Dynamic Liquid Level Prediction of Steam Generator under Main Steam Pipe Rupture Accidents

YIN Yuzhuo; WANG Biaoxin; LIN Mei; WANG Qiuwang

doi:10.7652/xjtuxb202508014

您当前的位置：

首页 >

文章列表页 >

Dynamic Liquid Level Prediction of Steam Generator under Main Steam Pipe Rupture Accidents

更新时间：2025-07-30

- Dynamic Liquid Level Prediction of Steam Generator under Main Steam Pipe Rupture Accidents
- Journal of Xi’an Jiaotong University Vol. 59, Issue 8, Pages: 147-157(2025)
- 作者机构：
  
  西安交通大学能源与动力工程学院， 710049，西安
- 作者简介：
- 基金信息：
- DOI：10.7652/xjtuxb202508014
  CLC： TL375.1
- Received：27 February 2025，
  
  Online First：28 April 2025，
  
  Published：10 August 2025
- 稿件说明：
移动端阅览
YIN Yuzhuo, WANG Biaoxin, LIN Mei, et al. Dynamic Liquid Level Prediction of Steam Generator under Main Steam Pipe Rupture Accidents[J]. Journal of Xi’an Jiaotong University, 2025, 59(8): 147-157.
DOI：

YIN Yuzhuo, WANG Biaoxin, LIN Mei, et al. Dynamic Liquid Level Prediction of Steam Generator under Main Steam Pipe Rupture Accidents[J]. Journal of Xi’an Jiaotong University, 2025, 59(8): 147-157. DOI： 10.7652/xjtuxb202508014.

摘要

为提升蒸汽发生器液位监测的实时性与准确性，以保障核动力系统安全运行，提出了主蒸汽管道破裂事故下蒸汽发生器的动态液位预测方法。首先，通过模拟主蒸汽管道破裂工况进行实验，采用AP1000蒸汽发生器缩比建模，结合电动球阀控制与高速相机图像识别，实现了液位与关键热工参数采集；接着，构建了液位时间序列集并进行了小波分解和相关性分析，研究了液位本身的时频特征以及与热工参数之间的关系；最后，建立了基于Informer、深度线性网络（DLinear）的深度学习液位预测模型，并进行了预测结果的对比分析。结果显示，DLinear模型在预测精度与模型鲁棒性方面均优于Informer模型，能更准确地反映液位剧烈波动特征，验证了其在处理长时序依赖问题中的适用性与优势。DLinear模型在均方误差、平均绝对误差和决定系数上较Informer模型分别提升了24.9%、16.0%、9.3%，在±5 mm误差范围内预测准确率达到81.5%，不仅能更好地捕捉液位细节变化，还表现出更强的鲁棒性与泛化能力。研究验证了DLinear模型在液位预测任务中的高效性与工程应用潜力，为核电站事故预警和智能监测提供技术支持。

Abstract

To enhance the real-time and accurate monitoring of liquid levels in steam generators during main steam pipe rupture accidents

thereby ensuring the safe operation of nuclear power systems

a dynamic liquid level prediction method is proposed. First

experiments simulating main steam pipe rupture conditions are conducted using a scaled model of the AP1000 steam generator. This involves the integration of electric ball valve control and high-speed camera image recognition to collect data on liquid levels and key thermal parameters. Next

a liquid level time series dataset is constructed

followed by wavelet decomposition and correlation analysis to examine the time-frequency characteristics of the liquid level itself and its relationship with thermal parameters. Finally

a deep learning liquid level prediction model based on Informer and DLinear is established to perform a comparative analysis of the prediction results. The results indicate that the DLinear model outperforms the Informer model in terms of prediction accuracy and model robustness

accurately reflecting the characteristics of severe liquid level fluctuations and demonstrating its suitability and advantages in handling long-term sequence dependency issues. The DLinear model improves the mean squared error

mean absolute error

and coefficient of determination by 24.9%

16.0%

and 9.3%

respectively

compared to the Informer model. It achieves a prediction accuracy of 81.5% within a ±5 mm error range

capturing detailed changes in liquid levels while exhibiting stronger robustness and generalization ability. This study verifies the efficiency and engineering application potential of the DLinear model in liquid level prediction tasks

providing technical support for accident warnings and intelligent monitoring in nuclear power plants.

关键词

Keywords

references

李冬生 . 主蒸汽管道破裂事故的安全评价 [J ] . 核动力工程 , 1997 , 18 ( 4 ): 303 - 306 .

LI Dongsheng . Safety assessment of main steam line break accidents [J ] . Nuclear Power Engineering , 1997 , 18 ( 4 ): 303 - 306 .

LIU Li , YING Bingbin . Effect of water level on performance of swirl-vane separator and steam dryer in PWR SG [J ] . Nuclear Engineering and Design , 2020 , 370 : 110918 .

俞尔俊 . 秦山核电厂主蒸汽管道破裂事故的分析研究 [J ] . 原子能科学技术 , 1989 , 23 ( 5 ): 15 - 22 .

YU Erjun . Analysis for postulated mainsteam line break accident in Qinshan nuclear power plant [J ] . Atomic Energy Science and Technology , 1989 , 23 ( 5 ): 15 - 22 .

KONG Xiangsong , SHI Changqing , LIU Hang , et al . Performance optimization of a steam generator level control system via a revised simplex search-based data-driven optimization methodology [J ] . Processes , 2022 , 10 ( 2 ): 264 .

KOTHARE M V , METTLER B , MORARI M , et al . Level control in the steam generator of a nuclear power plant [J ] . IEEE Transactions on Control Systems Technology , 2000 , 8 ( 1 ): 55 - 69 .

CHEN Yongwei , XIE Yongjing , LI Yonggang , et al . Full-range steam generator's water level model and analysis method based on cross-calculation [J ] . Progress in Nuclear Energy , 2021 , 133 : 103635 .

WILSON E D , CLAIRON Q , TAYLOR C J . Non-minimal state-space polynomial form of the Kalman filter for a general noise model [J ] . Electronics Letters , 2018 , 54 ( 4 ): 204 - 206 .

TATJEWSKI P . Offset-free nonlinear model predictive control with state-space process models [J ] . Archives of Control Sciences , 2017 , 27 ( 4 ): 595 - 615 .

WANG Youqing , FANG Mengqi , JIANG Xu , et al . Intensive insulin therapy for critically ill subjects based on direct data-driven model predictive control [J ] . Journal of Process Control , 2014 , 24 ( 5 ): 493 - 503 .

曾碧凡 , 吴婕 , 武万强 , 等 . 基于遗传算法的核电站蒸汽发生器水位动态滑模控制 [J ] . 热力发电 , 2016 , 45 ( 8 ): 43 - 48 .

ZENG Bifan , WU Jie , WU Wanqiang , et al . Genetic algorithm based dynamic sliding mode water level control for steam generators in nuclear power stations [J ] . Thermal Power Generation , 2016 , 45 ( 8 ): 43 - 48 .

CHO B H , NO H C . Design of stability-guaranteed fuzzy logic controller for nuclear steam generators [J ] . IEEE Transactions on Nuclear Science , 1996 , 43 ( 2 ): 716 - 730 .

DONG Wei , DOSTER J M , MAYO C W . Steam generator control in nuclear power plants by water mass inventory [J ] . Nuclear Engineering and Design , 2008 , 238 ( 4 ): 859 - 871 .

DEMERDASH N A , EL-HAMEED M A , EISAWY E A , et al . Optimal feed-water level control for steam generator in nuclear power plant based on meta-heuristic optimization [J ] . Journal of Radiation Research and Applied Sciences , 2020 , 13 ( 1 ): 468 - 484 .

RODRÍGUEZ-ABREO O , RODRÍGUEZ-RESÉNDIZ J , FUENTES-SILVA C , et al . Self-tuning neural network PID with dynamic response control [J ] . IEEE Access , 2021 , 9 : 65206 - 65215 .

SHE Jingke , WANG Jiani , YANG Suyuan , et al . The design and implementation of an LSTM-based steam generator level prediction model [C ] // Nuclear Power Plants: Innovative Technologies for Instrumentation and Control Systems . Singapore : Springer Singapore , 2021 : 505 - 517 .

STEFANOVA A , GROUDEV P , SANCHEZ-ESPINOZA V H , et al . Comparison of MSLB transient results using the 3D coupled code TRACEv5p05/PARCS and the system thermal hydraulic code RELAP5 [J ] . Annals of Nuclear Energy , 2024 , 203 : 110518 .

STEFANOVA A , GROUDEV P . Comparison of VVER1000 plant respond during MSLB scenario using TRACE and RELAP computer codes [C ] // IOP Conference Series: Earth and Environmental Science . Bristol, UK : IOP Publishing , 2024 : 012022 .

YANG Ye , HU Mengyan , ZHANG Xueyan , et al . Analysis of main steam line break accident on a BWR test facility using TRACE [J ] . Nuclear Engineering and Design , 2024 , 416 : 112765 .

CHEN Jianhao , HUANG Zhiwen , HU Bin , et al . Visualization and monitoring dynamic water levels of steam generators based on deep learning [J ] . Progress in Nuclear Energy , 2024 , 169 : 105052 .

WANG Biaoxin , JIANG Yuang , LIN Mei , et al . Prediction of steam generator liquid level under main steam line break accident based on wavelet decomposition combined with deep learning [J ] . Nuclear Engineering and Design , 2025 , 436 : 113998 .

BHOWMIK P K , SABHARWALL P , JOHNSON J T , et al . Scaling methodologies and similarity analysis for thermal hydraulics test facility development for water-cooled small modular reactor [J ] . Nuclear Engineering and Design , 2024 , 424 : 113235 .

RHIF M , BEN ABBES A , FARAH I R , et al . Wavelet transform application for/in non-stationary time-series analysis: a review [J ] . Applied Sciences , 2019 , 9 ( 7 ): 1345 .

ZHOU Haoyi , ZHANG Shanghang , PENG Jieqi , et al . Informer: beyond efficient transformer for long sequence time-series forecasting [C ] // Proceedings of the AAAI Conference on Artificial Intelligence . Palo Alto, CA, USA : AAAI Press , 2021 : 11106 - 11115 .

ZENG Ailing , CHEN Muxi , ZHANG Lei , et al . Are transformers effective for time series forecasting? [C ] // Proceedings of the AAAI Conference on Artificial Intelligence . Palo Alto, CA, USA : AAAI Press , 2023 : 11121 - 11128 .

LEI Jichong , REN Changan , LI Wei , et al . Prediction of crucial nuclear power plant parameters using long short-term memory neural networks [J ] . International Journal of Energy Research , 2022 , 46 ( 15 ): 21467 - 21479 .

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Intelligent Quantitative Non-Destructive Evaluation Method for Delamination of Carbon Fiber Composite Tube with Mirror-Reflection Infrared Thermography

Model Predictive Control-Oriented Deep Koopman Global Linear Modeling Method for Wind Turbines

A Pure Convolutional Model Fused with U-net Network for Video Prediction

Application of Interpretable Convolutional Neural Network Enabled by Bi-Damped Wavelets in Bearing Fault Diagnosis

Intelligent Non-destructive Quantitative Evaluation Method for Delamination of Carbon Fiber Composite Tube with Mirror-reflection Infrared Thermography

Related Author

YANG Yang

CHEN Hongen

LIU Bofan

TONG Zongfei

PEI Cuixiang

CHEN Zhenmao

TIAN Runze

KOU Peng

Related Institution

School of Aerospace Engineering，Xi’an Jiaotong University

State Key Laboratory for Strength and Vibration of Mechanical Structures，Xi’an Jiaotong University

Shaanxi Engineering Research Center of Nondestructive Testing and Structural Integrity Evaluation，Xi’an Jiaotong University

Northern Branch, Beijing Jingneng International Holding Co., Ltd.

State Key Laboratory of Electrical Insulation and Power Equipment, Xi'an Jiaotong University

⁰