Cornerstones are the key stones: Using interpretable machine learning to probe the clogging process in 2D granular hoppers

This dataset contains the information recorded for approximately 50,000 hopper flows under varying conditions. Each file represents a single flow event, from beginning of flow to final clog forming. The files are matlab structures, containing the positions, radii, frame number, tracked particle ID's and velocities for every grain in the camera field of view throughout the flow. Other values, such as the position of the outlet and the total mass ejected during the flow are also included., Data are the tracked positions of grains throughout individual hopper flows (beginning of flow to final clog). A camera records images of grains near the outlet at 130 frames per second, which was then analyzed using matlab code. The grain centers were located and species (size) identified; this information was then fed into a tracking algorithm to uniquely identify grains throughout flow. From these unique identifiers, velocity and ejected mass information was calculated. , , # Data from: Cornerstones are the key stones: Using interpretable machine learning to probe the clogging process in 2D granular hoppers ## Grain positions during hopper flow for Autohopper Data are the grain positions, velocities, sizes, and IDs throughout the flow from the breaking of a clog to a new stable clog forming in a granular hopper. Grains are a tridisperse mixture of discs made from anti-static Ultra High Molecular Weight Polyethylene. The hopper is two vertical sheets of plexiglass with enough space between them to admit a single layer of discs with minimal displacement. Images of the grains during flow were recorded using a camera, and grain locations were tracked using custom MATLAB code. ## Description of the data and file structure The data are separated into three folders reflecting different experimental conditions. The folder FixedParticle.zip contains 5551 flows in which a fixed grain was inserted near the outlet, systematically affecting the flow. SingleOutletNo...,本数据集包含约50000组不同实验条件下的料斗流动（hopper flow）记录数据。每个文件对应单次流动事件，从流动开始直至最终形成堵塞（clog）。所有文件均为MATLAB结构体，存储了流动全程中相机视场内所有颗粒的位置、半径、帧号、追踪粒子ID以及速度信息，同时还包含出口位置、流动过程中总喷出质量等其他参数。 数据集核心数据为单次料斗流动（从流动起始至最终堵塞形成）全程中颗粒的追踪位置。实验采用帧率为130帧每秒的相机采集出口附近的颗粒图像，随后通过MATLAB代码进行分析：首先定位颗粒质心并识别其粒径种类，再将该信息输入追踪算法（tracking algorithm）以在流动全程中唯一区分各颗粒，最终基于这些唯一标识符计算得到颗粒速度与喷出质量等信息。 # 数据来源：《基石即关键：利用可解释机器学习探究二维颗粒料斗的堵塞过程》 # 自动料斗（Autohopper）的料斗流动颗粒位置数据 本数据集包含颗粒料斗中从一次堵塞破除至新稳定堵塞形成的全程流动数据，涵盖颗粒的位置、速度、粒径与ID信息。实验所用颗粒为抗静电超高分子量聚乙烯（Ultra High Molecular Weight Polyethylene）制成的圆盘颗粒，采用三分散混合体系。料仓由两块垂直有机玻璃（plexiglass）板构成，板间距仅可容纳单层圆盘颗粒且位移受限。实验通过相机采集流动过程中的颗粒图像，并借助定制MATLAB代码完成颗粒位置的追踪。 # 数据与文件结构说明 数据集按不同实验条件分为三个文件夹。其中FixedParticle.zip压缩包包含5551组流动数据，该组实验在出口附近植入固定颗粒，以此系统性地改变流动特性。SingleOutletNo...