault recognition rate and lack of evidence in single-sensor fault diagnosis for nuclear power plant reactor coolant pumps (RCPs), this paper proposes a method of multi-source heterogeneous fault characterization for RCPs based on cyclic stationary analysis and D-S evidence theory. By using time domain analysis and cyclic stationary analysis to process the high frequency sensor data, the signal demodulation and denoising are realized, and the feature parameters are calculated to construct the feature vector. And then, multi-source sensing data is fused based on D-S evidence theory, and the typical fault diagnosis of RCPs is realized at decision level according to the fusion results. The experimental verification results show that the fusion of multi-source sensing information can significantly improve the diagnosis rate of typical RCP faults, and improve the interpretability of diagnosis results. The relevant research results can provide a reference for the predictive maintenance of RCPs, and improve the operation reliability and intelligent operation and maintenance level of RCPs in nuclear power plants.
- Reactor coolant pump,
- Cyclic stationary analysis,
- D-S evidence theory,
- Fault detection and diagnosis

FullText(HTML)

References(12)

References

[1]	张金豹,邹天刚,王敏,等. 滚动轴承剩余使用寿命预测综述[J]. 机械科学与技术,2023, 42(1): 1-23.
[2]	晏云海,郭瑜,伍星. 基于循环谱分析的鲁棒性滚动轴承故障特征提取方法[J]. 振动与冲击,2022, 41(6): 1-7.
[3]	陈科,段伟建,吴胜利,等. 多深度学习模型决策融合的齿轮箱故障诊断分类方法[J]. 科学技术与工程,2022, 22(12): 4804-4811. doi: 10.3969/j.issn.1671-1815.2022.12.016
[4]	LIN Y, LI Y Y, YIN X H, et al. Multisensor fault diagnosis modeling based on the evidence theory[J]. IEEE Transactions on Reliability, 2018, 67(2): 513-521. doi: 10.1109/TR.2018.2800014
[5]	李洋,赵鸣,徐梦瑶,等. 多源信息融合技术研究综述[J]. 智能计算机与应用,2019, 9(5): 186-189.
[6]	蒋雯,邓鑫洋. D-S证据理论信息建模与应用[M]. 北京: 科学出版社,2018: 16-20.
[7]	周志杰,唐帅文,胡昌华,等. 证据推理理论及其应用[J]. 自动化学报,2021, 47(5): 970-984.
[8]	ANTONI J, XIN G, HAMZAOUI N. Fast computation of the spectral correlation[J]. Mechanical Systems and Signal Processing, 2017, 92: 248-277. doi: 10.1016/j.ymssp.2017.01.011
[9]	DEMPSTER A P. Upper and lower probabilities induced by a multivalued mapping[J]. The Annals of Mathematical Statistics, 1967, 38(2): 325-339. doi: 10.1214/aoms/1177698950
[10]	SHAFER G. A mathematical theory of evidence[M]. Princeton: Princeton University Press, 1976:39-40.
[11]	ZHANG H P, DENG Y. Engine fault diagnosis based on sensor data fusion considering information quality and evidence theory[J]. Advances in Mechanical Engineering, 2018, 10(11): 1687814018809184.
[12]	WANG S N, TANG Y C. An improved approach for generation of a basic probability assignment in the evidence theory based on Gaussian distribution[J]. Arabian Journal for Science and Engineering, 2022, 47(2): 1595-1607. doi: 10.1007/s13369-021-06011-w