Nuclear reactor dynamics on-line estimation by Locally Recurrent Neural Networks

作者：Zio Enrico^*; Broggi Matteo; Pedroni Nicola

来源：Progress in Nuclear Energy, 2009, 51(3): 573-581.

DOI：10.1016/j.pnucene.2008.11.006

• Infinite Impulse Response-Locally Recurrent Neural Network (IIR-LRNN)
• Causal Recursive Back-Propagation (CRBP) algorithm
• On-line training
• Nonlinear dynamics
• Lead-Bismuth Eutectic-eXperimental
• Accelerator Driven System (LBE-XADS)
• Transient recovery

In this paper, the Causal Recursive Back-Propagation (CRBP) algorithm is employed to train on-line an Infinite Impulse Response-Locally Recurrent Neural Network (IIR-LRNN) for modelling the dynamics of a next-generation nuclear reactor. The results demonstrate the advantages of the on-line training over the batch-mode learning in the reconstruction of complex nonlinear dynamic relationships.

• 出版日期2009-4
• 单位中国地震局工程力学研究所