Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userA deep-learning based generalized reduced-order model of glottal flow during normal phonation
91
0
0.0
(
0
)
Ask ChatGPT about the research
No Arabic abstract
This paper proposes a deep-learning based generalized reduced-order model (ROM) that can provide a fast and accurate prediction of the glottal flow during normal phonation. The approach is based on the assumption that the vibration of the vocal folds can be represented by a universal kinematics equation (UKE), which is used to generate a glottal shape library. For each shape in the library, the ground truth values of the flow rate and pressure distribution are obtained from the high-fidelity Navier-Stokes (N-S) solution. A fully-connected deep neural network (DNN)is then trained to build the empirical mapping between the shapes and the flow rate and pressure distributions. The obtained DNN based reduced-order flow solver is coupled with a finite-element method (FEM) based solid dynamics solver for FSI simulation of phonation. The reduced-order model is evaluated by comparing to the Navier-Stokes solutions in both statics glottal shaps and FSI simulations. The results demonstrate a good prediction performance in accuracy and efficiency.
rate research
Read More
Reduced Order Modelling (ROM) has been widely used to create lower order, computationally inexpensive representations of higher-order dynamical systems. Using these representations, ROMs can efficiently model flow fields while using significantly lesser parameters. Conventional ROMs accomplish this by linearly projecting higher-order manifolds to lower-dimensional space using dimensionality reduction techniques such as Proper Orthogonal Decomposition (POD). In this work, we develop a novel deep learning framework DL-ROM (Deep Learning - Reduced Order Modelling) to create a neural network capable of non-linear projections to reduced order states. We then use the learned reduced state to efficiently predict future time steps of the simulation using 3D Autoencoder and 3D U-Net based architectures. Our model DL-ROM is able to create highly accurate reconstructions from the learned ROM and is thus able to efficiently predict future time steps by temporally traversing in the learned reduced state. All of this is achieved without ground truth supervision or needing to iteratively solve the expensive Navier-Stokes(NS) equations thereby resulting in massive computational savings. To test the effectiveness and performance of our approach, we evaluate our implementation on five different Computational Fluid Dynamics (CFD) datasets using reconstruction performance and computational runtime metrics. DL-ROM can reduce the computational runtimes of iterative solvers by nearly two orders of magnitude while maintaining an acceptable error threshold.
A reduced description of shear flows consistent with the Reynolds number scaling of lower-branch exact coherent states in plane Couette flow [J. Wang et al., Phys. Rev. Lett. 98, 204501 (2007)] is constructed. Exact time-independent nonlinear solutions of the reduced equations corresponding to both lower and upper branch states are found for Waleffe flow [F. Waleffe, Phys. Fluids 9, 883--900 (1997)]. The lower branch solution is characterized by fluctuations that vary slowly along the critical layer while the upper branch solutions display a bimodal structure and are more strongly focused on the critical layer. The reduced model provides a rational framework for investigations of subcritical spatiotemporal patterns in parallel shear flows.
Analyzing large-scale data from simulations of turbulent flows is memory intensive, requiring significant resources. This major challenge highlights the need for data compression techniques. In this study, we apply a physics-informed Deep Learning technique based on vector quantization to generate a discrete, low-dimensional representation of data from simulations of three-dimensional turbulent flows. The deep learning framework is composed of convolutional layers and incorporates physical constraints on the flow, such as preserving incompressibility and global statistical characteristics of the velocity gradients. The accuracy of the model is assessed using statistical, comparison-based similarity and physics-based metrics. The training data set is produced from Direct Numerical Simulation of an incompressible, statistically stationary, isotropic turbulent flow. The performance of this lossy data compression scheme is evaluated not only with unseen data from the stationary, isotropic turbulent flow, but also with data from decaying isotropic turbulence, a Taylor-Green vortex flow, and a turbulent channel flow. Defining the compression ratio (CR) as the ratio of original data size to the compressed one, the results show that our model based on vector quantization can offer CR$=85$ with a mean square error (MSE) of $O(10^{-3})$, and predictions that faithfully reproduce the statistics of the flow, except at the very smallest scales where there is some loss. Compared to the recent study of Glaws. et. al. (Physical Review Fluids, 5(11):114602, 2020), which was based on a conventional autoencoder (where compression is performed in a continuous space), our model improves the CR by more than $30$ percent...
In global efforts to reduce harmful greenhouse gas emissions from the transport sector, novel bio-hybrid liquid fuels from renewable energy and carbon sources can be a major form of energy for future propulsion systems due to their high energy density. A fundamental understanding of the spray and mixing performance of the new fuel candidates in combustion systems is necessary to design and develop the fuels for advanced combustion concepts. In the fuel design process, a large number of candidates is required to be screened to arrive at potential fuels for further detailed investigations. For such a screening process, three-dimensional (3D) simulation models are computationally too expensive and hence unfeasible. Therefore, in this paper, we present a fast, reduced-order model (ROM) for inert sprays. The model is based on the cross-sectionally averaged spray (CAS) model derived by Wan (1997) from 3D multiphase equations. The original model was first tested against a wide range of conditions and different fuels. The discrepancies between the CAS model and experimental data are addressed by integrating state-of-the-art breakup and evaporation models. A transport equation for vapor mass fraction is proposed, which is important for evaporation modeling. Furthermore, the model is extended to consider polydisperse droplets by modeling the droplet size distribution by commonly used presumed probability density functions, such as Rosin-Rammler, lognormal, and gamma distributions. The improved CAS model is capable of predicting trends in the macroscopic spray characteristics for a wide range of conditions and fuels. The computational cost of the CAS model is lower than the 3D simulation methods by up to 6 orders of magnitude depending on the method. This enables the model to be used not only for the rapid screening of novel fuel candidates, but also for other applications, where ROMs are useful.
We investigate the applicability of machine learning based reduced order model (ML-ROM) to three-dimensional complex flows. As an example, we consider a turbulent channel flow at the friction Reynolds number of $Re_tau=110$ in a minimum domain which can maintain coherent structures of turbulence. Training data set are prepared by direct numerical simulation (DNS). The present ML-ROM is constructed by combining a three-dimensional convolutional neural network autoencoder (CNN-AE) and a long short-term memory (LSTM). The CNN-AE works to map high-dimensional flow fields into a low-dimensional latent space. The LSTM is then utilized to predict a temporal evolution of the latent vectors obtained by the CNN-AE. The combination of CNN-AE and LSTM can represent the spatio-temporal high-dimensional dynamics of flow fields by only integrating the temporal evolution of the low-dimensional latent dynamics. The turbulent flow fields reproduced by the present ML-ROM show statistical agreement with the reference DNS data in time-ensemble sense, which can also be found through an orbit-based analysis. Influences of the population of vortical structures contained in the domain and the time interval used for temporal prediction on the ML- ROM performance are also investigated. The potential and limitation of the present ML-ROM for turbulence analysis are discussed at the end of our presentation.
Log in to be able to interact and post comments
comments
Fetching comments
Sign in to be able to follow your search criteria
