Performance evaluation of adaptive neuro-fuzzy inference system, artificial neural network and response surface methodology in modeling biodiesel synthesis from palm kernel oil by transesterification

Betiku, Eriola; Osunleke, Ajiboye S.; Odude, Victoria O.; Bamimore, Ayorinde; Oladipo, Babatunde; Okeleye, Adebisi A.; Ishola, Niyi B.

doi:10.1080/17597269.2018.1472980

Cited by 49 publications

(37 citation statements)

References 43 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…At a methanol to oil molar ratio 0.2758 v/v, catalyst concentration 1.045 gm of NaOH and reaction duration of 1.11 hrs, RSM predicted a yield of 97.62% Vitis vinifera biodiesel as shown in Table 4. The predicted biodiesel yield is validated experimentally which shows a yield of 97.6% with an error of 0.8% [6], [8].…”

Section: Experimental Design Materials and Methodsmentioning

confidence: 96%

“…Fig. 3 represents regression analysis fitting data for training, validation, testing and whole set corresponding to ANN approach [8].n=2k+2true(ktrue)+no.ofcentrepointsWhere k is number of factorial data's.…”

Section: Experimental Design Materials and Methodsmentioning

confidence: 99%

“…4 showcases the influence of molar ratio and catalyst concentration at constant reaction time (A), molar ratio and reaction time at constant catalyst concentration (B) and catalyst concentration and reaction time at constant molar ratio (C) respectively using ANFIS. Table 1 compares the variation in methanol to oil molar ratio, catalyst concentration and reaction time with the experimental results and the predications of RSM, ANN and ANFIS [8]. It can be seen that methanol to oil molar ratio of 0.25 v/v, 0.9 gm of NaOH catalyst concentration and 1 hr reaction time yielded a maximum experimental biodiesel of 97.4% which is in comparison with the predicted biodiesel yield of 97.184, 97.3322 and 97.18333 for RSM, ANN and ANFIS respectively as tabulated in Table 1.

Fig.…”

Section: Experimental Design Materials and Methodsmentioning

confidence: 99%

See 2 more Smart Citations

Dataset on optimized biodiesel production from seeds of Vitis vinifera using ANN, RSM and ANFIS

2019

View full text Add to dashboard Cite

This dataset disclose the investigational data on the extraction of bio-oil from seeds of Vitis vinifera through combination of mechanical pressing and soxhlet solvent extractor. Biodiesel is produced through single stage base catalysed transesterification process due to lower free fatty acid content in the Vitis vinifera bio-oil. Independent variable process parameters like molar ratio, reaction time and catalyst concentration are optimized using Artificial Neural Network, Response Surface Methodology and Adaptive Neuro-Fuzzy Interference System to predict the maximum biodiesel yield and the results are compared with the experimental data. Response Surface Methodology predicted a maximum Vitis vinifera biodiesel yield of 97.62% at methanol to oil molar ratio 0.2758 v/v, catalyst concentration 1.045 gm of NaOH and reaction duration of 1.11 hrs which is also confirmed with experimental results.

show abstract

Section: Experimental Design Materials and Methodsmentioning

confidence: 96%

Section: Experimental Design Materials and Methodsmentioning

confidence: 99%

Fig.…”

Section: Experimental Design Materials and Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Dataset on optimized biodiesel production from seeds of Vitis vinifera using ANN, RSM and ANFIS

2019

View full text Add to dashboard Cite

show abstract

“…Pyrolyzed rice husks were also applied in the transesterification of waste cooking oil, with a maximum conversion yield of 87.57% obtained with a methanol / oil ratio 20:1, catalyst concentration of 5 wt%, time of 900 min, and temperature of 110 °C reported in Etim et al 41 . Pawpaw peels calcined at 600 °C were reported to be sufficient to transesterify moringa oil to methyl ester with a conversion yield of 96.53% under the activity effect of methanol oil ratio of 9:1, catalyst loading of 3.5 wt%, temperature 35 °C and time of 40 min 95 . Attention was also drawn to some edible oil transesterification with maximum yield of 91.4% obtained by the application of calcined cocoa pod husk ash at 650 °C to transesterified soybeans oil with the effect of methanol / oil ratio of 1:6, catalyst loading of 1 wt%, time of 120 min, and temperature of 60 °C 17 .…”

Section: Potentials Of Biogenic Waste Derived Catalysts In Biodiesel mentioning

confidence: 99%

Effectiveness of biogenic waste‐derived heterogeneous catalysts and feedstock hybridization techniques in biodiesel production

Etim

Musonge

Eloka‐Eboka

2020

Biofuels Bioprod Bioref

View full text Add to dashboard Cite

Biodiesel has the potential to contribute significantly to the elimination of the present global energy and climate change logjam, but its production and commercialization have been hindered by the diverse nature of the feedstocks used for production. This paper reviews the effectiveness of applying various types of crop and animal waste-derived catalysts together with innovative feedstock hybridization as an economically viable technique for biodiesel production. Feedstock challenges, availability, and sustainability for large-scale applications are addressed with a view to bridging the existing gaps. Challenges in the use of edible oils and algae oil sources and development remain, but the technique of feedstock hybridization appears to be very promising, innovative, and cost-effective for biodiesel production. The present state of biodiesel production could be improved by the application of simple and cost-effective technologies in the feedstock system. High free fatty acid (FFA) content is the major hurdle to the use of most oils, especially low-grade/advanced oil feedstocks, in biodiesel production. This could be addressed through technological application of feedstock hybrids and biogenic waste-derived heterogenous catalysts, and their biochemical modifications. Conventional technology for the large-scale application of inorganically derived catalysts in biodiesel production with various characteristic differences is presented. Heterogenous catalysts derived from biogenic wastes and their modification could be used to overcome associated problems with the use of inorganic catalysts in biodiesel production. Biogenic waste-derived heterogenous catalysts are renewable, available, eco-friendly, and cost-effective. Technological applications of heterogeneous catalysts derived from biogenic waste are outlined and reviewed, considering various materials and different modification techniques to identify appropriate options for scaling up development. This review also discusses fundamental considerations for the Review

show abstract

“…However, published literature on ANN-ANFIS based modelling of biodiesels from non-edible oils is scarce. A hybrid of ANN and ANFIS was adopted to optimize biodiesels from sorrel oil (Ishola et al, 2019), palm kernel oil (Betiku et al, 2018), Vitis vinifera seed oil (Hariram et al, 2019), and waste cooking oil, aided with a prepared heterogeneous catalyst (Betiku and Ishola, 2020).…”

Section: Introductionmentioning

confidence: 99%

Modelling of Nicotiana Tabacum L. Oil Biodiesel Production: Comparison of ANN and ANFIS

et al. 2021

View full text Add to dashboard Cite

Among the modern computational techniques, Artificial Neural Network (ANN) and Adaptive Neuro-Fuzzy Inference System (ANFIS) are preferred because of their ability to deal with non-linear modelling and complex stochastic dataset. Nondeterministic models involve some computational complexities while solving real-life problems but would always produce better outcomes. For the first time, this study utilized the ANN and ANFIS models for modelling tobacco seed oil methyl ester (TSOME) production from underutilized tobacco seeds in the tropics. The dataset for the models was obtained from an earlier study which focused on design of the experiment on TSOME production. This study is an an exposition of the influence of transesterification parameters such as reaction duration (T), methanol/oil molar ratio (M:O), and catalyst dosage on the TSOME/biodiesel yield. A multi-layer ANN model with ten hidden layers was trained to simulate the methanolysis process. The ANFIS approach was further implemented to model TSOME production. A comparison of the formulated models was completed by statistical criteria such as coefficient of determination (R2), mean average error (MAE), and average absolute deviation (AAD). The R2 of 0.8979, MAE of 4.34468, and AAD of 6.0529 for the ANN model compared to those of the R2 of 0.9786, MAE of 1.5311, and AAD of 1.9124 for the ANFIS model. The ANFIS model appears to be more reliable than the ANN model in predicting TSOME production in the tropics.

show abstract

Performance evaluation of adaptive neuro-fuzzy inference system, artificial neural network and response surface methodology in modeling biodiesel synthesis from palm kernel oil by transesterification

Cited by 49 publications

References 43 publications

Dataset on optimized biodiesel production from seeds of Vitis vinifera using ANN, RSM and ANFIS

Dataset on optimized biodiesel production from seeds of Vitis vinifera using ANN, RSM and ANFIS

Effectiveness of biogenic waste‐derived heterogeneous catalysts and feedstock hybridization techniques in biodiesel production

Modelling of Nicotiana Tabacum L. Oil Biodiesel Production: Comparison of ANN and ANFIS

Contact Info

Product

Resources

About