CNN-sindy based reduced order modeling of unsteady flow fields

Takaaki Murata, Kai Fukami, Koji Fukagata

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

We present a new framework of nonlinear reduced order model to extract low-dimensional modes and to predict their temporal evolutions. Autoencoder-type Convolutional Neural Network (CNN) which can learn nonlinearity of data is used to extract low-dimensional modes. For obtaining the temporal evolution of a mapped data by CNN, Sparse Identification of Nonlinear Dynamics (SINDy) is performed. The proposed method is applied to a circular cylinder wake at ReD = 100. The CNN trained using fluctuation components of velocity vector u, v shows better results than the snapshot Proper Orthogonal Decomposition in terms of the energy reconstruction rate. Although time-evolving flow fields reproduced by SINDy equation also show reasonable agreement with the reference direct numerical simulation, the errors of CNN and SINDy are accumulated through integral computation. The error of CNN can be reduced by devising a better network structure; however, the error of SINDy depends on the waveform of latent vector.

Original languageEnglish
Title of host publicationComputational Fluid Dynamics
PublisherAmerican Society of Mechanical Engineers (ASME)
ISBN (Electronic)9780791859032
DOIs
Publication statusPublished - 2019 Jan 1
EventASME-JSME-KSME 2019 8th Joint Fluids Engineering Conference, AJKFluids 2019 - San Francisco, United States
Duration: 2019 Jul 282019 Aug 1

Publication series

NameASME-JSME-KSME 2019 8th Joint Fluids Engineering Conference, AJKFluids 2019
Volume2

Conference

ConferenceASME-JSME-KSME 2019 8th Joint Fluids Engineering Conference, AJKFluids 2019
CountryUnited States
CitySan Francisco
Period19/7/2819/8/1

ASJC Scopus subject areas

  • Fluid Flow and Transfer Processes

Fingerprint Dive into the research topics of 'CNN-sindy based reduced order modeling of unsteady flow fields'. Together they form a unique fingerprint.

  • Cite this

    Murata, T., Fukami, K., & Fukagata, K. (2019). CNN-sindy based reduced order modeling of unsteady flow fields. In Computational Fluid Dynamics (ASME-JSME-KSME 2019 8th Joint Fluids Engineering Conference, AJKFluids 2019; Vol. 2). American Society of Mechanical Engineers (ASME). https://doi.org/10.1115/AJKFluids2019-5056