Towards Reusable Surrogate Models: Graph-Based Transfer Learning on Trusses

Abstract

Surrogate models have several uses in engineering design, including speeding up design optimization, noise reduction, test measurement interpolation, gradient estimation, portability, and protection of intellectual property. Traditionally, surrogate models require that all training data conform to the same parametrization (e.g. design variables), limiting design freedom and prohibiting the reuse of historical data. In response, this paper proposes Graph-based Surrogate Models (GSMs) for trusses. The GSM can accurately predict displacement fields from static loads given the structure's geometry as input, enabling training across multiple parametrizations. GSMs build upon recent advancements in geometric deep learning which have led to the ability to learn on undirected graphs: a natural representation for trusses. To further promote flexible surrogate models, the paper explores transfer learning within the context of engineering design, and demonstrates positive knowledge transfer across data sets of different topologies, complexities, loads and applications, resulting in more flexible and data-efficient surrogate models for trusses.

Accepted to the ASME Journal of Mechanical Design

References in corpus (14)

• Adam: A Method for Stochastic Optimization
• Scikit-learn: Machine Learning in Python
• A Comprehensive Survey on Graph Neural Networks
• Geometric deep learning: going beyond Euclidean data
• Graph Neural Networks: A Review of Methods and Applications
• Fast Graph Representation Learning with PyTorch Geometric
• MeshCNN: A Network with an Edge
• Geometric deep learning for computational mechanics Part I: Anisotropic Hyperelasticity
• Integrating Deep Learning into CAD/CAE System: Generative Design and Evaluation of 3D Conceptual Wheel
• Multi-level Convolutional Autoencoder Networks for Parametric Prediction of Spatio-temporal Dynamics
• StressGAN: A Generative Deep Learning Model for 2D Stress Distribution Prediction
• Learning to design from humans: Imitating human designers through deep learning
• StructureNet: Hierarchical Graph Networks for 3D Shape Generation
• Learning to simulate and design for structural engineering

Cited by in corpus (6)

• Graph Neural Network for Stress Predictions in Stiffened Panels Under Uniform Loading
• Heterogeneous Graph Representation of Stiffened Panels with Non-Uniform Boundary Conditions and Loads
• Scalar Field Prediction on Meshes Using Interpolated Multi-Resolution Convolutional Neural Networks
• Machine learning for structural design models of continuous beam systems via influence zones
• A hypergraph model shows the carbon reduction potential of effective space use in housing
• Text2Structure3D: Graph-Based Generative Modeling of Equilibrium Structures with Diffusion Transformers