Jove
Visualize
联系我们
JoVE
x logofacebook logolinkedin logoyoutube logo
关于 JoVE
概览领导团队博客JoVE 帮助中心
作者
出版流程编辑委员会范围与政策同行评审常见问题投稿
图书馆员
用户评价订阅访问资源图书馆顾问委员会常见问题
研究
JoVE JournalMethods CollectionsJoVE Encyclopedia of Experiments存档
教育
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab Manual教师资源中心教师网站
使用条款与条件
隐私政策
政策

相关概念视频

Strength and Heat of Hydration01:29

Strength and Heat of Hydration

201
The hydration of cement is an exothermic reaction in which heat is generated as cement hydrates. This heat of hydration is critical to cement's strength development. The rate at which this heat is generated affects the temperature rise, with a majority of the heat being released early in the hydration process, half within the first three days, and about 75% within the first week.
The heat of hydration for each cement compound is significant; for instance, tricalcium aluminate (C3A) and...
201

您也可能阅读

相关文章

通过共同作者、期刊和引用图与本文相关的文章。

排序
Same author

Isolated unilateral pulmonary vein atresia with hemoptysis in a child: A case report and literature review.

Medicine·2018
Same author

Clinical factors associated with intestinal strangulating obstruction and recurrence in adhesive small bowel obstruction: A retrospective study of 288 cases.

Medicine·2018
Same author

[Determination of organic acids in 1, 2-butylene oxide products by valve switch-ion chromatography].

Se pu = Chinese journal of chromatography·2018
Same author

Disruption of Planar Cell Polarity Pathway Attributable to Valproic Acid-Induced Congenital Heart Disease through Hdac3 Participation in Mice.

Chinese medical journal·2018
Same author

Multispectral and large bandwidth achromatic imaging with a single diffractive photon sieve.

Optics express·2018
Same author

Immunization with Chlamydia psittaci plasmid-encoded protein CPSIT_p7 induces partial protective immunity against chlamydia lung infection in mice.

Immunologic research·2018

相关实验视频

Updated: May 23, 2025

Additive Manufacturing of Functionally Graded Ceramic Materials by Stereolithography
06:53

Additive Manufacturing of Functionally Graded Ceramic Materials by Stereolithography

Published on: January 25, 2019

14.1K

机器学习预测了从多种固体废物中生产陶矿的烧结温度.

Guanqi Yu1, Chuan Wang2, Qianlan Zhuo3

  • 1College of Ecology and Environment, Inner Mongolia University, Hohhot, China; School of Environmental Science & Engineering, Tianjin University, Tianjin, China.

Waste management (New York, N.Y.)
|May 21, 2025
PubMed
概括

一个机器学习模型使用化学成分准确预测陶矿烧结温度. XGBoost模型显示了高性能,识别了影响过程的SiO2和Al2O3等关键组件.

关键词:
陶矿是一种陶矿.化学成分 化学成分机器学习是机器学习.这就是 SHAP SHAP 的意思.烧结温度是烧结的温度.

更多相关视频

Reducing Willow Wood Fuel Emission by Low Temperature Microwave Assisted Hydrothermal Carbonization
09:46

Reducing Willow Wood Fuel Emission by Low Temperature Microwave Assisted Hydrothermal Carbonization

Published on: May 19, 2019

8.1K
Fused Filament Fabrication FFF of Metal-Ceramic Components
08:43

Fused Filament Fabrication FFF of Metal-Ceramic Components

Published on: January 11, 2019

17.1K

相关实验视频

Last Updated: May 23, 2025

Additive Manufacturing of Functionally Graded Ceramic Materials by Stereolithography
06:53

Additive Manufacturing of Functionally Graded Ceramic Materials by Stereolithography

Published on: January 25, 2019

14.1K
Reducing Willow Wood Fuel Emission by Low Temperature Microwave Assisted Hydrothermal Carbonization
09:46

Reducing Willow Wood Fuel Emission by Low Temperature Microwave Assisted Hydrothermal Carbonization

Published on: May 19, 2019

8.1K
Fused Filament Fabrication FFF of Metal-Ceramic Components
08:43

Fused Filament Fabrication FFF of Metal-Ceramic Components

Published on: January 11, 2019

17.1K

科学领域:

  • 材料科学 材料科学 材料科学
  • 化学工程是化学工程的重要组成部分.
  • 数据科学数据科学数据科学

背景情况:

  • 从固体废物中生产陶石对于可持续性至关重要.
  • 预测烧结温度是优化陶材料质量和生产效率的关键.

研究的目的:

  • 开发一种高效的机器学习模型,用于预测陶矿烧结温度.
  • 为了确定化学成分对烧结温度的影响.
  • 评估预测模型的概括性和可靠性.

主要方法:

  • 从236个陶石样本收集了实验数据.
  • 定义了八个关键化学成分作为输入特征.
  • 训练和评估了六个机器学习模型,包括XGBoost.
  • 使用SHAP分析来确定特征的重要性和适用性领域分析来验证模型.

主要成果:

  • 该XGBoost模型实现了高预测精度 (R2=0.950,RMSE=7.767).
  • 发现SiO2和Al2O3会增加烧结温度,而CaO和MgO会降低烧结温度.
  • 该模型在未见的数据上展示了强大的概括性和预测可靠性.

结论:

  • 机器学习,特别是XGBoost,为预测陶矿烧结温度提供了一个强大的框架.
  • 了解化学成分的影响,可以从固体废物中优化陶矿生产.
  • 这种方法提高了在陶矿制造中的固体废物材料的可持续利用.