Key points are not available for this paper at this time.
To address the challenge of interpreting the decisions made by machine learning-based control algorithms, the Integrated Artificial Reasoning Framework (IARF) introduced in Part I of this work was developed. Further implementing this framework within a Markov Decision Process (MDP) yielded a decision-making system which produces optimal decisions whose logic can be easily traced and understood. The IARF with MDP formulated in Part I of this study was applied to two case studies of relevance to the nuclear power community: 1) operational decision-making while experiencing the degradation of key components, and 2) optimal control of a nuclear power and hydrogen co-generation facility. This work details the steps of implementing and analyzing these two studies, beginning with the creation of simulation models using the Modelica programming language, covering the formulation of the MDP using the IARF, and concluding with the execution and analysis of the scenarios. Technical challenges related to implementation, such as maintaining physically understandable traceability and efficiently producing large amount of data for calculating state transition probabilities, are addressed and their resolutions are suggested. Emphasis is placed on the benefits of relying on a replaceable modeling framework for simulating system behavior. Results indicate that optimal operational trajectories were successfully found by the MDP, and through utilization of the IARF, these results are easily interpretable and understandable to any user.
Warns et al. (Thu,) studied this question.