Gas mixing caused by interacting heat sources. Part ii: Modelling

The analyses of hypothetical accident scenario in various containment designs include the evaluation of the effectiveness of Passive Autocatalytic Recombiners (PARs), which are installed to mitigate the hydrogen risk, or are considered by utilities for retro-fitting the plants to implement revised regulatory requirements motivated by the Fukushima accident. The assessment requires validated computational tools. To build confidence in the codes, their capability must also be assessed against separate effect tests addressing specific phenomena under conditions that are representative of those expected in an accident scenario in a real plant. Under the conditions of a severe accident, the large amount of hydrogen release requires the installation of several units, and therefore the study of their interaction is necessary for the optimal layout. Within the OECD/NEA HYMERES project, four experiments have been performed in the large-scale PANDA facility, addressing the thermal effect of one or two PARs, which was simulated by means of heaters (Part I). The tests were of increasing complexity, to permit a step-by-step validation of the codes. These experiments have been analyzed with the GOTHIC code. In general, the GOTHIC code in conjunction with a coarse mesh could predict the mixing process reasonably well. The only notable discrepancy with the experiments was the overprediction of the mixing rate when the lower heater was activated. The analyses revealed that this was due to the incorrect representation of the interaction of the flow out of the lower heater with the obstruction, and better results could be obtained by refining the mesh around the heaters. It was concluded that a coarse mesh is adequate for representing the flow produced by multiple heat sources in an open geometry, but detailed models are generally required if the flows could interact with structures.