Learning low-dimensional feature dynamics using convolutional recurrent autoencoders

Gonzalez, Francisco Javier

Permalink

https://hdl.handle.net/2142/101628 Copy

Description

Title

Learning low-dimensional feature dynamics using convolutional recurrent autoencoders

Author(s)

Gonzalez, Francisco Javier

Issue Date

2018-07-20

Director of Research (if dissertation) or Advisor (if thesis)

Balajewicz, Maciej

Department of Study

Aerospace Engineering

Discipline

Aerospace Engineering

Degree Granting Institution

University of Illinois at Urbana-Champaign

Degree Name

M.S.

Degree Level

Thesis

Keyword(s)

• Nonlinear model reduction
• deep learning
• dynamical systems
• data-driven modeling
• convolutional neural networks
• recurrent neural networks

Abstract

Model reduction of high-dimensional dynamical systems alleviates computational burdens faced in various tasks from design optimization to model predictive control. One popular model reduction approach is based on projecting the governing equations onto a subspace spanned by basis functions obtained from the compression of a dataset of solution snapshots. However, this method is intrusive since the projection requires access to the system operators. Further, some systems may require special treatment of nonlinearities to ensure computational efficiency or additional modeling to preserve stability. In this work we propose a deep learning-based strategy for nonlinear model reduction that is inspired by projection-based model reduction where the idea is to identify some optimal low-dimensional representation and evolve it in time. Our approach constructs a modular model consisting of a deep convolutional autoencoder and a modified LSTM network. The deep convolutional autoencoder returns a low-dimensional representation in terms of coordinates on some expressive nonlinear data-supporting manifold. The dynamics on this manifold are then modeled by the modified LSTM network in a computationally efficient manner. An offline training strategy that exploits the model modularity is also developed. We demonstrate our model on three illustrative examples each highlighting the model's performance in prediction tasks for systems with large parameter-variations and its stability in long-term prediction.

Graduation Semester

2018-08

Type of Resource

text

Permalink

http://hdl.handle.net/2142/101628

Copyright and License Information

Copyright 2018 Francisco J. Gonzalez

Owning Collections