使用PCA和机器学习模型对滑油基油生产厂的自动模式检测进行调查分析
Muhamad Amir Mohd Fadzil1, Adi Aizat Razali1, Haslinda Zabiri2
1Group Research & Technology, PETRONAS, Kawasan Institusi Bangi, Kajang 43000, Selangor, Malaysia.
ACS omega
|January 29, 2024
概括
本研究使用机器学习引入了滑油基油模式的每小时预测模型. XGBoost模型准确地预测了动力学粘度变化,大大减少了非规格产品和工业滑剂生产中的废物.
科学领域:
- 工业化学和工艺工程 工业化学和工艺工程
- 数据科学和机器学习应用程序数据科学和机器学习应用程序
背景情况:
- 在工业应用中,滑剂对于抑制摩擦和传热至关重要.
- 目前的方法依赖于8小时的动力粘度实验室分析,延迟了基油模式变化 (4,6,10 cSt) 和过渡的检测.
- 延迟检测导致大量生产非规格产品和增加浪费.
研究的目的:
- 开发一种新的工业应用,用于每小时预测基油动力学粘度模式和转变.
- 通过实时模式检测来减少与非规格产品和废物相关的损失.
- 为了确定与动力学粘度变化相关的植物数据中的基本模式.
主要方法:
- 在42,000个运行工厂数据点上利用主要组件分析 (PCA) 来确定关键的相关因素.
- 第三个主要组成部分,显示了对八个基油类 (3种模式+5种过渡) 的最高相关性,被用作输入.
- 实现并比较了使用过程变量和小时预测的第三个主要组件的XGBoost,Random Forest和CatBoost机器学习模型.
主要成果:
- 来自PCA的第三个主要成分与所有八个基油模式类别都表现出强烈的相关性.
- XGBoost算法实现了最高和最一致的分类准确性:在测试集上达到92.96%,在部署集上达到89.22%.
- 开发的模型允许每小时预测基油模式,这与之前的8小时分析间隔相比是显著的改进.
结论:
- 使用机器学习,特别是XGBoost,每小时预测基油模式是可行的和有效的.
- 这种预测能力可以大幅减少非规格产品的产生,并减少滑剂制造中的浪费.
- 该研究介绍了PCA和ML在滑油行业实时过程监控和优化方面的新应用.
更多相关视频
07:29HPLC Coupled with Chemical Fingerprinting for Multi-Pattern Recognition for Identifying the Authenticity of Clematidis Armandii Caulis
Published on: November 11, 2022
2.0K
08:38Microfluidic Devices for Characterizing Pore-scale Event Processes in Porous Media for Oil Recovery Applications
Published on: January 16, 2018
10.5K
相关概念视频
01:23Design Example: Deciding Thickness of Lubricating Fluid in a Shaft
110
Effective lubrication between a rotating shaft and its bearing housing is essential in rotating machinery to minimize friction, wear, and energy loss. With carefully controlled thickness and viscosity, the lubricant layer prevents metal-to-metal contact, ensuring smooth operation.
To calculate the required thickness of the lubricant layer, the tangential velocity at the shaft's surface must first be determined. This velocity is calculated by converting the rotational speed to angular...
To calculate the required thickness of the lubricant layer, the tangential velocity at the shaft's surface must first be determined. This velocity is calculated by converting the rotational speed to angular...
110
01:29Mechanistic Models: Compartment Models in Algorithms for Numerical Problem Solving
55
Mechanistic models play a crucial role in algorithms for numerical problem-solving, particularly in nonlinear mixed effects modeling (NMEM). These models aim to minimize specific objective functions by evaluating various parameter estimates, leading to the development of systematic algorithms. In some cases, linearization techniques approximate the model using linear equations.
In individual population analyses, different algorithms are employed, such as Cauchy's method, which uses a...
In individual population analyses, different algorithms are employed, such as Cauchy's method, which uses a...
55