서강대학교

초록 (요약문)

To model complex turbulent flow and heat transfer phenomena, this study aims to analyze and develop a reduced modeling approach based on artificial neural network (ANN) and wrapper methods. This approach has an advantage over other methods such as the correlation-based filter method in terms of removing duplicate or unnecessary parameters even under non-linearity among the parameters. As a downside, the randomness of ANN training may produce inconsistent subsets over selection trials especially in a higher physical dimension. This study analyzes a few existing ANN-based wrapper methods and develops a revised one based on the gradientbased subset selection indices to minimize the loss in the total derivative or the directional consistency. To examine parameter reduction performance and consistency-over-trials, we apply these methods to a manufactured subset selection problem, the modeling of the bubble size in a turbulent bubbly flow, and the modeling of the spatially varying turbulent Prandtl number in a duct flow. It is found that the gradient-based index to minimize the total derivative loss results in improved consistency-over-trials compared to the other ANN-based wrapper methods. For the reduced turbulent Prandtl number model, the gradient-based index improves the prediction in the validation case over the other methods.