Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userClassifying vortex wakes using neural networks
76
0
0.0
(
0
)
Ask ChatGPT about the research
No Arabic abstract
Unsteady flows contain information about the objects creating them. Aquatic organisms offer intriguing paradigms for extracting flow information using local sensory measurements. In contrast, classical methods for flow analysis require global knowledge of the flow field. Here, we train neural networks to classify flow patterns using local vorticity measurements. Specifically, we consider vortex wakes behind an oscillating airfoil and we evaluate the accuracy of the network in distinguishing between three wake types, 2S, 2P+2S and 2P+4S. The network uncovers the salient features of each wake type.
rate research
Read More
An unsupervised machine learning strategy is developed to automatically cluster the vortex wakes of bio-inspired propulsors into groups of similar propulsive thrust and efficiency metrics. A pitching and heaving foil is simulated via computational fluid dynamics with $121$ unique kinematics by varying the frequency, heaving amplitude, and pitching amplitude. A Reynolds averaged Navier-Stokes (RANS) model is employed to simulate the flow over the oscillating foils at $Re=10^6$, computing the propulsive efficiency, thrust coefficient and the unsteady vorticity wake signature. Using a pairwise Pearson correlation it is found that the Strouhal number most strongly influences the thrust coefficient, whereas the relative angle of attack, defined by both the mid-stroke and maximum have the most significant impact on propulsive efficiency. Next, the various kinematics are automatically clustered into distinct groups exclusively using the vorticity footprint in the wake. A convolutional autoencoder is developed to reduce vortex wake images to their most significant features, and a k-means++ algorithm performs the clustering. The results are assessed by comparing clusters to a thrust versus propulsive efficiency map, which confirms that wakes of similar performance metrics are successfully clustered together. This automated clustering has the potential to identify complex vorticity patterns in the wake and modes of propulsion not easily discerned from traditional classification methods.
Process Mining consists of techniques where logs created by operative systems are transformed into process models. In process mining tools it is often desired to be able to classify ongoing process instances, e.g., to predict how long the process will still require to complete, or to classify process instances to different classes based only on the activities that have occurred in the process instance thus far. Recurrent neural networks and its subclasses, such as Gated Recurrent Unit (GRU) and Long Short-Term Memory (LSTM), have been demonstrated to be able to learn relevant temporal features for subsequent classification tasks. In this paper we apply recurrent neural networks to classifying process instances. The proposed model is trained in a supervised fashion using labeled process instances extracted from event log traces. This is the first time we know of GRU having been used in classifying business process instances. Our main experimental results shows that GRU outperforms LSTM remarkably in training time while giving almost identical accuracies to LSTM models. Additional contributions of our paper are improving the classification model training time by filtering infrequent activities, which is a technique commonly used, e.g., in Natural Language Processing (NLP).
Direct numerical simulation (DNS) of turbulent flows is computationally expensive and cannot be applied to flows with large Reynolds numbers. Large eddy simulation (LES) is an alternative that is computationally less demanding, but is unable to capture all of the scales of turbulent transport accurately. Our goal in this work is to build a new data-driven methodology based on super-resolution techniques to reconstruct DNS data from LES predictions. We leverage the underlying physical relationships to regularize the relationships amongst different physical variables. We also introduce a hierarchical generative process and a reverse degradation process to fully explore the correspondence between DNS and LES data. We demonstrate the effectiveness of our method through a single-snapshot experiment and a cross-time experiment. The results confirm that our method can better reconstruct high-resolution DNS data over space and over time in terms of pixel-wise reconstruction error and structural similarity. Visual comparisons show that our method performs much better in capturing fine-level flow dynamics.
Large eddy simulations (LES) are employed to investigate the role of time-varying currents on the form drag and vortex dynamics of submerged 3D topography in a stratified rotating environment. The current is of the form $U_c+U_t sin(2pi f_t t)$, where $U_c$ is the mean, $U_t$ is the tidal component and $f_t$ is its frequency. A conical obstacle is considered in the regime of low Froude number. When tides are absent, eddies are shed at the natural shedding frequency $f_{s,c}$. The relative frequency $f^*=f_{s,c}/f_t$ is varied in a parametric study which reveals states of high time-averaged form drag coefficient. There is a two-fold amplification of the form drag coefficient relative to the no-tide ($U_t=0$) case when $f^*$ lies between 0.5 and 1. The spatial organization of the near-wake vortices in the high drag states is different from a Karman vortex street. For instance, the vortex shedding from the obstacle is symmetric when $f^*=5/12$ and strongly asymmetric when $f^*=5/6$. The increase in form drag with increasing $f^*$ stems from bottom intensification of the pressure in the obstacle lee which is linked to changes in flow separation and near-wake vortices.
The interaction between turbulent axisymmetric wakes plays an important role in many industrial applications, notably in the modelling of wind farms. While the non-equilibrium high Reynolds number scalings present in the wake of axisymmetric plates has been shown to modify the averaged streamwise scalings of individual wakes, little attention has been paid to their consequences in terms of wake interactions. We propose an experimental setup that tests the presence of non-equilibrium turbulence using the streamwise variation of velocity fluctuations between two bluff bodies facing a laminar flow. We have studied two different sets of plates (one with regular and another with irregular peripheries) with hot-wire anemometry in a wind tunnel. By acquiring streamwise profiles for different plate separations and identifying the wake interaction length for each separation it is possible to show that the interaction between them is consistent with non-equilibrium scalings. This work also generalises previous studies concerned with the interaction of plane wakes to include axisymmetric wakes. We find that a simple mathematical expression for the wake interaction length based on non-equilibrium turbulence scalings can be used to collapse the streamwise developments of the second, third and fourth moments of the streamwise fluctuating velocity.
Log in to be able to interact and post comments
comments
Fetching comments
Sign in to be able to follow your search criteria
