EBaLM-THP : A neural network thermohydraulic prediction model of advanced nuclear system components

In lieu of the worldwide energy demand, economics and consensus concern regarding climate change, nuclear power – specifically near-term nuclear power plant designs are receiving increased engineering attention. However, as the nuclear industry is emerging from a lull in component modeling and analyses, optimization for example using ANN has received little research attention. This paper presents a neural network approach, EBaLM, based on a specific combination of two training algorithms, error-back propagation (EBP), and Levenberg–Marquardt (LM), applied to a problem of thermohydraulics predictions (THPs) of advanced nuclear heat exchangers (HXs). The suitability of the EBaLM-THP algorithm was tested on two different reference problems in thermohydraulic design analysis; that is, convective heat transfer of supercritical CO2 through a single tube, and convective heat transfer through a printed circuit heat exchanger (PCHE) using CO2. Further, comparison of EBaLM-THP and a polynomial fitting approach was considered. Within the defined reference problems, the neural network approach generated good results in both cases, in spite of highly fluctuating trends in the dataset used. In fact, the neural network approach demonstrated cumulative measure of the error one to three orders of magnitude smaller than that produce via polynomial fitting of 10th order.

[1]  Lefteri H. Tsoukalas,et al.  Hybrid fuzzy-neural flow identification methodology , 1996, Proceedings of IEEE 5th International Fuzzy Systems.

[2]  David A. Petti,et al.  The Next Generation Nuclear Plant , 2009 .

[3]  Xiang Ling,et al.  Optimal design approach for the plate-fin heat exchangers using neural networks cooperated with genetic algorithms , 2008 .

[4]  Yasuyoshi Kato,et al.  High performance printed circuit heat exchanger , 2007 .

[5]  P. S. Sastry,et al.  Numerical simulation and artificial neural network modeling of natural circulation boiling water reactor , 2007 .

[6]  D. A. Reay.  Compact heat exchangers: A review of current equipment and R&D in the field , 1994 .

[7]  M. Boroushaki,et al.  Simulation of nuclear reactor core kinetics using multilayer 3-D cellular neural networks , 2005, IEEE Transactions on Nuclear Science.

[8]  Kenneth Levenberg.  A METHOD FOR THE SOLUTION OF CERTAIN NON – LINEAR PROBLEMS IN LEAST SQUARES , 1944 .

[9]  F. H. Southworth,et al.  The Next Generation Nuclear Plant (NGNP) Project , 2003 .

[10]  Lefteri H. Tsoukalas,et al.  Vertical two-phase flow identification using advanced instrumentation and neural networks , 1998 .

[11]  Belle R. Upadhyaya,et al.  Sensor validation for power plants using adaptive backpropagation neural network , 1990 .

[12]  Frank P. Incropera,et al.  Fundamentals of Heat and Mass Transfer , 1981 .

[13]  Roh Myung-Sub,et al.  Thermal power prediction of nuclear power plant using neural network and parity space model , 1991 .

[14]  Kemal Ermis,et al.  ANN modeling of compact heat exchangers , 2008 .

[15]  Jacek M. Zurada,et al.  Introduction to artificial neural systems , 1992 .

[16]  Lefteri H. Tsoukalas,et al.  Fuzzy and neural approaches in engineering , 1997 .

[17]  R. L. Pierres,et al.  Heat Exchangers for the Next Generation of Nuclear Reactors , 2006 .

[18]  Hoseok Song,et al.  Investigations of a printed circuit heat exchanger for supercritical CO2 and water , 2007 .

[19]  Y. Kato,et al.  Printed circuit heat exchanger thermal–hydraulic performance in supercritical CO2 experimental loop , 2006 .

[20]  Mihir Sen,et al.  Simulation of heat exchanger performance by artificial neural networks , 1999 .

[21]  Lefteri H. Tsoukalas,et al.  Flow regime identification methodology with neural networks and two-phase flow models , 2001 .

[22]  D. Marquardt.  An Algorithm for Least-Squares Estimation of Nonlinear Parameters , 1963 .

[23]  D. P. Sekulic,et al.  Fundamentals of Heat Exchanger Design , 2003 .

[24]  Z. Guo,et al.  Nuclear power plant performance study by using neural networks , 1991, Conference Record of the 1991 IEEE Nuclear Science Symposium and Medical Imaging Conference.

[25]  Paul J. Werbos,et al.  The roots of backpropagation , 1994 .

[26]  Pei-Xue Jiang,et al.  A Computational Study of Convection Heat Transfer to CO2 at Supercritical Pressures in a Vertical Mini Tube , 2004 .

[27]  Kenji Fukuda,et al.  Analysis of the critical heat flux in round vertical tubes under low pressure and flow oscillation conditions. Applications of artificial neural network , 2003 .

[28]  N. Vaziri,et al.  Critical heat flux prediction by using radial basis function and multilayer perceptron neural networks: A comparison study , 2007 .

[29]  Rodney L. McClain,et al.  Neural network analysis of fin-tube refrigerating heat exchanger with limited experimental data , 2001 .