Performance evaluation of artificial neural network coupled with generic algorithm and response surface methodology in modeling and optimization of biodiesel production process parameters from shea tree (Vitellaria paradoxa) nut butter

Abstract

a b s t r a c tThis work investigated the potential of shea butter oil (SBO) as feedstock for synthesis of biodiesel. Due to high free fatty acid (FFA) of SBO used, response surface methodology (RSM) was employed to model and optimize the pretreatment step while its conversion to biodiesel was modeled and optimized using RSM and artificial neural network (ANN). The acid value of the SBO was reduced to 1.19 mg KOH/g with oil/ methanol molar ratio of 3.3, H 2 SO 4 of 0.15 v/v, time of 60 min and temperature of 45 C. Optimum values predicted for the transesterification reaction by RSM were temperature of 90 C, KOH of 0.6 w/v, oil/ methanol molar ratio of 3.5, and time of 30 min with actual shea butter oil biodiesel (SBOB) yield of 99.65% (w/w). ANN combined with generic algorithm gave the optimal condition as temperature of 82 C, KOH of 0.40 w/v, oil/methanol molar ratio of 2.62 and time of 30 min with actual SBOB yield of 99.94% (w/w). Coefficient of determination (R 2 ) and absolute average deviation (AAD) of the models were 0.9923, 0.83% (RSM) and 0.9991, 0.15% (ANN), which demonstrated that ANN model was more efficient than RSM model. Properties of SBOB produced were within biodiesel standard specifications.

Potential of Ripe Plantain Fruit Peels as an Ecofriendly Catalyst for Biodiesel Synthesis: Optimization by Artificial Neural Network Integrated with Genetic Algorithm

“…The sigmoid transfer function (Equation (1)) and pure-linear transfer function (Equation (2)) were selected for the hidden and output layers, respectively. Each neural network was trained using a default stopping criteria of 100,000 iterations [8,22]. Other parameters were chosen as the default values of the software.…”

“…Other parameters were chosen as the default values of the software. The number of hidden neurons was determined by testing several neural networks iteratively until the root mean square error (RMSE) value of the output was minimized [8,22]. The experimental data set was divided into two subsets: training set and testing set [21].…”

“…The developed model was coupled with GA and used to predict the optimal condition of the input variables for maximum AIOME yield. The predicted optimum values were validated by carrying out triplicate experiments using these values, and the average observed values obtained were compared with the predicted responses [22].…”

“…The physical, chemical and fuel properties of the AIOME produced were determined as previously described by Betiku et al [22]. The fuel properties such as flash point, pour point, and cloud point were determined via ASTM D 93, ASTM D 97, and ASTM D 2500, respectively.…”

“…While Sarve et al [21] employed ANN in the ultrasound-assisted transesterification using barium hydroxide as a heterogeneous catalyst, sesame oil and methanol. In order to maximize or minimize the response of an objective function, models generated using ANN are usually coupled with an optimization tool such as genetic algorithm, GA [20,22], particle swarm Sustainability 2018, 10, 707 3 of 15 optimization, PSO [23], rotation inherit optimization, RIO [24], to achieve this by optimizing the operating input variables involved.…”