Abstract
FUELCON is an expert system in nuclear engineering. The practitioner of nuclear fuel management uses it to generate configurations of reactor core refueling. The domain expert, on the other hand, employs the system to discover new heuristics for the previous task, based on performance during previous iterations in the same session. Expert use involves a manual phase of revising the ruleset. We expose the building blocks of the design of a new version, that incorporates a neural component to carry out the revision. It uses the system's previous performance it for adaptation and learning better rules. for adaptation and learning better rules. The neural component is based on a particular language and schema for symbolic to recurrent-analog conversion, called NEL, and on reinforcement learning for the adaptation.
Preview
Unable to display preview. Download preview PDF.
References
Barto, A.G., Sutton, R.S., Watkins, C.J.: Learning and sequential decision making. In: M. Gabriel, J.W. Moore (eds.), Learning and computational neuroscience. Cambridge, MA: MIT Press 1991.
Galperin, A., Kimhi, Y., Nissan, E.: 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, 4 (1993) 369–415.
Nissan, E., Siegelmann, H., Galperin, A., Kimhi, Y.: Upgrading automation for nuclear fuel in-core management: from the symbolic generation of configurations, to the neural adaptation of heuristics. (forthcoming).
Parks, G.T., Lewins, J.D.: In-core fuel management and optimization: the state of the art. Nuclear Europe Worldscan 12, 3/4 (1992) 41.
Rothleder, B.M., Poetschhat, G.R., Faught, W.S., Eich, W.J.: The potential for expert system support in solving the Pressurized Water Reactor fuel shuffling problem. Nuclear Science and Engineering 100 (1988) 440 ff.
Siegelmann, H.T.: Foundations of recurrent neural networks. Ph.D. dissertation. New Brunswick, NJ: Rutgers University (1993).
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1994 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Nissan, E., Siegelmann, H., Galperin, A., Kimhi, S. (1994). Towards full automation of the discovery of heuristics in a nuclear engineering project: Integration with a neural information language. In: RaÅ›, Z.W., Zemankova, M. (eds) Methodologies for Intelligent Systems. ISMIS 1994. Lecture Notes in Computer Science, vol 869. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-58495-1_43
Download citation
DOI: https://doi.org/10.1007/3-540-58495-1_43
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-58495-7
Online ISBN: 978-3-540-49010-4
eBook Packages: Springer Book Archive