Skip to main navigation Skip to search Skip to main content

I-FENN with DeepONets: Accelerating simulations in coupled multiphysics problems

Research output: Contribution to journal › Article › peer-review

Abstract

Coupled multiphysics simulations for high-dimensional, large-scale problems can be prohibitively expensive due to their computational demands. This article presents a novel framework integrating a deep operator network (DeepONet) with the Finite Element Method (FEM) to address coupled thermoelasticity and poroelasticity problems. This integration occurs within the context of the I-FENN framework, where a neural network (NN) is coupled with FEM in a hybrid staggered solver. In this approach, FEM computes the mechanical field while the NN predicts the coupled field, effectively reducing the number of FEM unknowns and lowering the overall computational cost. The proposed work introduces a new I-FENN architecture with extended generalizability due to the DeepONets’ ability to efficiently address several combinations of natural boundary conditions and body loads. A modified DeepONet architecture is introduced to accommodate multiple inputs, along with a streamlined strategy for enforcing boundary conditions on distinct boundaries. We showcase the applicability and merits of the proposed work through numerical examples covering thermoelasticity and poroelasticity problems, demonstrating computational efficiency, accuracy, and generalization capabilities. In all examples, the test cases involve unseen loading conditions. The computational savings scale with the model complexity while preserving an accuracy of more than 95 % in the non-trivial regions of the domain.

Original languageEnglish (US)
Article number118645
JournalComputer Methods in Applied Mechanics and Engineering
Volume451
DOIs
StatePublished - Apr 1 2026

Keywords

  • DeepONet
  • Enforcing boundary conditions
  • I-FENN
  • MIONet
  • Multiphysics
  • Poroelasticity
  • Thermoelasticity

ASJC Scopus subject areas

  • Computational Mechanics
  • Mechanics of Materials
  • Mechanical Engineering
  • General Physics and Astronomy
  • Computer Science Applications

Fingerprint

Dive into the research topics of 'I-FENN with DeepONets: Accelerating simulations in coupled multiphysics problems'. Together they form a unique fingerprint.

Cite this