Development of a Reduced Order Model of Geostrophic Flow based on a Combination of Proper Orthogonal Decomposition and Long-Short Term Memory Network

Document Type : Research Article

Authors

1 Department of Computer Engineering, University of Qom, Qom, Iran

2 CFD, Turbulence and Combustion Research Lab, Department of Mechanical Engineering, University of Qom, Qom, Iran

Abstract

Mathematical modeling is used to study the phenomena and behavior of the system. Complex mathematical equations require powerful and time-consuming computational tools where that must be examined in order to obtain the correct behavior of a system. However, they require robust computational tools and take a lot of time. High-accuracy numerical simulations utilize numerical schemes and modeling tools to solve this set of equations and generate useful information about the behavior of a system. It makes many restrictions on the solution of scientific problems in different research fields such as geophysical and atmospheric flows, which have high temporal and spatial variations. Therefore, the development of effective and robust algorithms to achieve the maximum quality of numerical simulations with the optimal computational cost is a research topic. There are several methods for dimension reduction but this study used a combination of Proper Orthogonal Decomposition and long-short term memory network. Finally, comparing the results related to the modal coefficients which are obtained by the reduced order model and computational fluid dynamics snapshots projection shows the high accuracy of the proposed method. Also, one of the items considered in the study of algorithms is the time complexity of the algorithm. The computational time of the proposed method which is reconstructed using 15 modes is ten times faster than when all features have been used to reconstruct the model.

Keywords

Main Subjects


[1] Z. Bai, P.M. Dewilde, R.W. Freund, Reduced-order modeling, Handbook of numerical analysis, 13 (2005) 825-895.
[2] K.H. Park, S.O. Jun, S.M. Baek, M.H. Cho, K.J. Yee, D.H. Lee, Reduced-order model with an artificial neural network for aerostructural design optimization, Journal of Aircraft, 50(4) (2013) 1106-1116.
[3] S.A. Nahvi, M.A. Bazaz, H. Khan, Model order reduction in power electronics: Issues and perspectives, in:  2017 International Conference on Computing, Communication and Automation (ICCCA), IEEE, 2017, pp. 1417-1421.
[4] M.A. Cardoso, L.J. Durlofsky, P. Sarma, Development and application of reduced‐order modeling procedures for subsurface flow simulation, International journal for numerical methods in engineering, 77(9) (2009) 1322-1350.
[5] D.B. Segala, D. Chelidze, Robust and dynamically consistent model order reduction for nonlinear dynamic systems, Journal of Dynamic Systems, Measurement, and Control, 137(2) (2015) 021011.
[6] K.T. Carlberg, Model reduction of nonlinear mechanical systems via optimal projection and tensor approximation, Stanford University, 2011.
[7] M.F.A. Azeez, A.F. Vakakis, Numerical and experimental analysis of a continuous overhung rotor undergoing vibro-impacts, International journal of non-linear mechanics, 34(3) (1999) 415-435.
[8] R. Kappagantu, B. Feeny, An" optimal" modal reduction of a system with frictional excitation, Journal of Sound and vibration, 224(5) (1999) 863-877.
[9] Y. Liang, W. Lin, H. Lee, S. Lim, K. Lee, H. Sun, Proper orthogonal decomposition and its applications–part II: Model reduction for MEMS dynamical analysis, Journal of Sound and Vibration, 256(3) (2002) 515-532.
[10] X. Ma, A.F. Vakakis, L.A. Bergman, Karhunen-Loeve modes of a truss: transient response reconstruction and experimental verification, AIAA journal, 39(4) (2001) 687-696.
[11] X. Ma, A.F. Vakakis, Karhunen-Lo-ccedil; ve Decomposition of the Transient Dynamics of a Multibay Truss, AIAA journal, 37(8) (1999) 939-946.
[12] A. Steindl, H. Troger, Methods for dimension reduction and their application in nonlinear dynamics, International Journal of Solids and Structures, 38(10-13) (2001) 2131-2147.
[13] M.I. Friswell, D.J. Inman, Sensor validation for smart structures, Journal of intelligent material systems and structures, 10(12) (1999) 973-982.
[14] G. Kerschen, P. De Boe, J.-C. Golinval, K. Worden, Sensor validation using principal component analysis, Smart materials and structures, 14(1) (2004) 36.
[15] B. Feeny, On proper orthogonal co-ordinates as indicators of modal activity, Journal of Sound and Vibration, 255(5) (2002) 805-817.
[16] S. Han, B. Feeny, Application of proper orthogonal decomposition to structural vibration analysis, Mechanical Systems and Signal Processing, 17(5) (2003) 989-1001.
[17] K. Fukunaga, Introduction to statistical pattern recognition, Elsevier, 2013.
[18] D. Xiao, F. Fang, J. Du, C. Pain, I. Navon, A. Buchan, A.H. Elsheikh, G. Hu, Non-linear Petrov–Galerkin methods for reduced order modelling of the Navier–Stokes equations using a mixed finite element pair, Computer Methods In Applied Mechanics and Engineering, 255 (2013) 147-157.
[19] D. Xiao, F. Fang, C. Pain, G. Hu, Non‐intrusive reduced‐order modelling of the Navier–Stokes equations based on RBF interpolation, International Journal for Numerical Methods in Fluids, 79(11) (2015) 580-595.
[20] F. Fang, T. Zhang, D. Pavlidis, C. Pain, A. Buchan, I. Navon, Reduced order modelling of an unstructured mesh air pollution model and application in 2D/3D urban street canyons, Atmospheric Environment, 96 (2014) 96-106.
[21] M. Diez, E.F. Campana, F. Stern, Design-space dimensionality reduction in shape optimization by Karhunen–Loève expansion, Computer Methods in Applied Mechanics and Engineering, 283 (2015) 1525-1544.
[22] A. Manzoni, F. Salmoiraghi, L. Heltai, Reduced Basis Isogeometric Methods (RB-IGA) for the real-time simulation of potential flows about parametrized NACA airfoils, Computer Methods in Applied Mechanics and Engineering, 284 (2015) 1147-1180.
[23] X. Chen, S. Akella, I. Navon, A dual‐weighted trust‐region adaptive POD 4‐D Var applied to a finite‐volume shallow water equations model on the sphere, International Journal for Numerical Methods in Fluids, 68(3) (2012) 377-402.
[24] R. Ştefănescu, I.M. Navon, POD/DEIM nonlinear model order reduction of an ADI implicit shallow water equations model, Journal of Computational Physics, 237 (2013) 95-114.
[25] R. Ştefănescu, A. Sandu, I.M. Navon, Comparison of POD reduced order strategies for the nonlinear 2D shallow water equations, International Journal for Numerical Methods in Fluids, 76(8) (2014) 497-521.
[26] D.A. Bistrian, I.M. Navon, An improved algorithm for the shallow water equations model reduction: Dynamic Mode Decomposition vs POD, International Journal for Numerical Methods in Fluids, 78(9) (2015) 552-580.
[27] D. Xiao, C. Heaney, L. Mottet, F. Fang, W. Lin, I. Navon, Y. Guo, O. Matar, A. Robins, C. Pain, A reduced order model for turbulent flows in the urban environment using machine learning, Building and Environment, 148 (2019) 323-337.
[28] M. Moayyedi, Reconstruction of Gappy Unsteady Flow Fields using Improved Reduced Order POD Model based on Temporal Decomposition Procedure, Amirkabir Journal of Mechanical Engineering, 49(1) (2017) 101-112. (in persian)
[29] D. Kosambi, Statistics in function space, in:  DD Kosambi, Springer, 2016, pp. 115-123.
[30] M. Loeve, Functions aleatoires du second ordre, Processus stochastique et mouvement Brownien,  (1948) 366-420.
[31] K. Karhunen, Über lineare Methoden in der Wahrscheinlichkeitsrechnung: akademische Abhandlung, Sana, 1947.
[32] V.S. Pugachev, The general theory of correlation of random functions, Izvestiya Rossiiskoi Akademii Nauk. Seriya Matematicheskaya, 17(5) (1953) 401-420.
[33] A. Obukhov, Statistical description of continuous fields, Transactions of the Geophysical International Academy Nauk USSR, 24(24) (1954) 3-42.
[34] S.M. Rahman, S.E. Ahmed, O. San, A dynamic closure modeling framework for model order reduction of geophysical flows, Physics of Fluids, 31(4) (2019) 046602.
[35] M. Moayyedi, M.T.R. , F.S. , Calibrated Reduced Order POD Model for Simulation of Unsteady Incompressible Flows, Fluid Mechanics & Aerodynamics Journal, 1(1) (2012))in persian).
[36] Y. Liang, H. Lee, S. Lim, W. Lin, K. Lee, C. Wu, Proper orthogonal decomposition and its applications—Part I: Theory, Journal of Sound and vibration, 252(3) (2002) 527-544.
[37] S. Ravindran, Proper orthogonal decomposition in optimal control of fluids, National Aeronautics and Space Administration, Langley Research Center, 1999.
[38] S.L. Brunton, B.R. Noack, P. Koumoutsakos, Machine learning for fluid mechanics, Annual Review of Fluid Mechanics, 52 (2020) 477-508.
[39] C. Olah, Understanding LSTM Networks, in, 2015.
[40] J. Cheng, L. Dong, M. Lapata, Long short-term memory-networks for machine reading, arXiv preprint arXiv:1601.06733,  (2016).
[41] S.M. Rahman, Reduced Order Modeling of Geophysical Flows Using Physics-based and Data-driven Modeling Techniques, PhD diss, Oklahoma State University, 2019.
[42] H. Ahmad, Machine learning applications in oceanography, Aquatic Research, 2(3) (2019) 161-169.
[43] G. Batchelor, Turbulence, coherent structures, dynamical system, and symmetry, in, Cambridge, United Kingdom: Cambridge University Press, 2000.
[44] O. San, T. Iliescu, A stabilized proper orthogonal decomposition reduced-order model for large scale quasigeostrophic ocean circulation, Advances in Computational Mathematics, 41(5) (2015) 1289-1319.
[45] O. San, A.E. Staples, Z. Wang, T. Iliescu, Approximate deconvolution large eddy simulation of a barotropic ocean circulation model, Ocean Modelling, 40(2) (2011) 120-132.
[46] R.J. Hyndman, A.B. Koehler, Another look at measures of forecast accuracy, International journal of forecasting, 22(4) (2006) 679-688.