Abstract
FUELCON is an expert system in nuclear engineering. Its task is optimized refueling-design, which is crucial to keep down operation costs at a plant. FUELCON proposes sets of alternative configurations of fuel-allocation; the fuel is positioned in a grid representing the core of a reactor. The practitioner of in-core fuel management uses FUELCON to generate a reasonably good configuration for the situation at hand. The domain expert, on the other hand, resorts to the system to test heuristics and discover new ones, for the task described above. Expert use involves a manual phase of revising the ruleset, based on performance during previous iterations in the same session. This paper is concerned with a new phase: the design of a neural component to carry out the revision automatically. Such an automated revision considers previous performance of the system and uses it for adaptation and learning better rules. The neural component is based on a particular schema for a symbolic to recurrent-analogue bridge, called NIPPL, and on the reinforcement learning of neural networks for the adaptation.
Similar content being viewed by others
References
Galperin, A.; Kimhi, Y.; Nissan, E. (1993). FUELCON: an expert system for assisting the practice and research of in-core fuel management and optimal design in nuclear engineering, Computers and Artificial Intelligence, 12, 369–415
Kimhi, Y. (1992) A non-algorithmic approach to the in-core fuel management problem of a PWR core, PhD dissertation, Department of Nuclear Engineering, Ben-Gurion University of the Negev (Beer-Sheva, Israel) (in Hebrew; English abstract)
Galperin, A.; Kimhi, Y. (1991) Application of knowledge-based methods to in-core fuel management. Nuclear Science and Engineering, 109, 103–110
Galperin, A.; Yimhi, Y.; Segev, M. (1989) A knowledge-based system for optimization of fuel reload configurations, Nuclear Science and Engineering, 102, 43
Galperin, A.; Nissan, E. (1988) Application of a heuristic search method for generation of fuel reload configurations, Nuclear Science and Engineering, 99 (4), 343–352
Siegelmann, H.T. (1994) Neural programming language, Proceedings of the 12th National Conference on Artificial Intelligence, Seattle, Washington.
Cochran, R.G.; Tsoulfanidis, N. (1990) The Nuclear Reactor Cycle: Analysis and Management, American Nuclear Society, La Grange Park, IL
Parks, G.T.; Lewins, J.D. (1992) In-core fuel management and optimization: the state of the art, Nuclear Europe Worldscan, 12 (3/4), 41
Petschhat, G.R.; Rothleder, B.M.; Faught, W.S.; Eich, W.J. (1986) Interactive fuel shuffle assistant graphics interface and automation for nuclear fuel shuffle with PDQ7, Proceedings of the American Nuclear Society Topical Meeting on Advances in Fuel Management, Pinehurst, NC
Faught, W.S. (1987) Prototype fuel shuffling system using a knowledge-based toolkit, Technical Report, IntelliCorp, Mountain View, CA
Rothleder, B.M.; Petschhat, G.R.; Faught, W.S.; Eich, W.J. (1988) The potential for expert system support in solving the Pressurized Water Reactor fuel shuffling problem, Nuclear Science and Engineering, 100, 400
Kropaczek, D.J.; Turinski, P.J. (1991) In-core nuclear fuel optimization for Pressurized Water Reactors using simulated annealing. Nuclear Technology, 95, 9
Sontag, E.D. (1992) Neural nets as systems models and controllers, Proceedings of the Seventh Yale Workshop on Adaptive and Learning Systems, Yale University, New Haven, CN, pp. 73–79
Matthews, M. (1992) On the uniform approximation of nonlinear discrete-time fading-memory systems using neural network models, PhD dissertation, ETH No. 9635, E.T.H., Zurich
Polycarpou, M.M.; Ioannou, P.A. (1991) Identification and control of nonlinear systems using neural network models: design and stability analysis, Report 91-09-01, Department of EE/Systems, University of South California, Los Angeles
Cleeremans, A.; Servan-Schreiber, D.; McClelland, J. (1989) Finite state automata and simple recurrent networks, Neural Computation, 1, 372
Elman, J. L. (1990) Finding structure in time, Cognitive Science, 14, 179–211
Giles, C.L.; Miller, C.B.; Chen, D.; Chen, H.H.; Sun, G.Z.; Lee, Y.C. (1992) Learning and extracting finite state automata with second-order recurrent neural networks,Neural Computation, 4 (3), 393–405
Pollack, J.B. (1990) The induction of dynamical recognizers, Report 90-JP-Automata, Department of Computer and Information Science, Ohio State University
Williams, R.J.; Zipser, D. (1989) A learning algorithm for continually running fully recurrent neural networks, Neural Computation, 1, 270–280
Barto, A. G.; Singh, S. P. (1990) On the computational economics of reinforcement learning, Proceedings of the 1990 Connectionist Models Summer School, D. S. Touretzky, J. L. Elman, T. I. Sejnowski, and G. E. Hinton (Editors), Morgan Kaufmann, San Mateo, CA
Narendra, K.; Thathacar, M. A. L. (1989)Learning Automata: An Introduction, Prentice-Hallm, Engelwood Cliffs, NJ
Barto, A. G.; Anandan, P. (1985) Pattern recognizing stochastic learning Aatomata,IEEE Transactions on System, Man, and Cybernetics,15, 360–375
Barto, A.G.; Jordan, M.I. (1987) Gradient following without back-propagation in layered networks, Proceedings of the First IEEE International Conference on Neural Networks, San Diego, Vol. 2, pp. 629–636
Hertz, J.; Krogh, A.; Palmer, R.G. (1991) Introduction to the Theory of Neural Computation, Addison-Wesley, Reading, MA
Barto, A.G.; Sutton, R.S.; Watkins, C.J.C.H. (1991) Learning and sequential decision making, In Learning and Computational Neuroscience, M. Gabriel and J.W. Moore (Editors), MIT Press, Cambridge, MA
Jordan, M.I. (1992) Forward models: supervised learning with a distal teacher, Cognitive Science, 16, 307–354
Siegelmann, H.T. (1993) Foundations of recurrent neural networks, PhD Dissertation, Rutgers University, New Brunswick, New Jersey
Gallant, S.I. (1988) Connectionist expert systems, Communications of the ACM, 31 (2), 152–169
Medsker, L.R. Editor (1991) The Synergism of Expert System and Neural Network Technologies, special issue of Expert Systems with Applications, 2 (1)
Medsker, L.R. (1994) Hybrid Neural Network and Expert Systems, Kluwer, Dordrecht, The Netherlands
Bhogal, A.S.; Seviora, R.E.; Elmasry, M.I. (1991) Towards connectionist expert systems, Expert Systems with Applications, 2 (1), 3–14
Silverman, B.G. (1992) Survey of expert critiquing systems: practical and theoretical frontiers, Communications of the ACM, 35 (4), 106–127
Towell, G.G.; Shavlik, J.; Noordewier, M.O. (1990) Refinement of approximately correct domain theories by knowledge-based neural networks, Proceedings of the Eighth National Conference on Artificaial Intelligence, p. 861
Maclin, R.; Shavlik, J.W. Incorporating advice into agents that learn from reinforcement (journal submission)
Nissan, E.; Siegelmann, H.; Galperin, A.; Kimhi, S. (1994) Towards full automation of the discovery of heuristics in a nuclear engineering project, by combining symbolic and subsymbolic Computation, Proceedings of the Eighth International Symposium on Methodologies for Intelligent Systems (ISMIS'94), Charlotte, N.C., Springer-Verlag, New York (Lecture Noter in Artificial Intelligence, Vol. 869), pp. 427–436
Nissan, E.; Siegelmann, H.; Galperin, A. (1994) An integrated symbolic and neural network architecture for machine learning in the domain of nuclear engineering, Proceedings of the Conference on Pattern Recognition and Neural Networks, within the 12th ICPR: International Conferences on Pattern Recognition, Jerusalem, IEEE, Computer Society Press, New York
Galperin, A.; Kimhi, S.; Nissan, E.; Siegelmann, H.; Zhao, J. (1995)Symbolic and subsymbolic integration in prediction and rule-revision tasks for fuel allocation in nuclear reactors. Proceedings of the Third European Congress on Intelligent Techniques and Soft Computing (EUFIT'95), Aachen, Germany, (in press)
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Nissan, E., Siegelmann, H., Galperin, A. et al. Upgrading automation for nuclear fuel in-core management: From the symbolic generation of configurations, to the neural adaptation of heuristics. Engineering with Computers 13, 1–19 (1997). https://doi.org/10.1007/BF01201857
Issue Date:
DOI: https://doi.org/10.1007/BF01201857