TRACE：用于颗粒动力学的时空接触记忆图网络模拟器
TRACE: A spatiotemporal contact memory graph network simulator for granular dynamics
- Faculty of Engineering and IT, The University of Melbourne（墨尔本大学工程与信息技术学院）
- School of Computing, National University of Singapore（新加坡国立大学计算机学院）
- Norwegian Geotechnical Institute（挪威岩土工程研究所）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
TRACE是直接在接触边存储交互历史的图网络模拟器，经单步预训练与自回归微调后，在2D、3D颗粒柱坍塌基准上，相比GNS、NMGNS等方法误差显著降低且运行更快。
AI中文摘要：
学习得到的图模拟器是颗粒动力学高保真求解器的高效替代方案。然而，颗粒运动强烈依赖颗粒间的接触历史，当颗粒接触形成、断裂和重新排列时，这类历史信息难以保留。现有模拟器主要将时间信息存储在节点特征或节点级记忆中。本文提出TRACE，一种直接在接触边存储交互历史的图网络模拟器：每条边维护通过基于注意力的消息传递和门控循环单元更新的持久记忆，边身份字典在接触图变化时保留该记忆；物理结构解码器预测颗粒间法向和切向接触力，满足库仑摩擦极限并应用大小相等、方向相反的内力。模型采用单步预训练后经自回归展开微调，在2D和3D颗粒柱坍塌基准上评估：两种场景下TRACE均生成稳定、物理一致的长时程展开结果，精准复现最终沉积形态及坍塌过程释放的动能；与图网络模拟器（GNS）、节点记忆图神经模拟器（NMGNS）相比，TRACE在两个基准上分别将长时程展开位置误差降低31%-62%、最终沉积误差降低58%-89%，同时参数更少且保持颗粒几乎无相互穿透；TRACE在2D和3D场景下分别比物质点法（MPM）参考求解器提速12.2倍和8.9倍，代码可在指定网址获取。
英文摘要：
Learned graph simulators provide an efficient alternative to high-fidelity solvers for granular dynamics. However, granular motion depends strongly on inter-granular contact history, which is difficult to preserve when particle contacts form, break, and rearrange. Existing simulators mainly store temporal information in node features or node-level memory. Here we introduce TRACE, a graph-network simulator that stores interaction history directly on contact edges. Each edge maintains a persistent memory updated by attention-based message passing and a gated recurrent unit, while an edge-identity dictionary preserves this memory as the contact graph changes. A physics-structured decoder predicts inter-granular normal and tangential contact forces, enforces the Coulomb friction limit, and applies equal-and-opposite internal forces. The model is trained with single-step pretraining followed by autoregressive rollout fine-tuning. We evaluate TRACE on 2D and 3D granular column-collapse benchmarks. In both cases, TRACE produces stable, physically consistent long-horizon rollouts, closely reproducing the final deposit geometry and the kinetic energy released during collapse. Compared with graph network simulator (GNS) and node-memory graph neural simulator (NMGNS), TRACE reduces long-rollout position error by 31-62% and final-deposit error by 58-89% across the two benchmarks, while using fewer parameters and maintaining near-zero particle interpenetration. TRACE also achieves 12.2$\times$ and 8.9$\times$ speedups over the material point method (MPM) reference solver in 2D and 3D, respectively. Our code is available at https://github.com/Data-Driven-Computational-Geotechnics/TRACE.
