The Capability of Recurrent Neural Networks to Predict Turbulence Flow via Spatiotemporal Features

Abstract

This study presents a deep learning (DL) neural network hybrid data-driven method that is able to predict turbulence flow velocity field. Recently many studies have reported the application of recurrent neural network (RNN) methods, particularly the Long short-term memory (LSTM) for sequential data. The airflow around the objects and wind speed are the most presented with different hybrid architecture. In some of them, the data series is used with the known equation, and the data is firstly generated. Data series extracted from Computational Fluid Dynamics (CFD) have been used in many cases. This work aimed to determine a method with raw data that could be measured with devices in the airflow, wind tunnel, water flow in the river, wind speed and industry application to process in the DL model and predict the next time steps. This method suggests spatialtemporal data in time series, which matches the Lagrangian framework in fluid dynamics. Gated Recurrent Unit (GRU), the next generation of LSTM, has been employed to create a DL model and forecasting. Time series data source is from turbulence flow has been generated in a laboratory and extracted via 2D Lagrangian Particle Tracking (LPT). This data has been used for the training model and to validate the prediction in the suggested approach. The achievement via this method dictates a significant result and could be developed.

Review of Challenges and Opportunities in Turbulence Modeling: A Comparative Analysis of Data-Driven Machine Learning Approaches

“…There are several advantages to using recurrent neural networks (RNNs) for the modeling of turbulence [54][55][56].…”

Deep Learning Forecasts a Strained Turbulent Flow Velocity Field in Temporal Lagrangian Framework: Comparison of LSTM and GRU

“…In particular, in turbulent flow, which has no known equation and is investigated using statistics, a sequential dataset could be used from the Lagrangian view for the forecasting model. It is a crucial challenge to be able to have accurate prediction for turbulent flow velocity via an approach that does not need preprocessing to extract hidden features or reduced order methods [6][7][8][17][18][19]. Some numerical methods due have drawbacks, such as missing features because of dimension reduction [6][7][8][17][18][19].…”

“…It is a crucial challenge to be able to have accurate prediction for turbulent flow velocity via an approach that does not need preprocessing to extract hidden features or reduced order methods [6][7][8][17][18][19]. Some numerical methods due have drawbacks, such as missing features because of dimension reduction [6][7][8][17][18][19]. Based on the above description for the velocity in the Lagrangian framework, in this study we will apply velocity denotation (2) to train LSTM or GRU model via velocity component as an input.…”

“…Figure 3. Gated recurrent unit cell;h (t−1) is hidden state from previous step, X (t) is current input, h (t) is new hidden state, y (t) is output, r (t) is reset gate, z (t) is update gate, g (t)is candidate hidden state, σ is sigmoid function, tanh is hyperbolic tangent function[18].…”

Turbulent Flow Prediction-Simulation: Strained Flow with Initial Isotropic Condition Using a GRU Model Trained by an Experimental Lagrangian Framework, with Emphasis on Hyperparameter Optimization

“…The use of computational fluid dynamic (CFD) methods is a convenient approach for simulating turbulent flows, mainly via direct numerical simulation (DNS) and large eddy simulation (LES) [1]. Although LES is less accurate than DNS, both methods require extensive computing [4] on high-performance computing (HPC) systems. Solving Reynolds-averaged Navier Stokes (RANS) equations is a cheap method used widely in the industry, though it does not provide results on the level of accuracy of LES or DNS.…”