No abstract

No abstract

In the field of multi-objective optimization, there are a multitude of algorithms from which to choose. Each algorithm has strengths and weaknesses associated with the mechanics for finding the Pareto front. Recently, researchers have begun to examine how multi-agent environments can be used to help solve multi-objective optimization problems. In this work, we propose a multi-objective optimization algorithm based on a multi-agent blackboard system (MABS). The MABS framework allows for multiple agents to read and write pertinent optimization problem data to a central blackboard agent. Agents can stochastically search the design space, use previously discovered solutions to explore local optima, or update and prune the Pareto front. A centralized blackboard framework allows the optimization problem to be solved in a cohesive manner and permits stopping, restarting, or updating the optimization problem. The MABS framework is tested against three alternative optimization algorithms across a suite of engineering design problems and typically outperforms the other algorithms in discovering the Pareto front. A parallelizability study is performed where we find that the MABS is able to evaluate a set number of designs, which require an evaluation time ranging from 0 to 300 seconds, quicker than a traditional optimization algorithm: this fact becomes more apparent the longer it takes to evaluate a design. To provide context for the benefits provided by MABS, a real-world nuclear engineering design problem is examined. MABS is used to examine the placement of experiments in a nuclear reactor, where we are able to evaluate hundreds of configurations for experimental placement while maintaining a strict set of safety constraints.

This case study describes the development of technologies that enable digital-engineering and digital-twinning efforts in proliferation detection. The project presents a state-of-the-art approach to supporting IAEA safeguards by incorporating diversion-pathway analysis, facility misuse, and detection of indicators within the reactor core, applying the safeguards-by-design concept, and demonstrates its applicability as a sensitive monitoring system for advanced reactors and power plants. There are two pathways a proliferating state might take using the reactor core. One is “diversion,” where special fissionable nuclear material—i.e., Pu-239, U-233, U enriched in U-233/235—that has been declared to the International Atomic Energy Agency (IAEA) is removed surreptitiously, either by taking small amounts of nuclear material over a long time (known as protracted diversion) or large amounts in a short time (known as abrupt diversion). The second pathway is “misuse,” where undeclared source material—material that can be transmuted into special fissionable nuclear material: depleted uranium, natural uranium, and thorium—is placed in the core, where it uses the neutron flux for transmutation. Digital twinning and digital engineering have demonstrated significant performance improvement and schedule reduction in the aerospace, automotive, and construction industries. This integrated modeling approach has not been fully applied to nuclear safeguards programs in the past. Digital twinning, combined with machine learning technologies, can lead to new innovations in process-monitoring detection, specifically in event classification, real-time notification, and data tampering. It represents a technological leap in evaluation and detection capability to safeguard any nuclear facility.