Sun Research Group at Columbia University
  • Home
  • News
  • PI
  • Team Members
  • Publications
  • Research
  • Teaching
  • Software & Data
  • Presentations
  • Recruitment & Advice
  • ML for Mechanics
  • Home
  • News
  • PI
  • Team Members
  • Publications
  • Research
  • Teaching
  • Software & Data
  • Presentations
  • Recruitment & Advice
  • ML for Mechanics

Our paper on using manifold embedding to enable distance-minimizing model-free/data-driven simulations for finite elasticity problems has been accepted by JMPS

5/4/2022

0 Comments

 
This paper (see the preprint available here) introduces a manifold embedding data-driven paradigm to solve small- and finite-strain elasticity problems without a conventional constitutive law. ​
Picture

​

Traditionally, data-driven paradigm often replace a constitutive law with a search that select an experimental data point that is " the closest" to the balance principle. However, how distance or length is measured remains ambiguous. Often time, an arbitrarily energy norm is chosen, but such a practice has shown to be affected which closest data point is getting selected. In particular, in a nonlinear manifold, the shortest distance between two points and the Euclidean distance can be quite different when they are far apart. Furthermore, the resultant model-free simulation could be sensitive to the chosen norm used to measure distance (see figure below). ​
Picture
We follows the classical data-driven paradigm by seeking the solution that obeys the balance of linear momentum and compatibility conditions while remaining consistent with the material data through minimizing a distance measure. Our key point of departure is the introduction of a global manifold embedding as a means to learn the geometrical trend of the constitutive data mathematically represented by a smooth manifold.

Conventionally, an incremental nonlinear constitutive update is sought by solving a sequence of linearized equations that moves along the admissible range of the constitutive law until the solution is found. Instead of doing this, we propose to simply deform the phase space where the nonlinear constitutive law exists such that the resultant constitutive law in the deformed space appear to be linear. 

A pair of neural networks (see below) are trained to learn (1) how to deform this nonlinear constitutive manifold to make it flat (i.e. there is one normal vector everywhere in the deformed hyperplane), and (2) how to deform the hyperplane back into a smooth manifold. Consequently, the flatness of the deformed hyperplane then makes it very easy to measure the distance between a point and the hyperplane, while the inverse map allows us to convert the local search result back into a point in the nonlinear constitutive law. 
Picture
By training an invertible neural network to embed the data of an underlying constitutive manifold onto a Euclidean space, we reformulate the local distance-minimization problem such that it replace the computationally intensive combinatorial search to identify the optimal data points closest to the conservation law with a cost-efficient projection step.

Meanwhile, numerical experiments performed on path-independent elastic materials of different material symmetries suggest that the geometrical inductive bias learned by the neural network is helpful to ensure more consistent predictions when dealing with data sets of limited sizes or those with missing data (see examples below).
Picture
Picture
0 Comments



Leave a Reply.

    Group News

    News about Computational Poromechanics lab at Columbia University.

    Categories

    All
    Invited Talk
    Job Placements
    Journal Article
    Presentation
    Special Events

    Archives

    December 2022
    November 2022
    August 2022
    July 2022
    May 2022
    April 2022
    March 2022
    December 2021
    November 2021
    October 2021
    September 2021
    August 2021
    July 2021
    June 2021
    May 2021
    April 2021
    March 2021
    February 2021
    January 2021
    October 2020
    August 2020
    July 2020
    June 2020
    May 2020
    February 2020
    January 2020
    December 2019
    September 2019
    July 2019
    June 2019
    May 2019
    April 2019
    March 2019
    February 2019
    December 2018
    October 2018
    September 2018
    August 2018
    July 2018
    June 2018
    May 2018
    April 2018
    March 2018
    January 2018
    December 2017
    November 2017
    October 2017
    September 2017
    August 2017
    July 2017
    June 2017
    May 2017
    April 2017
    March 2017
    February 2017
    January 2017
    December 2016
    November 2016
    October 2016
    May 2016
    April 2016
    March 2016
    February 2016
    January 2016
    November 2015
    October 2015
    September 2015
    August 2015
    July 2015
    June 2015
    May 2015
    March 2015
    February 2015
    January 2015
    December 2014
    November 2014
    October 2014
    September 2014
    August 2014
    July 2014
    June 2014
    May 2014
    April 2014
    March 2014
    February 2014
    January 2014
    November 2013
    September 2013

    RSS Feed

Contact Information
Prof. Steve Sun
Phone: 212-851-4371 
Fax: +1 212-854-6267
Email: wsun@columbia.edu
Copyright @ 2014-2022.  All rights reserved.