Search

The prediction of an unsteady flow field inherently involving high-dimensional dynamics is challenging. The multi-cycle prediction is especially difficult due to the inevitably accumulated errors over time. A novel deep learning model is proposed in this paper to disentangle the high-dimensional dynamics into two separate attributes that, respectively, represent spatial and temporal dynamics. A continuous mapping of temporal dynamics is subsequently constructed, which alleviates the error accumulation and, thus, contributes to the long-term prediction of the unsteady flow field. The dynamics-disentangled deep learning model (D3LM) processes sequential image data of the unsteady flow field and is constituted by three sub-networks, an encoder introducing a stochastic latent variable to explicitly model the low-order temporal dynamics (called varying attribute herein) and extracting multi-level representations of spatial dynamics (called consistent attribute herein), a decoder integrating the disentangled attributes and generating a future flow field, and a discriminator improving the quality of the predicted flow field. The proposed model is evaluated by two simulated datasets of unsteady flows around a circular cylinder at divergent Reynolds numbers. Benefiting from modeling the continuous distribution of temporal dynamics with the stochastic latent variable, the proposal can give multi-cycle future predictions with high accuracy both spatially and temporally on the two datasets with a small amount of training data. Our work demonstrates the potential practicability of deep learning techniques for modeling the long-term nonlinear laws of unsteady flow. [ABSTRACT FROM AUTHOR]

Multi-conditional holographic pressure coefficients over a wing are crucial for wing design, and a wind tunnel test is an indispensable means to obtain this profile. However, it is resource-consuming to obtain wind tunnel data under different conditions and only a limited number of sensors can be placed on the wing model during one test, which results in sparse pressure coefficient data with distribution inconsistency across cross sections and conditions. Thus, how to obtain pressure coefficients of more cross sections or even the whole wing surface with multiple conditions from the distribution-inconsistent sensor data becomes a challenging problem. Therefore, a deep learning framework based on transfer learning is proposed in this paper, in which the spatial dependency captured by a long short-term memory model between the obtained multi-conditional sensor data is transferred to other cross sections with few-condition data on the wing. The results demonstrate that the proposed framework achieves high accuracy on the pressure coefficients prediction of distribution-inconsistent cross sections on wind tunnel test data, and thus improves data utilization and cuts costs by reducing wind tunnel tests under different design conditions. Our work proves the possibility of reconstructing the holographic flow field from sparse sensor data of wind tunnel tests and puts forward recommendations on the placement of sensors for achieving this goal. [ABSTRACT FROM AUTHOR]

Separation-induced transitions can affect the hydrodynamic performance of submarines significantly. The onset of this transition plays a critical role in the design of aircrafts and underwater vehicles. Since the transition is affected by various factors, its prediction is a challenging task. Convolutional neural networks (CNNs) in the field of machine learning can extract features from high-dimensional data automatically and have good generalization performance. In this paper, we propose an end-to-end CNN-based model to automatically extract the features of separation-induced transitions by learning from image-expressed flow field data. The proposed data-driven deep learning model employs a high-resolution network, which is widely used in key-point detection in the field of computer vision, to extract the underlying features in the separation-induced transition under only a few empirical assumptions. A novel representation of separation-induced transition onset in the form of a heatmap is especially proposed to indicate the probability of transition onset. We use implicit-large-eddy-simulation data generated by the second-order discontinuous Galerkin method over Lyu's-1 model line submarine to verify the proposed method, and the results demonstrate that the new method is able to predict separation-induced transition onsets with quantified uncertainty. The proposed model can be used as an auxiliary tool for aerodynamic and hydrodynamic designs. [ABSTRACT FROM AUTHOR]