Nuclear Reactor Reactivity Prediction Using Feed Forward Artificial Neural Networks

  • Authors:

  • Shan Jiang;Christopher C. Pain;Jonathan N. Carter;Ahmet K. Ziver;Matthew D. Eaton;Anthony J. Goddard;Simon J. Franklin;Heather J. Phillips

  • Affiliations:

  • Applied Modelling and Computation Group, Department of Earth Science and Engineering, Imperial College London, U.K;Applied Modelling and Computation Group, Department of Earth Science and Engineering, Imperial College London, U.K;Applied Modelling and Computation Group, Department of Earth Science and Engineering, Imperial College London, U.K;RM Consultant, Abingdon, U.K;Applied Modelling and Computation Group, Department of Earth Science and Engineering, Imperial College London, U.K;Applied Modelling and Computation Group, Department of Earth Science and Engineering, Imperial College London, U.K;Imperial College Reactor Centre, Berkshire, U.K;Imperial College Reactor Centre, Berkshire, U.K

  • Venue:
  • ISNN '08 Proceedings of the 5th international symposium on Neural Networks: Advances in Neural Networks
  • Year:
  • 2008

Quantified Score

Hi-index 0.00

Visualization

Abstract

In this paper, a feed forward artificial neural network (ANN) is used to predict the effective multiplication factor (keff), an indication of the reactivity of a nuclear reactor, given a fuel Loading Pattern (LP). In nuclear engineering, the keffis normally calculated by running computer models, e.g. Monte Carlo model and finite element model, which can be very computationally expensive. In case that a large number of reactor simulations is required, e.g. searching for the optimal LP that maximizes the keffin a solution space of 1010to 10100, the computational time may not be practical. A feed forward ANN is then trained to perform fast and accurate keffprediction, by using the known LPs and corresponding keffs. The experiments results show that the proposed ANN provides accurate, fast and robust keffpredictions.