Search:
Match:
1 results

Analysis

This paper demonstrates the generalization capability of deep learning models (CNN and LSTM) in predicting drag reduction in complex fluid dynamics scenarios. The key innovation lies in the model's ability to predict unseen, non-sinusoidal pulsating flows after being trained on a limited set of sinusoidal data. This highlights the importance of local temporal prediction and the role of training data in covering the relevant flow-state space for accurate generalization. The study's focus on understanding the model's behavior and the impact of training data selection is particularly valuable.
Reference

The model successfully predicted drag reduction rates ranging from $-1\%$ to $86\%$, with a mean absolute error of 9.2.