Soft computing optimization of vegetable oil extraction

Authors

  • Ude C. N Department of Chemical Engineering, Michael Okpara University of Agriculture, Umudike, Umuahia, Abia State, Nigeria
  • Onukwuli, O. D. Department of Chemical Engineering, Nnamdi Azikiwe University, Awka, Anambra State, Nigeria.
  • Igwilo C. N., Department of Science Laboratory Technology, Federal College of Agriculture, P.M.B. 7008, Ishiagu, Ebonyi State, Nigeria.
  • Nwosu-Obieogu K., Department of Chemical Engineering, Michael Okpara University of Agriculture, Umudike, Umuahia, Abia State, Nigeria
  • Oguanobi, C. N. Department of Chemical Engineering, Michael Okpara University of Agriculture, Umudike, Umuahia, Abia State, Nigeria
  • Ezekannagha, C. B Department of Chemical Engineering, Madonna University, Nigeria.
  • Udunwa D. I. Department of Polymer and Textile Engineering, Federal University of Technology Owerri, Imo State, Nigeria

Keywords:

Artificial neural networks, adaptive neuro fuzzy inference systems, gmelina seed oil, extraction, optimization

Abstract

The introduction of machine learning in prediction of yield for bioprocessing is stimulating the wide usage of the first-generation biomass (vegetable oil) especially in production of biodiesel and biolubricant. This study focused on soft computing optimization of gmelina seed oil extraction using ANN and ANFIS. The results showed that ANN is better tool for prediction of oil yield with highest coefficient of determination of 0.998 and minimum error of 0.241. The optimal GSO yield of 50.4% was obtained when these factors were adjusted to 1.5mL/mg, 45minutes, 50oC, 0.55mm, and 200rpm. This provides a crucial step towards developing a sustainable and renewable energy source, which has the potential to positively impact both the environment and local communities.

Downloads

Published

2025-03-26

Issue

Vol. 4 No. 2 (2025): UNIZIK Journal of Engineering and Applied Sciences

Section

Articles