Application of Neural Network-Genetic Composite Algorithm in Core Refueling Design for PWR

被引：0
|
作者：
Wei Z. [1 ]
Wang D. [2 ]
Wang D. [2 ]
Pan C. [1 ]
机构：
[1] China Institute of Atomic Energy, Beijing
[2] Graduate School of CNNC, Beijing
来源：
Yuanzineng Kexue Jishu/Atomic Energy Science and Technology | 2020年 / 54卷 / 05期
关键词：
Adaptive BP neural network; Core refueling optimization; Genetic algorithm;
D O I：
10.7538/yzk.2019.youxian.0788
中图分类号：
学科分类号：
摘要：
The neural network model was trained by large-scale data, to accurately predict effective multiplication factor (keff), component power crest factor (Rad) and rod power crest factor (FΔH) of the nuclear reactor core, which were used for core refueling optimization. The improved genetic algorithm can obtain the best solution quickly, and solve time-consuming and cost-effectiveness problem. In modeling of core loading mode, the binary vector was designed as the input parameter, which effectively reduced the neural network complexity and improved the prediction accuracy. In the search of optimal scheme, the genetic algorithm with unique crossover operator and selection operator ensured that the search results were in the feasible region, and improved the search efficiency. The theoretical analysis and numerical experiment results show that, one-hidden-layer adaptive BP network predicts keff data well, while three-hidden-layer adaptive BP network is more suitable for Rad and FΔH data. Then the ideal core refueling schemes are obtained by the genetic algorithm. These practices are expected to promote a further application of artificial intelligence algorithms in the nuclear industry. © 2020, Editorial Board of Atomic Energy Science and Technology. All right reserved.
引用
收藏
页码：825 / 834
页数：9
相关论文
共 11 条
  • [1] Yao H., Fuel management study on PWR core included of 157 fuel assemblies, Atomic Energy Science and Technology, 47, 10, pp. 1845-1851, (2013)
  • [2] Kim T.K., Kim C.H., Mixed integer programming for pressurized water reactor fuel-loading-pattern optimization, Nuclear Science and Engineering, 127, pp. 346-357, (1997)
  • [3] Parks G.T., Multiobjective pressurized water reactor reload core design by nondominated genetic algorithm search, Nuclear Science and Engineering, 124, pp. 178-187, (1996)
  • [4] Kropaczek D.J., Turinsky P.J., In-core nuclear fuel management optimization for pressurized water reactors utiling simulated annealing, Nuclear Technology, 95, pp. 9-32, (1991)
  • [5] Yang B., Wu H., Wang L., Application of simulated annealing algorithms in the optimization of pressurized water reactor reloading pattern, Nuclear Power Engineering, 24, 4, pp. 327-331, (2003)
  • [6] Chapot J.L.C., Silva F.C.D., Schirru R., A new approach to the use of genetic algorithms to solve the pressurized water reactor's fuel management optimization problem, Annals of Nuclear Energy, 26, 7, pp. 641-655, (1999)
  • [7] Wang T., Xie Z., New hybrid optimization method and its application to pressurized water reactors reloading optimization, Journal of Xi'an Jiaotong University, 39, 5, pp. 522-525, (2005)
  • [8] Liu S., Cai J., Study on fuel loading pattern optimization for a pressurized water reactor using particles warm method, Nuclear Power Engineering, 34, 5, pp. 1-5, (2013)
  • [9] Kim H.G., Heung S., Lee B.H., Pressurized water reactor core parameter prediction using an artificial neural network, Foreign Nuclear Power, 6, pp. 49-55, (1996)
  • [10] Wang D., Wang W., Pan C., Et al., Prediction of core parameters of Qinshan Ⅱ PWR by adaptive BP neural network method, Atomic Energy Science and Technology, 54, 1, pp. 112-118, (2020)
12