arXiv：cs.LG（机器学习，全量分类）· Ruixin Zhou, Boliang Yu·· 14 小时前AI 评分24
颗粒剪切启动中加载历史与窗口几何如何限制紧凑态滑移排序
Loading history and window geometry bound compact-state slip ranking during granular shear startup
AI 导读
研究用紧凑神经评分（应力、压力、配位数、非仿射运动与力网络观测量）在缓慢剪切的二维摩擦圆盘上分离材料状态、加载进度与事件采样几何对颗粒滑移预测的影响。模型在36条轨迹上开发、冻结后在18条新轨迹上测试，紧凑评分在两种嵌套应力降定义下均将近滑移窗口排在流行率和轨迹内循环相位对照之上（代表性平均精度0.310，流行率0.173，相位零假设上界0.257）。
正文
Abstract:Granular slip forecasting can conflate material state, loading progress, and the geometry of event-centered sampling. We separated these contributions in slowly sheared two-dimensional frictional disks using a compact neural score of stress, pressure, coordination, non-affine motion, and force-network observables. The model was developed on 36 trajectories and frozen efore testing on 18 new trajectories under two nested stress-drop definitions. Inspection of held-out results revealed post-event sampling asymmetry; recovery-aware analyses are therefore descriptive. With trajectories weighted equally, the compact score ranked near-slip windows above both prevalence and within-trajectory circular-phase controls under both definitions (representative average precision 0.310 versus prevalence 0.173; phase-null upper bound 0.257). Loading-history coordinates ranked more strongly, reaching 0.534 for causal elapsed strain. The recovery-aware rule retained 78.4\% of activity-gated events and preferentially selected longer preceding intervals; ranking by time since the previous catalogued event remained compatible with a count-conditioned geometry null. Compact observables thus contain temporally aligned slip information, but stronger loading-history baselines and window-geometry sensitivity bound that evidence. These startup data do not isolate a state-specific short-horizon precursor beyond loading history or support a renewal interpretation of elapsed-strain ranking.
| Comments: | 28 pages, 6 figures |
| Subjects: | Soft Condensed Matter (cond-mat.soft); Statistical Mechanics (cond-mat.stat-mech); Machine Learning (cs.LG); Computational Physics (physics.comp-ph) |
| Cite as: | arXiv:2610.00124 [cond-mat.soft] |
| (or arXiv:2610.00124v1 [cond-mat.soft] for this version) | |
| https://doi.org/10.48550/arXiv.2610.00124 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Boliang Yu [view email]
[v1]
Wed, 9 Sep 2026 16:57:39 UTC (1,072 KB)
来源：arXiv：cs.LG（机器学习，全量分类） · arxiv.org