In this paper, we present two deep learning-based hybrid data-driven reduced-order models for prediction of unsteady fluid flows. These hybrid models rely on recurrent neural networks (RNNs) to evolve low-dimensional states of unsteady fluid flow. The first model projects the high-fidelity time series data from a finite element Navier–Stokes solver to a low-dimensional subspace via proper orthogonal decomposition (POD). The time-dependent coefficients in the POD subspace are propagated by the recurrent net (closed-loop encoder–decoder updates) and mapped to a high-dimensional state via the mean flow field and the POD basis vectors. This model is referred to as POD-RNN. The second model, referred to as the convolution recurrent autoencoder network (CRAN), employs convolutional neural networks (instead of POD) as layers of linear kernels with nonlinear activations, to extract low-dimensional features from flow field snapshots. The flattened features are advanced using a recurrent (closed-loop manner) net and up-sampled (transpose convoluted) gradually to high-dimensional snapshots. Two benchmark problems of the flow past a cylinder and the flow past side-by-side cylinders are selected as the unsteady flow problems to assess the efficacy of these models. For the problem of the flow past a single cylinder, the performance of both the models is satisfactory and the CRAN model is found to be overkill. However, the CRAN model completely outperforms the POD-RNN model for a more complicated problem of the flow past side-by-side cylinders involving the complex effects of vortex-to-vortex and gap flow interactions. Owing to the scalability of the CRAN model, we introduce an observer-corrector method for calculation of integrated pressure force coefficients on the fluid–solid boundary on a reference grid. This reference grid, typically a structured and uniform grid, is used to interpolate scattered high-dimensional field data as snapshot images. These input images are convenient in training the CRAN model, which motivates us to further explore the application of the CRAN-based models for prediction of fluid flows.
In this paper, we present a data-driven approach to construct a reduced-order model (ROM) for the unsteady flow field and fluid-structure interaction. This proposed approach relies on (i) a projection of the high-dimensional data from the Navier-Stokes equations to a low-dimensional subspace using the proper orthogonal decomposition (POD) and (ii) integration of the low-dimensional model with the recurrent neural networks. For the hybrid ROM formulation, we consider long short term memory networks with encoder-decoder architecture, which is a special variant of recurrent neural networks. The mathematical structure of recurrent neural networks embodies a non-linear state space form of the underlying dynamical behavior. This particular attribute of an RNN makes it suitable for non-linear unsteady flow problems. In the proposed hybrid RNN method, the spatial and temporal features of the unsteady flow system are captured separately. Time-invariant modes obtained by low-order projection embodies the spatial features of the flow field, while the temporal behavior of the corresponding modal coefficients is learned via recurrent neural networks. The effectiveness of the proposed method is first demonstrated on a canonical problem of flow past a cylinder at low Reynolds number. With regard to a practical marine/offshore engineering demonstration, we have applied and examined the reliability of the proposed data-driven framework for the predictions of vortex-induced vibrations of a flexible offshore riser at high Reynolds number.
The potential of vortex induced motion (VIM) in multi-column floating platforms such as semi-submersibles and tension leg platforms (TLPs) is well-acknowledged although the industry guidelines for design for VIM are not comprehensive and more research effort is required. Significant VIM in multi-column floating platforms will affect the fatigue life of the steel catenary risers and must be quantified and sometimes reduced. Industry-standard design tools used for drag estimation based on model tests of fixed structures may not accurately reflect the effects of drag augmentation due to VIM. Model tests and Computational Fluid Dynamics (CFD) analysis are feasible methods to investigate VIM, with the latter being more resource-efficient, provided sufficient benchmarking has been carried out to ensure reliable results. Subsequent to the model tests and preliminary Computational Fluid Dynamics (CFD) simulations done for a multi-column floating platform [1, 2], further CFD analyses for the VIM of the floating platform have been carried out using improved simulation techniques with a commercial software. Good agreement between model test results and CFD calculations for VIM of a multi-column floating platform is observed. Sensitivity of CFD results to the modeling assumptions such as mesh size and density, time-step size and different turbulence models is presented.
In order to evaluate the Vortex Induced Vibration (VIV) response of truss Spars and to optimize their strake configuration several model test programs have been carried out at MARIN. The results show that it is possible to optimize the strake design of Spars to obtain minimum VIV-response. The results of the model tests also suggest that modeling details, such as appendages, can have an influence on the Vortex Induced Vibrations. In order to reliably predict the full-scale VIV-behavior of the prototype Spar these details must therefore be accurately represented on the model. Furthermore, damping of attached structures such as the truss on a truss Spar can significantly contribute to the reduction of VIV. Loads on such structures have been measured in the model tests. An important aspect that needs consideration in VIV model testing is effect of model scale on the Reynolds number. Roughness can be added to the hard tank of the Spar to minimize scale effects. The paper discusses possible scale effects and the effect of hull roughness on model test results. The repeatability of VIV model tests and reliability of these tests in representing the full-scale situation is discussed. The effect of Spar heading with respect to the current direction as well as current speed will be discussed.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.