A Sensitivity Analysis of Design Parameters of an Underground Radioactive Waste Repository Using a Backpropagation Neural Network
0
조회
0
다운로드
1
인용
0
참고문헌
키워드
초록
The prediction of near field behavior around an underground high-level radioactive waste repository is important for the repository design as well as the safety assessment. In this study, a sensitivity analysis for seven parameters consisted of design parameters and material properties was carried out using a three-dimensional finite difference code. From the sensitivity analysis, it was found that the effects of borehole spacing, tunnel spacing, cooling time and rock thermal conductivity were more significant than the other parameters. For getting a statistical distribution of buffer and rock temperatures around the repository, an artificial neural network, backpropagation, was applied. The reliability of the trained neural network was tested with the cases with randomly chosen input parameters. When the parameter variation is within ±10%, the prediction from the network was found to be reliable with about a 1% error. It was possible to calculate the temperature distribution for many cases quickly with the trained neural network. The buffer and rock temperatures showed a normal distribution with means of 98℃ and 83.9℃ standard deviations of 3.82℃ and 3.67℃, respectively. Using the neural network, it was also possible to estimate the required change in design parameters for reducing the buffer and rock temperatures for 1℃.
Abstract
The prediction of near field behavior around an underground high-level radioactive waste repository is important for the repository design as well as the safety assessment. In this study, a sensitivity analysis for seven parameters consisted of design parameters and material properties was carried out using a three-dimensional finite difference code. From the sensitivity analysis, it was found that the effects of borehole spacing, tunnel spacing, cooling time and rock thermal conductivity were more significant than the other parameters. For getting a statistical distribution of buffer and rock temperatures around the repository, an artificial neural network, backpropagation, was applied. The reliability of the trained neural network was tested with the cases with randomly chosen input parameters. When the parameter variation is within ±10%, the prediction from the network was found to be reliable with about a 1% error. It was possible to calculate the temperature distribution for many cases quickly with the trained neural network. The buffer and rock temperatures showed a normal distribution with means of 98℃ and 83.9℃ standard deviations of 3.82℃ and 3.67℃, respectively. Using the neural network, it was also possible to estimate the required change in design parameters for reducing the buffer and rock temperatures for 1℃.
참고문헌 (8)
- Reference spent fuel and its characteristics for the concept development of a deep geological disposal system, "Choi, J.W.", ~, pp.KAERI (1997), TR- 914[DOI]
- Itasca, "FLAC3D user’s manual", ~ (2002)
- Kwon, S., "Thermo-mechanical stability analysis for a multi-level radioactive waste disposal concept", Geotechnical and Geological Engineering, 24, pp.361~377 (2006)
- Lawrence, J., "Introduction to Neural Networks" (1993), California Scientific
- Lee, J.Y., "Development of the Korean Reference Vertical Disposal System Concept for Spent fuels", Waste Management’06 (2006)
- Pre-conceptual design of Korean reference HLW disposal system, "Lee, J.Y.", ~, pp.KAERI (2005), TR3012[DOI]
- McCulloch, W., "A logical calculus of the ideas imminent in nervous activity", Bulle tin of Mathematical Biophysics, 5, pp.115~133 (1943)
- Rumelhart, D., "Learning internal representations by error prop agation. In Neurocomputing", pp.675~695 (1988), MIT Press