A novel channel selection method for CANDU refuelling based on the BPANN and GA techniques

Abstract A novel channel selection method for CANDU refuelling based on the back-propagation artificial neural network (BPANN) and genetic algorithm (GA) techniques is developed. In this method, GA is used as an “optimization tool” and BPANN as a refuelling “simulator” used to predict the core parameters. Based on this method an automatic refuelling channel selection program for CANDU reactors has been developed and tested by the refuelling simulation of the Qinshan Phase III CANDU reactor for 400 effective full power days. The numerical results show that the average properties of the time-dependent core are very close to the reference one and the refuelling channel selection method possesses superior computational efficiency.

[1]  H. Bonin.  Candu Pressurized Heavy Water Reactor Thorium-233U Oxide Fuel Evaluation Based on Optimal Fuel Management , 1987 .

[2]  X. Huo,et al.  Development of core fuel management code system for CANDU reactor based on coupled neutronics and thermal-hydraulic advanced nodal method , 2004 .

[3]  Zbigniew Michalewicz,et al.  Handbook of Evolutionary Computation , 1997 .

[4]  Geoffrey T. Parks,et al.  Multiobjective pressurized water reactor reload core design by nondominated genetic algorithm search , 1996 .

[5]  John H. Holland,et al.  Adaptation in Natural and Artificial Systems: An Introductory Analysis with Applications to Biology, Control, and Artificial Intelligence , 1992 .

[6]  V. Jagannathan,et al.  Quick and reliable estimation of power distribution in a PHWR by ANN , 1998 .

[7]  Christian Igel,et al.  Empirical evaluation of the improved Rprop learning algorithms , 2003, Neurocomputing.

[8]  Soon Heung Chang,et al.  PRESSURIZED WATER-REACTOR CORE PARAMETER PREDICTION USING AN ARTIFICIAL NEURAL NETWORK , 1993 .

[9]  Adem Erdoğan,et al.  A PWR reload optimisation code (XCore) using artificial neural networks and genetic algorithms , 2003 .

[10]  Roberto Schirru,et al.  A new approach to the use of genetic algorithms to solve the pressurized water reactor's fuel management optimization problem , 1999 .

[11]  Chang Joon Jeong.  An on-line fuel management method using in-core detector readings for CANDU reactors , 2002 .

[12]  Donald A. Waterman,et al.  A Guide to Expert Systems , 1986 .

[13]  Hangbok Choi.  A fast-running fuel management program for a CANDU reactor , 2000 .

[14]  Taiji Maruyama,et al.  INSIGHT: An Integrated Scoping Analysis Tool for In-core Fuel Management of PWR , 1997 .

[15]  Wei Shen,et al.  A Parametric Study of the DUPIC Fuel Cycle to Reflect Pressurized Water Reactor Fuel Management Strategy , 2001 .

[16]  Geoffrey T. Parks,et al.  Application of genetic algorithms to in-core nuclear fuel management optimization , 1993 .

[17]  Robert J. Schalkoff,et al.  Artificial neural networks , 1997 .

[18]  D. McNabb,et al.  The Application of Generalized Perturbation Theory and Mathematical Programming to Equilibrium Refueling Studies of a CANDU Reactor , 1981 .

[19]  David E. Goldberg,et al.  Genetic Algorithms in Search Optimization and Machine Learning , 1988 .

[20]  Toru Yamamoto,et al.  Development of neural network for analysis of local power distributions in BWR fuel bundles , 1993 .