Predicting the core thermal hydraulic parameters with a gated recurrent unit model based on the soft attention mechanism
0
조회
0
다운로드
0
인용
0
참고문헌
키워드
초록
Accurately predicting the thermal hydraulic parameters of a transient reactor core under different working conditions is the first step toward reactor safety. Mass flow rate and temperature are important parameters of core thermal hydraulics, which have often been modeled as time series prediction problems. This study aims to achieve accurate and continuous prediction of core thermal hydraulic parameters under instantaneous conditions, as well as test the feasibility of a newly constructed gated recurrent unit (GRU) model based on the soft attention mechanism for core parameter predictions. Herein, the China Experimental Fast Reactor (CEFR) is used as the research object, and CEFR 1/2 core was taken as subject to carry out continuous predictive analysis of thermal parameters under transient conditions., while the subchannel analysis code named SUBCHANFLOW is used to generate the time series of core thermal-hydraulic parameters. The GRU model is used to predict the mass flow and temperature time series of the core. The results show that compared to the adaptive radial basis function neural network, the GRU network model produces better prediction results. The average relative error for temperature is less than 0.5 % when the step size is 3, and the prediction effect is better within 15 s. The average relative error of mass flow rate is less than 5 % when the step size is 10, and the prediction effect is better in the subsequent 12 s. The GRU model not only shows a higher prediction accuracy, but also captures the trends of the dynamic time series, which is useful for maintaining reactor safety and preventing nuclear power plant accidents. Furthermore, it can provide long-term continuous predictions under transient reactor conditions, which is useful for engineering applications and improving reactor safety
Abstract
Accurately predicting the thermal hydraulic parameters of a transient reactor core under different working conditions is the first step toward reactor safety. Mass flow rate and temperature are important parameters of core thermal hydraulics, which have often been modeled as time series prediction problems. This study aims to achieve accurate and continuous prediction of core thermal hydraulic parameters under instantaneous conditions, as well as test the feasibility of a newly constructed gated recurrent unit (GRU) model based on the soft attention mechanism for core parameter predictions. Herein, the China Experimental Fast Reactor (CEFR) is used as the research object, and CEFR 1/2 core was taken as subject to carry out continuous predictive analysis of thermal parameters under transient conditions., while the subchannel analysis code named SUBCHANFLOW is used to generate the time series of core thermal-hydraulic parameters. The GRU model is used to predict the mass flow and temperature time series of the core. The results show that compared to the adaptive radial basis function neural network, the GRU network model produces better prediction results. The average relative error for temperature is less than 0.5 % when the step size is 3, and the prediction effect is better within 15 s. The average relative error of mass flow rate is less than 5 % when the step size is 10, and the prediction effect is better in the subsequent 12 s. The GRU model not only shows a higher prediction accuracy, but also captures the trends of the dynamic time series, which is useful for maintaining reactor safety and preventing nuclear power plant accidents. Furthermore, it can provide long-term continuous predictions under transient reactor conditions, which is useful for engineering applications and improving reactor safety
참고문헌 (25)
- Q. Lu, "Prediction method for thermal-hydraulic parameters of nuclear reactor system based on deep learning algorithm", Appl. Therm. Eng, 196, pp.117272~ (2021)
- Shuang Jin, "Optimization method of CFD coarse grid numerical simulation based on neural network", Nucl. Sci. Tech, 44(6), pp.77~83 (2021)
- Shixian Li, "Fault diagnosis of LOCA based on ANN methods", Nucl. Sci. Tech, 40(8), pp.91~98 (2017)
- Hanying Chen, "Methodology Research on Condition Prognosis and Diagnosis of Nuclear Power Plant Thermal-Hydraulic System", pp.2018
- Junyoung Chung, "Empirical evaluation of gated recurrent neural networks on sequence modeling", NIPS 2014 Workshop on Deep Learning (2014)
- Xin Tan, "Research on Harmonic Current Detection and Suppression Technology Based on RBF Neural Network", pp.2022
- Xianbing Chen, "Study of Simulated Coupled Neutronic-Thermo-Hydraulic Low Pressure Natural Circulation Flow Instability", pp.2019
- Xiaojian Wu, "LSTM-GRU vehicle trajectory prediction based on Dropout and attention mechanism", J. Hunan Univ, 50(4), pp.65~75 (2023)[DOI]
- X. Zhu, "An empirical study of spatial attention mechanisms in deep networks", Proc. IEEE, 2019, 6688~6697
- M. Shoaib, "Comparative study of different wavelet based neural network models for rainfall–runoff modeling", J. Hydrol, 515, pp.47~58 (2014)
- Yan Sun, "Phase prediction of measurement and control equipment based on optimized GRU model under historical data", J. Measurement and Control Technol, 42(1), pp.16~20 (2023)[DOI]
- D. François, "Resampling methods for parameter free and robust feature selection with mutual information", Neurocomputing, 70(7–9), pp.1276~1288 (2007)
- C. X. J. Feng, "Threefold vs. fivefold cross validation in one-hidden-layer and two-hidden-layer predictive neural network modeling of machining surface roughness data", J. Manuf. Syst, 24(2), pp.93~107 (2005)
- L. Du, "How much deep learning does neural style transfer really need? an ablation study", Proceedings of the IEEE, 2020, 3150~3159
- S. Chen, "Exploring the attention mechanism in LSTM-based Hong Kong stock price movement prediction", Quant. Finance, 19(9), pp.1507~1515 (2019)
- J. Fei, "Adaptive sliding mode control of dynamic system using RBF neural network", Nonlinear Dynam, 70, pp.1563~1573 (2012)
- Sepp Hochreiter, "Long short-term memory", Neural Comput, 9(8), pp.1735~1780 (1997)[DOI]
- Xiaoying Huangfu, "A review of deep neural networks combined with attention mechanism", Comput. Mod, (2), pp.40~57 (2023)
- J. I. Nan, "Research on adaptive RBF neural network prediction method for core thermal-hydraulic parameters of fast reactor", Nucl. Sci. Tech, 45(9), pp.69~78 (2022)
- G. P. Nason, "Wavelets and Statistics", pp.261~280 (1995), Springer
- P. R. Prakash, "A novel convolutional neural network with gated recurrent unit for automated speech emotion recognition and classification", J. Control and Decision, 10(1), pp.54~63 (2023)
- Jiao Wei, "Application of Machine Learning Algorithm in Rapid Prediction of Multiphase Thermal Hydraulic parameters", pp.2022