A deep learning framework for turbulence modeling using data assimilation and feature extraction

Turbulent problems in industrial applications are predominantly solved using Reynolds Averaged Navier Stokes (RANS) turbulence models. The accuracy of the RANS models is limited due to closure assumptions that induce uncertainty into the RANS modeling. We propose the use of deep learning algorithms via convolution neural networks along with data from direct numerical simulations to extract the optimal set of features that explain the evolution of turbulent flow statistics. Statistical tests are used to determine the correlation of these features with the variation in the quantities of interest that are to be predicted. These features are then used to develop improved partial differential equations that can replace classical Reynolds Averaged Navier Stokes models and show improvement in the accuracy of the predictions.

[1]  G. Iaccarino,et al.  Sensitivity of flow evolution on turbulence structure , 2016 .

[2]  Josef Sivic,et al.  Convolutional Neural Network Architecture for Geometric Matching , 2019, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[3]  Heng Xiao,et al.  Physics-Informed Machine Learning for Predictive Turbulence Modeling: Towards a Complete Framework. , 2016 .

[4]  Gianluca Iaccarino,et al.  A framework for epistemic uncertainty quantification of turbulent scalar flux models for Reynolds-averaged Navier-Stokes simulations , 2013 .

[5]  Alexei A. Efros,et al.  Image-to-Image Translation with Conditional Adversarial Networks , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[6]  Roland Schinzinger,et al.  Conformal Mapping: Methods and Applications , 1991 .

[7]  Yi Li,et al.  A public turbulence database cluster and applications to study Lagrangian evolution of velocity increments in turbulence , 2008, 0804.1703.

[8]  Hester Bijl,et al.  Bayesian estimates of parameter variability in the k-ε turbulence model , 2014, J. Comput. Phys..

[9]  Arthur Flexer,et al.  Basic filters for convolutional neural networks applied to music: Training or design? , 2017, Neural Computing and Applications.

[10]  Tara N. Sainath,et al.  Deep Neural Networks for Acoustic Modeling in Speech Recognition: The Shared Views of Four Research Groups , 2012, IEEE Signal Processing Magazine.

[11]  Sai Hung Cheung,et al.  Bayesian uncertainty analysis with applications to turbulence modeling , 2011, Reliab. Eng. Syst. Saf..

[12]  P. Cinnella,et al.  Predictive RANS simulations via Bayesian Model-Scenario Averaging , 2014, J. Comput. Phys..

[13]  Raghu Machiraju,et al.  Physics-based Feature Mining for Large Data Exploration D a T a M I N I N G , 2001 .

[14]  Sam Kwong,et al.  Building Correlations Between Filters in Convolutional Neural Networks , 2017, IEEE Transactions on Cybernetics.

[15]  Heng Xiao,et al.  Quantifying and reducing model-form uncertainties in Reynolds-averaged Navier-Stokes simulations: A data-driven, physics-informed Bayesian approach , 2015, J. Comput. Phys..

[16]  Heng Xiao,et al.  Quantification of Uncertainties in Turbulence Modeling: A Comparison of Physics-Based and Random Matrix Theoretic Approaches , 2016, 1603.05549.

[17]  J. Templeton.  Evaluation of machine learning algorithms for prediction of regions of high Reynolds averaged Navier Stokes uncertainty , 2015 .

[18]  Yi Li,et al.  Data exploration of turbulence simulations using a database cluster , 2007, Proceedings of the 2007 ACM/IEEE Conference on Supercomputing (SC '07).

[19]  George E. Karniadakis,et al.  Hidden physics models: Machine learning of nonlinear partial differential equations , 2017, J. Comput. Phys..

[20]  Todd A. Oliver,et al.  Bayesian uncertainty quantification applied to RANS turbulence models , 2011 .

[21]  Louis-Philippe Morency,et al.  Multimodal Machine Learning: A Survey and Taxonomy , 2017, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[22]  Gianluca Iaccarino,et al.  Uncertainty Estimation for Reynolds-Averaged Navier–Stokes Predictions of High-Speed Aircraft Nozzle Jets , 2017 .

[23]  A. A. Mishra,et al.  RANS predictions for high-speed flows using enveloping models , 2017, 1704.01699.

[24]  Bengt Fornberg,et al.  Accuracy of radial basis function interpolation and derivative approximations on 1-D infinite grids , 2005, Adv. Comput. Math..

[25]  Yee Whye Teh,et al.  A Fast Learning Algorithm for Deep Belief Nets , 2006, Neural Computation.

[26]  Guigang Zhang,et al.  Deep Learning , 2016, Int. J. Semantic Comput..

[27]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[28]  Yongfeng Huang,et al.  CSFL: A novel unsupervised convolution neural network approach for visual pattern classification , 2017, AI Communications.

[29]  H. Schaeffer,et al.  Learning partial differential equations via data discovery and sparse optimization , 2017, Proceedings of the Royal Society A: Mathematical, Physical and Engineering Sciences.

[30]  Gianluca Iaccarino,et al.  Eigenspace perturbations for uncertainty estimation of single-point turbulence closures , 2017 .

[31]  J. Templeton,et al.  Reynolds averaged turbulence modelling using deep neural networks with embedded invariance , 2016, Journal of Fluid Mechanics.

[32]  Ryan Nicholas King,et al.  Learning and Optimization for Turbulent Flows , 2016 .

[33]  Gianluca Iaccarino,et al.  Modeling of structural uncertainties in Reynolds-averaged Navier-Stokes closures , 2013 .

[34]  Roberto Cipolla,et al.  SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation , 2015, IEEE Transactions on Pattern Analysis and Machine Intelligence.