Application of information technologies (genetic algorithms, neural networks, parallel calculations) in safety analysis of Nuclear Power Plants.
This paper investigates important issues in three types of safety assessment methodologies commonly applied for Nuclear Power Plants (NPP). These methodologies are i) dynamic probabilistic safety assessment (DPSA) where application of genetic algorithm (GA) is shown to improve the efficiency of the analysis, ii) deterministic safety assessment (DSA) with meta model representation of the system using pre-performed computational fluid dynamics (CFD) code and iii) vulnerability search (e.g. identification of accident scenarios in an NPP) with application of neural network (NN). The use of advanced computational tools and methods such as genetic algorithms, neural networks and parallel computations improve the efficiency of safety analysis. To achieve the best effect, these advanced technologies are to be integrated with existing classical methods of safety analysis of the NPP.
Proceedings of the Institute for System Programming, vol. 26, issue 2, 2014, pp. 137-158.
ISSN 2220-6426 (Online), ISSN 2079-8156 (Print).
DOI: 10.15514/ISPRAS-2014-26(2)-6Full text of the paper in pdf (in Russian) Back to the contents of the volume