摘要
机器人与机器学习的新闻编辑每日新闻-机器学习的新研究是一篇报道的主题。根据NewsRx编辑在英国伦敦的新闻报道，研究称：“本研究引入了一种机器学习(ML)辅助的图像分割方法，用于固体准二维流化床中气泡的自动识别，提高了气泡识别的准确性。用ML方法分割二值图像，并开发了内部拉格朗日变换技术来跟踪气泡的演变。”我们的新闻记者引用了伦敦大学学院(UCL)的研究，“ML辅助分割方法只需要很少的训练数据，准确率达到98.75%，并且可以过滤掉流体力学中常见的不确定性来源，例如不同的光照条件和焦点区域，从而提供了一个以标准、一致和可重复的方式研究气泡的有效工具。在一个特别具有挑战性的情况下对ML辅助ME理论进行了测试：结构化振动流化床，其中气泡位置、Velo城市和形状的时空演变是成核-传播-破裂循环的特征。实验证明了该方法的通用性和有效性。该方法能够捕捉具有挑战性的鼓泡动力学和在不同粒径的床层中观察到的速度和粒度分布的细微变化。识别了振荡床层的新特征，包括频率和粒度对气泡形态、形貌和形状因子的影响以及它们与流动稳定性的关系。通过合并和分裂事件的速率量化。
Abstract
By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News – New research on Machine Learning is th e subject of a report. According to news reporting out of London, United Kingdom , by NewsRx editors, research stated, “This study introduces a machine learning (ML)-assisted image segmentation method for automatic bubble identification in g as-solid quasi-2D fluidized beds, offering enhanced accuracy in bubble recogniti on. Binary images are segmented by the ML method, and an in-house Lagrangian tra cking technique is developed to track bubble evolution.” Our news journalists obtained a quote from the research from University College London (UCL), “The ML-assisted segmentation method requires few training data, a chieves an accuracy of 98.75%, and allows for filtering out common sources of uncertainty in hydrodynamics, such as varying illumination conditions and out-of-focus regions, thus providing an efficient tool to study bubbling in a standard, consistent, and repeatable manner. In this work, the ML-assisted me thodology is tested in a particularly challenging case: structured oscillating f luidized beds, where the spatial and time evolution of the bubble position, velo city, and shape are characteristics of the nucleation-propagation-rupture cycle. The new method is validated across various operational conditions and particle sizes, demonstrating versatility and effectiveness. It shows the ability to capt ure challenging bubbling dynamics and subtle changes in velocity and size distri butions observed in beds of varying particle size. New characteristic features o f oscillating beds are identified, including the effect of frequency and particl e size on the bubble morphology, aspect, and shape factors and their relationshi p with the stability of the flow, quantified through the rate of coalescence and splitting events.”
NETL
NSTL