An Overview of AI Methods for in-Core Fuel Management: Tools for the Automatic Design of Nuclear Reactor Core Configurations for Fuel Reload, (Re)arranging New and Partly Spent Fuel

摘要

An important aspect of managing a nuclear reactor is how to design refuellings, and fromthe 1980s to the present different artificial intelligence (AI) techniques have been applied to thisproblem. A section of the reactor core resembles a symmetrical grid; long fuel assemblies are insertedthere, some of them new, some of them partly spent. Rods of “burnable poisons” dangle above, readyto be inserted into the core, in order to stop the reactor. Traditionally, manual design was madeby shuffling positions in the grid heuristically, but AI enabled to automatically generate families ofcandidate configurations, under safety constraints, as well as in order to optimize combustion, withlonger cycles of operation between shutdown periods, thus delaying the end-of-cycle point (except inFrance, where shutdown is on an annual basis, and Canada, where individual fuel assemblies arereplaced, with no need for shutdown for rearranging the entire batch). Rule-based expert systems,the first being FUELCON, were succeeded by projects combining neural and rule-based processing (asymbolic-to-neural compilation of rules we did not implement), and later on, genetic algorithms inFUELGEN. In the literature, one also comes across the application of fuzzy techniques, tabu search,cellular automata and simulated annealing, as well as particle swarms. Safety regulations requiresimulating the results using a parameter prediction tool; this is done using either nodal algorithms, orneural processing.