Differentiable Multiphysics Co-Optimization via Implicit Neural Representations: A Transient Hamburger-Cooking Benchmark

• URL: http://arxiv.org/abs/2605.01040v1
• Date: Fri, 01 May 2026 19:08:14 GMT
• Title: Differentiable Multiphysics Co-Optimization via Implicit Neural Representations: A Transient Hamburger-Cooking Benchmark
• Abstract summary: We present an end-to-end differentiable co-optimization framework that couples an implicit neural representation of geometry with a JAX-compiled Eulerian multiphysics solver.<n>Results show that geometry-only optimization modifies shape to relieve thermal bottlenecks, while joint co-optimization distributes the design response across geometry, material state, process variables, and boundary conditions.
• Score: 0.40611352512781856
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The co-optimization of geometry and physical parameters remains challenging in transient multiphysics systems involving moving boundaries, nonlinear material response, phase transitions, and competing objectives. Existing methods often optimize geometry and physical variables separately, rely on simplified steady-state physics, or require offline data generation and reduced design spaces. Here, we present an end-to-end differentiable co-optimization framework that couples an implicit neural representation of geometry with a JAX-compiled Eulerian multiphysics solver. Geometry is represented as a signed distance field using Fourier-feature-encoded spatial coordinates, while boundary conditions, initial conditions, process controls, and material parameters are optimized within the same differentiable loop. Continuous relaxations represent non-smooth physical transitions while preserving compatibility with reverse-mode automatic differentiation and backpropagation through time. We demonstrate the framework using a transient hamburger-cooking benchmark, selected as an interpretable multiphysics problem rather than a culinary optimization exercise. The benchmark combines conductive and convective heat transfer, latent energy effects, moisture and fat transport, shrinkage-induced geometry evolution, evolving contact boundary conditions, flipping-induced boundary-condition changes, and competing quality objectives. Results show that geometry-only optimization modifies shape to relieve thermal bottlenecks, while joint co-optimization distributes the design response across geometry, material state, process variables, and boundary conditions through gradients propagated over the full transient rollout.

Related papers

• A meshfree exterior calculus for generalizable and data-efficient learning of physics from point clouds [8.15594797043476]
  We introduce a meshfree exterior calculus (MEEC) for learning structure-preserving descriptions of physics on point clouds.<n>We use it to build MEEC-Net, a data-efficient surrogate that transfers across resolutions, geometries, and physical parameters.
  arXiv  Detail & Related papers  (2026-05-08T19:59:40Z)
• Differentiable SpaTiaL: Symbolic Learning and Reasoning with Geometric Temporal Logic for Manipulation Tasks [10.590774471054255]
  Executing complex manipulation in cluttered environments requires satisfying geometric and temporal constraints.<n>We propose Differentiable SpaTiaL, a fully tensorized toolbox that constructs smooth, autograd-compatible geometric primitives directly over polygonal sets.<n>By deriving differentiable relaxations of key spatial predicates, we enable an end-to-end different semanticiable mapping from high-level specifications to low-level geometric configurations.
  arXiv  Detail & Related papers  (2026-04-03T02:13:47Z)
• A Unified Low-Dimensional Design Embedding for Joint Optimization of Shape, Material, and Actuation in Soft Robots [4.829343342713712]
  We introduce a smooth, low-dimensional design embedding for soft robots that unifies shape morphing, multi-material distribution, and actuation.<n>In experiments, we show that design increases with the number of basis functions, unlike comparable neural network encodings.<n>We further show that joint co-optimization of shape, material, and actuation using our unified embedding consistently outperforms sequential strategies.
  arXiv  Detail & Related papers  (2026-03-06T17:33:32Z)
• Surrogate-Based Differentiable Pipeline for Shape Optimization [64.24199762940444]
  We propose replacing non-differentiable pipeline components with surrogate models which are inherently differentiable.<n>We demonstrate an end-to-end differentiable pipeline where a 3D U-Net full-field surrogate replaces both meshing and simulation steps by training it on the mapping between the signed distance field (SDF) of the shape and the fields of interest.
  arXiv  Detail & Related papers  (2025-11-13T19:30:50Z)
• Transolver: A Fast Transformer Solver for PDEs on General Geometries [66.82060415622871]
  We present Transolver, which learns intrinsic physical states hidden behind discretized geometries. By calculating attention to physics-aware tokens encoded from slices, Transovler can effectively capture intricate physical correlations. Transolver achieves consistent state-of-the-art with 22% relative gain across six standard benchmarks and also excels in large-scale industrial simulations.
  arXiv  Detail & Related papers  (2024-02-04T06:37:38Z)
• Transferable Model for Shape Optimization subject to Physical Constraints [0.0]
  We provide a method which enables a neural network to transform objects subject to given physical constraints. An U-Net architecture is used to learn the underlying physical behaviour of fluid flows. The network is used to infer the solution of flow simulations.
  arXiv  Detail & Related papers  (2021-03-19T13:49:21Z)
• ResNet-LDDMM: Advancing the LDDMM Framework Using Deep Residual Networks [86.37110868126548]
  In this work, we make use of deep residual neural networks to solve the non-stationary ODE (flow equation) based on a Euler's discretization scheme. We illustrate these ideas on diverse registration problems of 3D shapes under complex topology-preserving transformations.
  arXiv  Detail & Related papers  (2021-02-16T04:07:13Z)
• Fast Gravitational Approach for Rigid Point Set Registration with Ordinary Differential Equations [79.71184760864507]
  This article introduces a new physics-based method for rigid point set alignment called Fast Gravitational Approach (FGA) In FGA, the source and target point sets are interpreted as rigid particle swarms with masses interacting in a globally multiply-linked manner while moving in a simulated gravitational force field. We show that the new method class has characteristics not found in previous alignment methods.
  arXiv  Detail & Related papers  (2020-09-28T15:05:39Z)
• Scalable Differentiable Physics for Learning and Control [99.4302215142673]
  Differentiable physics is a powerful approach to learning and control problems that involve physical objects and environments. We develop a scalable framework for differentiable physics that can support a large number of objects and their interactions.
  arXiv  Detail & Related papers  (2020-07-04T19:07:51Z)
• Geodesics in fibered latent spaces: A geometric approach to learning correspondences between conditions [62.997667081978825]
  This work introduces a geometric framework and a novel network architecture for creating correspondences between samples of different conditions. Under this formalism, the latent space is a fiber bundle stratified into a base space encoding conditions, and a fiber space encoding the variations within conditions.
  arXiv  Detail & Related papers  (2020-05-16T03:14:52Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.