Artificial neural network model for the kinetics of canola oil extraction for different seed samples and pretreatments

Abstract

In this work, a multi‐layer feedforward artificial neural network (ANN) was used for modeling and predicting the oil extraction yields of three canola samples with three pretreatments (unpretreatment, hydrothermal, and microwave pretreatment), considering extraction time and temperature as variables. Based on the results of the training, validation, and testing of the network, a neural network with eleven neurons in one hidden layer was selected as the best architecture for predicting the oil extraction yield response. Results obtained by the ANN model were compared with models from the literature (modified Fick's diffusion models), generally obtaining a more accurate fit with the ANN model. Practical applications Existing models of canola oil extraction kinetics have some limitations since they are not able to describe various conditions, such as variability among samples and pretreatments. Artificial neural networks (ANN) are powerful and high‐precision computational statistical modeling techniques that can address different problems. The aim of this work was to model the kinetics of canola oil extraction under different conditions (varying temperature, samples of canola, pretreatments applied) with an ANN, which presents several advantages over other reported models, allowing to describe a process that depends on many variables even when the data are incomplete or contain errors, thus facilitating its industrial application.

Ethanol extraction of canola oil: Kinetics and effects of type of solvent and microwave-pretreatment

“…Ramos et al (2017) and Sánchez et al (2017) studied the influence of microwave pretreatments on oil yield with hexane extraction and the quality of the obtained oils, observing an increase in the porosity of the extracted sample and higher yields for extraction times below 4 h. Sánchez et al (2018a) also studied the influence of microwave pretreatment on quality of extracted fraction with ethanol from canola seeds reporting an increase of canolol content by effect of microwave. In addition Sánchez et al (2017) applied a bidimensional Fick's diffusion model to describe the kinetics of canola oil extraction; and Sánchez et al (2018b) used an artificial neural network to model this process for different variety of canola seeds and pretreatments applied to these materials. However, the influence of the microwave pretreatment, kinetics and the phenomena involved in the oil extraction with ethanol has not yet been studied.…”

Artificial neural network based modeling for the prediction of yield and surface area of activated carbon from biomass

“…In this study, the tan‐sigmoidal function ( tansig as shown in Eqn (4)) was used as the activation function of hidden layer, and linear transfer function ( purelin , as shown in Eqn (5)) was selected for the output layer. This combination was selected based on its effectiveness in previous studies …”

“…Unlike a programmed model, an ANN model is a trained system that has adaptability and improved accuracy with updated data . It has been applied to predict the process parameters of biomass conversion such as oil extraction yields, kinetic parameters of pyrolysis, and selectivity of pyrolysis products . However, to the best of our knowledge, ANN has not been applied to the steam‐activation process to predict AC yield and surface area.…”

An Approach to the Application of a Modified Fick’s Diffusion Model: Development of an Algorithm

“…Table 1. Analysis of the model with 1-term series applied to the experimental data obtained by Sá nchez et al [7]…”

“…The importance of using this model for fitting experimental data lies not only in obtaining high correlation coefficients [7], but also in estimating parameters. The washing fraction (M0/M∞), related to the extraction of compounds in an early stages and, which gives a starting point to adjusted model; and diffusion coefficients (Deff), related to diffusion phenomena and velocity of convergence to asymptote of the model.…”