What is it about?
This research paper explores the use of artificial neural networks (ANNs) to predict the yield of biolubricants based on input process parameters such as temperature, catalyst loading, and alcohol/FAME ratio. The study also analyzes the tribological properties of the biolubricant samples produced. ANNs are robust computational means for solving problems, particularly in biotechnology, where the underlying theory is less obvious but the data is accessible. The authors aim to address the research question of predicting biolubricant yield using ANNs, which has not been investigated before. The study found that the relative sensitivity of temperature to biolubricant yield was lower than that of catalyst loading and alcohol/FAME ratios.
Featured Image
Photo by Annie Spratt on Unsplash
Why is it important?
This publication is about producing eco-friendly biolubricant. The authors used ANN for modeling. They also perfumed experiments using a few different factors like temperature and the amount of certain chemicals. The paper includes illustrations to show how the experiments were done and what the results were. Anyone who wants to make more environmentally friendly oil might find this paper useful.
Read the Original
This page is a summary of: Biolubricant production from castor oil using iron oxide nanoparticles as an additive: Experimental, modelling and tribological assessment, Fuel, September 2022, Elsevier,
DOI: 10.1016/j.fuel.2022.124565.
You can read the full text:
Contributors
The following have contributed to this page
