相关实验视频
Updated: Jun 13, 2026

Image-based Lagrangian Particle Tracking in Bed-load Experiments
Published on: July 20, 2017
基石是关键石:使用可解释的机器学习来探测2D颗粒式热中的堵塞过程
Jesse M Hanlan1, Sam Dillavou1, Andrea J Liu1
1Department of Physics & Astronomy, University of Pennsylvania, Philadelphia, PA 19104, USA. djdurian@physics.upenn.edu.
了解颗粒物质流,研究人员观察到成千上万的堵塞事件. 他们发现,颗粒在出口附近的位置显著影响弧形形成和流动,使得可以控制喷射的质量.
科学领域:
- 颗粒状材料的物理学 颗粒状材料的物理学
- 复杂系统的动态 复杂系统的动态
- 应用机器学习应用机器学习
背景情况:
- 颗粒状材料的特点是通过在出口上形成稳定的弧形来阻止流动.
- 导致颗粒流堵塞的精确微态配置仍然不太清楚.
- 以前的假设建议随机抽样流动微状态,但预测因素是难以捉摸的.
研究的目的:
- 通过实验识别颗粒流中堵塞微态的预测性特征.
- 调查谷物定位在阻流弧形形成中的作用.
- 证明可解释机器学习在揭示物理原理方面的实用性.
主要方法:
- 观测到超过5万个堵塞事件在一个准2D颗粒流系统与三分散混合物.
- 应用各种机器学习 (ML) 方法,包括线性支向量机 (SVM),以分析堵塞事件.
- 实验性地操纵固定"基石"粒的位置,以测试其对流量和堵塞的影响.
主要成果:
- 机器学习方法对堵塞事件显示了适度的预测能力.
- 线性SVM分析确定了潜在的门基石颗粒的位置作为堵塞可能性的关键因素.
- 基石颗粒位置的实验变化非单调地改变了流量持续时间和喷射质量,最佳定位将质量增加70%.
结论:
- 这些发现支持颗粒状材料堵塞的自下而上弧形形成机制.
- 特定颗粒的位置极大地影响弧形的稳定性和大小,从而控制流量.
- 可解释的ML,结合实验,可以揭示复杂系统的基本物理,即使具有有限的预测精度.
更多相关视频
09:00Visualization of Failure and the Associated Grain-Scale Mechanical Behavior of Granular Soils under Shear using Synchrotron X-Ray Micro-Tomography
Published on: September 29, 2019
08:21Forming Micro-and Nano-Plastics from Agricultural Plastic Films for Employment in Fundamental Research Studies
Published on: July 27, 2022
相关概念视频
Rolling Resistance: Problem Solving
Quarrying of Stone
One common method involves using a diamond belt saw to cut large blocks from the quarry face. These blocks can be about 50 feet long and 12 feet high. After the initial vertical cut, drilling is performed at the base of the block.
Specific Gravity of Aggregate
Bulk or gross specific gravity is calculated by taking the ratio of the mass of aggregates in the saturated surface-dry state to the total volume that includes both the solids and the voids within the...
Design Example: Maintaining Level of an Embankment
Design Example: Forces in Sluice Gate
Key variables in...
Hydraulic Jump: Problem Solving