Field-level prediction of mid-plane stress tensor fields in concrete target penetration: a cross-velocity graph neural operator surrogate
作者: Wenpu Du, Peng Zhou, Yunlong Xia, Sinuo Xin, Congcong Zhang, Boyang Zhang, Yi Zhang, Wenzheng Xu
分类: cs.LG
发布日期: 2026-09-09
💡 一句话要点
提出图神经算子代理以预测混凝土靶材的应力张量场
🎯 匹配领域: 支柱四:生成式动作 (Generative Motion)
关键词: 混凝土穿透 应力张量 图神经网络 时变应力场 数值模拟 材料科学 工程结构 抗冲击设计
📋 核心要点
- 现有方法缺乏将混凝土中观异质性与全场应力张量预测相结合的框架,限制了对穿透过程的深入理解。
- 本文提出了一种基于图神经网络的算子代理,能够学习时变应力场的演变,并进行交叉速度的外推评估。
- 实验结果表明,模型在穿透深度预测上取得了显著提升,相较于传统方法速度提升约3.6至4.3倍。
📝 摘要(中文)
尽管混凝土的抗冲击性已被广泛研究,但缺乏将中观异质性与全场应力张量预测相联系的框架。本文基于全尺度的LS-DYNA模型生成了包含400个案例的应力张量场数据集,并通过与已发表的穿透实验进行验证。研究报告了三个主要贡献:首先,通过逐案例验证终端穿透状态,确定了穿透深度的有效性;其次,提出了一种图神经算子代理,学习了时变应力场的演变;最后,建立了一个可重复的全尺度、交叉速度的数据库,作为研究资源。实验结果显示,穿透深度在不同速度下的表现差异,验证了模型的有效性。
🔬 方法详解
问题定义:本文旨在解决混凝土靶材穿透过程中的应力张量场预测问题,现有方法在处理中观异质性与全场应力预测时存在不足。
核心思路:通过构建图神经算子代理,学习应力场的时变演变,进而实现对不同速度下穿透过程的有效预测。
技术框架:整体框架包括数据生成、模型训练和验证三个主要模块。数据生成使用LS-DYNA模型,模型训练则基于图神经网络,最后通过与实验数据的对比进行验证。
关键创新:最重要的创新在于提出了图神经算子代理,能够有效捕捉应力场的时变特性,与传统的数值模拟方法相比,具有更高的计算效率和准确性。
关键设计:在模型设计中,采用了特定的损失函数以优化应力场预测精度,并通过多层图神经网络结构来增强模型的表达能力。
🖼️ 关键图片
📊 实验亮点
实验结果显示,模型在穿透深度预测上相较于传统LS-DYNA方法实现了约3.6至4.3倍的速度提升,单步相对L2误差为0.6977,验证了模型的有效性和实用性。
🎯 应用场景
该研究的潜在应用领域包括工程结构的抗冲击设计、材料科学中的应力分析以及军事领域的弹道研究。通过提供高效的应力场预测工具,能够为相关领域的决策支持提供重要参考,推动材料设计与优化的进程。
📄 摘要(原文)
Although the impact resistance of concrete has been studied extensively, a framework linking mesoscale heterogeneity to full-field stress-tensor prediction has been lacking. Data were generated with a full-scale aggregate-resolved LS-DYNA model (projectile diameter 45 mm, mass 2.13 kg, target diameter 500 mm x thickness 200 mm, mesh 10 mm), verified against published penetration experiments (Frew 2006, Hanchak 1992, Forrestal 1996) by configuration similarity. The dataset contains six-component stress-tensor fields on the X-Z mid-plane for 400 cases (4 impact velocities x 100 aggregate seeds). Three contributions are reported. First, case-by-case verification of the terminal penetration state delimited the rest-state validity of penetration depth and anchored reliable observables to rigid-body motion and field-level stress evolution. Second, a field-level graph neural operator surrogate learned the time-varying stress-field evolution and evaluated cross-velocity leave-one-out extrapolation. Third, the full-scale, aggregate-resolved, cross-velocity, per-seed database was established as a reproducible resource. Cases at 100, 135 and 200 m/s still moved at window end (negative velocity, i.e. rebound), and only one 165 m/s case arrested. Penetration depth is therefore not reported as a rest-state scalar except for the single arrested case (69.33 mm); nose-node depth differences were confirmed as numerical artifacts of displacement integration after erosion. The single-step relative L2 error was 0.6977, reported honestly; autoregressive rollout from frame 11 to 39 took about 144 ms, a speedup of about 3.6x10^3 to 4.3x10^3 relative to single-core LS-DYNA, reported as application value. Validation is bounded by configuration similarity and field-level self-consistency; the framework is a simulation-trained decision-support method within the studied parameter space.