A Dual-Graph Spatiotemporal GNN Surrogate for Nonlinear Response Prediction of Reinforced Concrete Beams under Four-Point Bending

TL;DR

This paper introduces a dual-graph spatiotemporal GNN surrogate model that efficiently predicts the nonlinear response of reinforced concrete beams under four-point bending, significantly reducing computational costs compared to traditional finite-element simulations.

Contribution

The paper presents a novel dual-graph GNN architecture that couples node- and element-level dynamics for accurate, fast prediction of RC beam responses, including internal stresses and displacements.

Findings

Accurately predicts full response trajectories at reduced computational cost.

Coupling node and element dynamics improves localized stress predictions.

Model enables rapid parametric analysis and design exploration.

Abstract

High-fidelity nonlinear finite-element (FE) simulations of reinforced-concrete (RC) structures are still costly, especially in parametric settings where loading positions vary. We develop a dual-graph spatiotemporal GNN surrogate to approximate the time histories of RC beams under four-point bending. To generate training data, we run a parametric Abaqus campaign that independently shifts the two loading blocks on a mesh-aligned grid and exports full-field responses at fixed normalized loading levels. The model rolls out autoregressively and jointly predicts nodal displacements, element wise von Mises stress, element-wise equivalent plastic strain (PEEQ), and the global vertical reaction force in a single multi-task setup. A key motivation is the peak loss introduced when element quantities are forced through node-based representations. We therefore couple node- and element-level dynamics using two recurrent graph branches: a node-level graph convolutional gated recurrent unit (GConvGRU) for kinematics and an element-level GConvGRU for history-dependent internal variables, with global force predicted through pooling on the element branch. In controlled ablations, removing the Element to Node to Element pathway improves peak-sensitive prediction in localized high-gradient stress/PEEQ regions without degrading global load displacement trends. After training, the surrogate produces full trajectories at a fraction of the cost of nonlinear FE, enabling faster parametric evaluation and design exploration.