Response surface modeling to predict biodiesel yield in a multi-feedstock biodiesel production plant

Unlocking the potential of transesterification catalysts for biodiesel production through machine learning approach

The growing demand for fossil fuels has motivated the search for a renewable energy source, and biodiesel has emerged as a promising and environmentally friendly alternative. In this study, machine learning techniques were employed to predict the biodiesel yield from transesterification processes using three different catalysts: homogeneous, heterogeneous, and enzyme. Extreme gradient boosting algorithms showed the highest accuracy in predictions, with a coefficient of determination accuracy of nearly 0.98, as determined through a 10-fold cross-validation of the input data. The results indicated that linoleic acid, behenic acid, and reaction time were the most crucial factors affecting biodiesel yield predictions for homogeneous, heterogeneous, and enzyme catalysts, respectively. This research provides insights into the individual and combined effects of key factors on transesterification catalysts, contributing to a deeper understanding of the system.

Using SVM-RSM and ELM-RSM Approaches for Optimizing the Production Process of Methyl and Ethyl Esters

The production of a desired product needs an effective use of the experimental model. The present study proposes an extreme learning machine (ELM) and a support vector machine (SVM) integrated with the response surface methodology (RSM) to solve the complexity in optimization and prediction of the ethyl ester and methyl ester production process. The novel hybrid models of ELM-RSM and ELM-SVM are further used as a case study to estimate the yield of methyl and ethyl esters through a trans-esterification process from waste cooking oil (WCO) based on American Society for Testing and Materials (ASTM) standards. The results of the prediction phase were also compared with artificial neural networks (ANNs) and adaptive neuro-fuzzy inference system (ANFIS), which were recently developed by the second author of this study. Based on the results, an ELM with a correlation coefficient of 0.9815 and 0.9863 for methyl and ethyl esters, respectively, had a high estimation capability compared with that for SVM, ANNs, and ANFIS. Accordingly, the maximum production yield was obtained in the case of using ELM-RSM of 96.86% for ethyl ester at a temperature of 68.48 °C, a catalyst value of 1.15 wt. %, mixing intensity of 650.07 rpm, and an alcohol to oil molar ratio (A/O) of 5.77; for methyl ester, the production yield was 98.46% at a temperature of 67.62 °C, a catalyst value of 1.1 wt. %, mixing intensity of 709.42 rpm, and an A/O of 6.09. Therefore, ELM-RSM increased the production yield by 3.6% for ethyl ester and 3.1% for methyl ester, compared with those for the experimental data.

Microwave pretreatment and optimization of osmotic dehydration of wild blueberries using response surface methodology

This study investigated the effects of pretreatments and optimized osmotic dehydration (OD) of lowbush blueberries using response surface methodology (RSM) to produce dehydrated blueberries with high antioxidants content and shelf life. Fresh wild blueberries (WB) were initially pretreated and then subjected to osmotic dehydration. Microwave pretreated WB had shown better water loss during osmotic dehydration as compared to other pretreatment methods investigated. The highest levels of phenolics, flavonoids, and anthocyanin content of the dehydrated WB were found to be 742.61 mg/100 g, 263.12 mg/100 g, and 428.11 mg/100 g d.m respectively, at optimized temperature of 40 °C, for 5 h OD, with 65% (w/w) Brix and 1:5 ratio of sample to Brix%. These results revealed that with rigorous optimization of the critical osmotic dehydration parameters high level of antioxidants could be obtained in the dehydrated product.

Biorefining of by-product streams from sunflower-based biodiesel production plants for integrated synthesis of microbial oil and value-added co-products

This study focuses on the valorisation of crude glycerol and sunflower meal (SFM) from conventional biodiesel production plants for the separation of value-added co-products (antioxidant-rich extracts and protein isolate) and for enhancing biodiesel production through microbial oil synthesis. Microbial oil production was evaluated using three oleaginous yeast strains (Rhodosporidium toruloides, Lipomyces starkeyi and Cryptococcus curvatus) cultivated on crude glycerol and nutrient-rich hydrolysates derived from either whole SFM or SFM fractions that remained after separation of value-added co-products. Fed-batch bioreactor cultures with R. toruloides led to the production of 37.4gL(-1) of total dry weight with a microbial oil content of 51.3% (ww(-1)) when a biorefinery concept based on SFM fractionation was employed. The estimated biodiesel properties conformed with the limits set by the EN 14214 and ASTM D 6751 standards. The estimated cold filter plugging point (7.3-8.6°C) of the lipids produced by R. toruloides is closer to that of biodiesel derived from palm oil.

Ultrasound-assisted biodiesel production from Camelina sativa oil

The main drawbacks of biodiesel production are high reaction temperatures, stirring and time. These could be alleviated by aiding transesterification with alternative energy sources, i.e. ultrasound (US). In this study, biodiesel was obtained from Camelina sativa oil, aided with an ultrasonic probe (20kHz, 70% duty cycle, 50% amplitude). Design of experiments included the combination of sonication and agitation cycles, w/wo heating (50°C). To gain knowledge about the implications of the proposed methodology, conventional transesterification was optimized, resulting in higher needs on catalyst concentration and reaction time, compared to the proposed reaction. Although FAME content met EN 14103 standard, FAME yields were lower than those provided by US-assisted transesterification. Energy consumption measurements showed that ultrasound assisted transesterification required lower energy, temperature, catalyst and reaction time.

Multiple response optimization of vegetable oils fatty acid composition to improve biodiesel physical properties

The effect of fatty acids chain length (LC) and its interaction with unsaturation degree (UD) on important biodiesel quality parameters was studied. Low calorific value, kinematic viscosity, flash point, cetane number and cold filter plugging point of biodiesel blends covering a wide range of fatty acids were analyzed. Analytical results were processed with statistical regression to obtain a prediction model for each property, combining LC and UD. Due to the antagonistic effects of the chemical composition over quality properties, the Derringer desirability function was proposed to allow the most suitable fatty acid composition. This target was achieved considering an average of 1.26 double bounds and 17 carbon atoms. A set of combinations of LC and UD values that provides a biodiesel that fits the European standard EN 14214 was proposed. It was found that a reduction of FAME LC allows a lower UD while keeping biodiesel specifications under the standard limits.

Modeling the effect of mixing in biodiesel production

The transesterification reaction models available in the literature are valid only for one particular mixing condition. In this work, a modeling strategy is presented in order to predict the effect of mixing conditions in the transesterification process. The proposed methodology was applied to independent sets of experimental data available in the literature that show the dependency of the transesterification reaction on the frequency of rotation of the stirrer. The accuracy of the developed models corroborates the validity of the proposed modeling approach.