Title: Optimisation of biodiesel production from Chlorella protothecoides microalgal oil using combined ANN-GA software

Authors: Mukesh Kumar; M.P. Sharma

Addresses: Department of Mechanical Engineering, IIEST Shibpur Howrah, West Bengal, India ' Biofuel Research Laboratory, Department of Hydro and Renewable Energy, IIT Roorkee, Roorkee, India

Abstract: Chlorella protothecoides microalgae are chosen for the present study because of having faster growth rate, high oil content, and high biomass productivity. Response surface methodology (RSM), as well as combined artificial neural network (ANN) with genetic algorithm (GA), are employed for the modelling of the reaction parameters and biodiesel yields. The input parameters were reaction time (40-120 min), temperature (45-65°C), methanol to oil molar ratio (6-10:1) (vol/vol), catalyst concentration (0.4-1.5 w/v), and biodiesel yield. An ANN model is developed, trained, and tested using experimental data from the combined RSM-based Box-Behnken design (BBD) technique. The optimised conditions the combined ANN-GA technique predicted were reaction time 105.6 min, reaction temperature 65°C, methanol to oil molar ratio 7.41:1 (vol. /vol.), and catalyst concentration 1.024 (w/v). Based on the results, combined ANN-GA techniques are recommended to be a quick and reliable approach for predicting reaction parameters for biodiesel production. [Received: February 23, 2022; Accepted: March 14, 2023]

Keywords: Chlorella protothecoides; microalgae oil; response surface methodology; RSM; artificial neural network; ANN; genetic algorithm; GA; transesterification.

DOI: 10.1504/IJOGCT.2023.132500

International Journal of Oil, Gas and Coal Technology, 2023 Vol.33 No.4, pp.388 - 407

Received: 22 Feb 2022
Accepted: 14 Mar 2023
Published online: 24 Jul 2023 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article