A novel neural/symbolic hybrid approach to heuristically optimized fuel allocation and automated revision of heuristics in nuclear engineering

FUELCON is an expert system for optimized refueling design in nuclear engineering. This task is crucial for keeping down operating costs at a plant without compromising safety. FUELCON proposes sets of alternative configurations of allocation of fuel assemblies that are each positioned in the planar grid of a horizontal section of a reactor core. Results are simulated, and an expert user can also use FUELCON to revise rulesets and improve on his or her heuristics. The successful completion of FUELCON led this research team into undertaking a panoply of sequel projects, of which we provide a meta-architectural comparative formal discussion. In this paper, we demonstrate a novel adaptive technique that learns the optimal allocation heuristic for the various cores. The algorithm is a hybrid of a fine-grained neural network and symbolic computation components. This hybrid architecture is sensitive enough to learn the particular characteristics of the ‘in-core fuel management problem’ at hand, and is powerful enough to use this information fully to automatically revise heuristics, thus improving upon those provided by a human expert.

Exploitation of symbolic information in interprocedural dependence analysis

The requirement for a very accurate dependence analysis to underpin software tools to aid the generation of efficient parallel implementations of scalar code is argued. The current status of dependence analysis is shown to be inadequate for the generation of efficient parallel code, causing too many conservative assumptions to be made. This paper summarises the limitations of conventional dependence analysis techniques, and then describes a series of extensions which enable the production of a much more accurate dependence graph. The extensions include analysis of symbolic variables, the development of a symbolic inequality disproof algorithm and its exploitation in a symbolic Banerjee inequality test; the use of inference engine proofs; the exploitation of exact dependence and dependence pre-domination attributes; interprocedural array analysis; conditional variable definition tracing; integer array tracing and division calculations. Analysis case studies on typical numerical code is shown to reduce the total dependencies estimated from conventional analysis by up to 50%. The techniques described in this paper have been embedded within a suite of tools, CAPTools, which combines analysis with user knowledge to produce efficient parallel implementations of numerical mesh based codes.

Upgrading automation for nuclear fuel in-core management: from the symbolic generation of configurations to the neural adaptation of heuristics

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.

FUELGEN: effective evolutionary design of refuellings for pressurized water reactors

The paper describes the design of an efficient and robust genetic algorithm for the nuclear fuel loading problem (i.e., refuellings: the in-core fuel management problem) - a complex combinatorial, multimodal optimisation., Evolutionary computation as performed by FUELGEN replaces heuristic search of the kind performed by the FUELCON expert system (CAI 12/4), to solve the same problem. In contrast to the traditional genetic algorithm which makes strong requirements on the representation used and its parameter setting in order to be efficient, the results of recent research results on new, robust genetic algorithms show that representations unsuitable for the traditional genetic algorithm can still be used to good effect with little parameter adjustment. The representation presented here is a simple symbolic one with no linkage attributes, making the genetic algorithm particularly easy to apply to fuel loading problems with differing core structures and assembly inventories. A nonlinear fitness function has been constructed to direct the search efficiently in the presence of the many local optima that result from the constraint on solutions.

Staggered-mesh computation for aerodynamic sound

For the numerical solution of the linearized Euler equations, an optimized computational scheme is considered. It is based on fully staggered (in space and time) regular meshes and on a simple mirroring procedure at the stepwise solid walls. There is no need to define ghost points into the solid ohjects that reflect the sound waves. Test results demonstrate the accuracy of the method that may be used for aeroacoustic problems with complex geometries.

Three parallel programming paradigms: Comparisons on an archetypal PDE computation

Three paradigms for distributed-memory parallel computation that free the application programmer from the details of message passing are compared for an archetypal structured scientific computation -- a nonlinear, structured-grid partial differential equation boundary value problem -- using the same algorithm on the same hardware. All of the paradigms -- parallel languages represented by the Portland Group's HPF, (semi-)automated serial-to-parallel source-to-source translation represented by CAP-Tools from the University of Greenwich, and parallel libraries represented by Argonne's PETSc -- are found to be easy to use for this problem class, and all are reasonably effective in exploiting concurrency after a short learning curve. The level of involvement required by the application programmer under any paradigm includes specification of the data partitioning, corresponding to a geometrically simple decomposition of the domain of the PDE. Programming in SPMD style for the PETSc library requires writing only the routines that discretize the PDE and its Jacobian, managing subdomain-to-processor mappings (affine global-to-local index mappings), and interfacing to library solver routines. Programming for HPF requires a complete sequential implementation of the same algorithm as a starting point, introduction of concurrency through subdomain blocking (a task similar to the index mapping), and modest experimentation with rewriting loops to elucidate to the compiler the latent concurrency. Programming with CAPTools involves feeding the same sequential implementation to the CAPTools interactive parallelization system, and guiding the source-to-source code transformation by responding to various queries about quantities knowable only at runtime. Results representative of "the state of the practice" for a scaled sequence of structured grid problems are given on three of the most important contemporary high-performance platforms: the IBM SP, the SGI Origin 2000, and the CRAYY T3E.