About this document
A Constrained Machine Learning Surrogate Model To by Сергей Кубах is a document available to read on EtoBox.
This document presents a constrained machine learning surrogate model designed to predict the distribution of water-in-oil emulsions under electrostatic fields, enhancing water separation efficiency in dehydration systems. The model, utilizing an extreme gradient boosting (XGBoost) algorithm fine-tuned with a genetic algorithm, incorporates key parameters such as droplet diameter and voltage, achieving high accuracy with a mean squared error of 0.005. The study highlights the importance of droplet size and
- Author
- Сергей Кубах
- Language
- EN