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

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.

Download Full-text

Estimation of Tree Heights in an Uneven-Aged, Mixed Forest in Northern Iran Using Artificial Intelligence and Empirical Models

Forests ◽

10.3390/f11030324 ◽

2020 ◽

Vol 11 (3) ◽

pp. 324 ◽

Cited By ~ 2

Author(s):

Mahmoud Bayat ◽

Pete Bettinger ◽

Sahar Heidari ◽

Azad Henareh Khalyani ◽

Meghdad Jourgholami ◽

...

Keyword(s):

Artificial Intelligence ◽

Mixed Forest ◽

Empirical Models ◽

Ann Model ◽

Mixed Stands ◽

Anfis Model ◽

Northern Iran ◽

Inference System ◽

Intelligence Models ◽

Artificial Intelligence Models

The diameters and heights of trees are two of the most important components in a forest inventory. In some circumstances, the heights of trees need to be estimated due to the time and cost involved in measuring them in the field. Artificial intelligence models have many advantages in modeling nonlinear height–diameter relationships of trees, which sometimes make them more useful than empirical models in estimating the heights of trees. In the present study, the heights of trees in uneven-aged and mixed stands in the high elevation forests of northern Iran were estimated using an artificial neural network (ANN) model, an adaptive neuro-fuzzy inference system (ANFIS) model, and empirical models. A systematic sampling method with a 150 × 200 m network (0.1 ha area) was employed. The diameters and heights of 516 trees were measured to support the modeling effort. Using 10 nonlinear empirical models, the ANN model, and the ANFIS model, the relationship between height as a dependent variable and diameter as an independent variable was analyzed. The results show, according to R2, relative root mean square error (RMSE), and other model evaluation criteria, that there is a greater consistency between predicted height and observed height when using artificial intelligence models (R2 = 0.78; RMSE (%) = 18.49) than when using regression analysis (R2 = 0.68; RMSE (%) = 17.69). Thus, it can be said that these models may be better than empirical models for predicting the heights of common, commercially-important trees in the study area.

Download Full-text

Adaptive neuro fuzzy inference system for profiling of the atmosphere

Atmospheric Measurement Techniques Discussions ◽

10.5194/amtd-7-2715-2014 ◽

2014 ◽

Vol 7 (3) ◽

pp. 2715-2736 ◽

Cited By ~ 3

Author(s):

K. Ramesh ◽

A. P. Kesarkar ◽

J. Bhate ◽

M. Venkat Ratnam ◽

A. Jayaraman

Keyword(s):

Fuzzy Inference System ◽

Fuzzy Inference ◽

Percentage Error ◽

Computational Techniques ◽

Temperature Profiles ◽

Atmospheric Parameters ◽

Wet Season ◽

Anfis Model ◽

Inference System ◽

Neuro Fuzzy

Abstract. Retrieval of accurate profiles of temperature and water vapor is important for the study of atmospheric convection. However, it is challenging because of the uncertainties associated with direct measurement of atmospheric parameters during convection events using radiosonde and retrieval of remote-sensed observations from satellites. Recent developments in computational techniques motivated the use of adaptive techniques in the retrieval algorithms. In this work, we have used the Adaptive Neuro Fuzzy Inference System (ANFIS) to retrieve profiles of temperature and humidity over tropical station Gadanki (13.5° N, 79.2° E), India. The observations of brightness temperatures recorded by Radiometrics Multichannel Microwave Radiometer MP3000 for the period of June–September 2011 are used to model profiles of atmospheric parameters up to 10 km. The ultimate goal of this work is to use the ANFIS forecast model to retrieve atmospheric profiles accurately during the wet season of the Indian monsoon (JJAS) season and during heavy rainfall associated with tropical convections. The comparison analysis of the ANFIS model retrieval of temperature and relative humidity (RH) profiles with GPS-radiosonde observations and profiles retrieved using the Artificial Neural Network (ANN) algorithm indicates that errors in the ANFIS model are less even in the wet season, and retrievals using ANFIS are more reliable, making this technique the standard. The Pearson product movement correlation coefficient (r) between retrieved and observed profiles is more than 99% for temperature profiles for both techniques and therefore both techniques are successful in the retrieval of temperature profiles. However, in the case of RH the retrieval using ANFIS is found to be better. The comparison of mean absolute error (MAE), root mean square error (RMSE) and symmetric mean absolute percentage error (SMAPE) of retrieved temperature and RH profiles using ANN and ANFIS also indicates that profiles retrieved using ANFIS are significantly better compared to the ANN technique. The error analysis of profiles concludes that retrieved profiles using ANFIS techniques have improved the retrievals substantially; however, retrieval of RH by both techniques (ANN and ANFIS) has limited success.

Download Full-text

Optimization of Production Parameters of Tobacco Seed Oil Methyl Ester using Multi-Response Taguchi Method and MANOVA

Journal of the chemical society of pakistan ◽

10.52568/000753/jcsp/41.03.2019 ◽

2019 ◽

Vol 41 (3) ◽

pp. 414-414

Author(s):

H lya Karaba H lya Karaba ◽

Semra Boran and Harun Resit Yazgan Semra Boran and Harun Resit Yazgan

Keyword(s):

Methyl Ester ◽

Taguchi Method ◽

Seed Oil ◽

Biodiesel Production ◽

Molar Ratio ◽

Catalyst Amount ◽

Tobacco Seed ◽

Production Parameters ◽

Tobacco Seeds ◽

Catalyst Type

There is a growing recognition that using of biodiesel in large commercial systems based on sustainability, existing resources and residues can help to natural resources. Tobacco seed oil (TSO) is also used for biodiesel production as a non-edible vegetable oil. A crude oil was obtained from tobacco seeds (TS) and then tobacco seed oil methyl ester-TSOME (biodiesel) was obtained by a transesterification process. In this study, we aimed to achieve optimal biodiesel properties based on different factors using multi response Taguchi method and multivariate analysis of variance (MANOVA). The purpose of the process was to meet a European Biodiesel Standard EN 14214. Properties of the biodiesel (responses) were determined as methyl ester quantity, kinematic viscosity, density, flash point of methyl ester and freezing point of methyl ester. The factors (production parameters) were chosen such as catalyst type, alcohol/oil molar ratio, reaction temperature and catalyst amount for experiment design. The factors that influenced the desired properties were determined using MANOVA. The factors’ level was obtained using a multi response Taguchi method. We found that catalyst type and catalyst amount have a significant effect on the responses and their levels must be level 1(KOH) and level 3 (1.5%) respectively. Thereby the methods provided to produce biodiesel meet requirements of the standard with minimum cost and in short time.

Download Full-text

Mango (Magnifera indica) seed oil grown in Dilla town as potential raw material for biodiesel production using NaOH- a homogeneous catalyst

10.31221/osf.io/xsq5y ◽

2019 ◽

Author(s):

Chem Int

Keyword(s):

Diesel Engine ◽

Physicochemical Properties ◽

Seed Oil ◽

Methyl Esters ◽

Pollution Prevention ◽

Raw Material ◽

Biodiesel Production ◽

Molar Ratio ◽

Homogeneous Catalyst ◽

Minimal Amount

Biodiesel produced by transesterification process from vegetable oils or animal fats is viewed as a promising renewable energy source. Now a day’s diminishing of petroleum reserves in the ground and increasing environmental pollution prevention and regulations have made searching for renewable oxygenated energy sources from biomasses. Biodiesel is non-toxic, renewable, biodegradable, environmentally benign, energy efficient and diesel substituent fuel used in diesel engine which contributes minimal amount of global warming gases such as CO, CO2, SO2, NOX, unburned hydrocarbons, and particulate matters. The chemical composition of the biodiesel was examined by help of GC-MS and five fatty acid methyl esters such as methyl palmitate, methyl stearate, methyl oleate, methyl linoleate and methyl linoleneate were identified. The variables that affect the amount of biodiesel such as methanol/oil molar ratio, mass weight of catalyst and temperature were studied. In addition to this the physicochemical properties of the biodiesel such as (density, kinematic viscosity, iodine value high heating value, flash point, acidic value, saponification value, carbon residue, peroxide value and ester content) were determined and its corresponding values were 87 Kg/m3, 5.63 Mm2/s, 39.56 g I/100g oil, 42.22 MJ/Kg, 132oC, 0.12 mgKOH/g, 209.72 mgKOH/g, 0.04%wt, 12.63 meq/kg, and 92.67 wt% respectively. The results of the present study showed that all physicochemical properties lie within the ASTM and EN biodiesel standards. Therefore, mango seed oil methyl ester could be used as an alternative to diesel engine.

Download Full-text

Efficient Micromixing for Continuous Biodiesel Production from Jatropha Oil

Nanoscience &Nanotechnology-Asia ◽

10.2174/2210681207666170718160304 ◽

2018 ◽

Vol 9 (1) ◽

pp. 133-139

Author(s):

Waleed S. Mohammed ◽

Ahmed H. El-Shazly ◽

Marwa F. Elkady ◽

Masahiro Ohshima

Keyword(s):

Methyl Esters ◽

Continuous Process ◽

Sol Gel ◽

Average Diameter ◽

Biodiesel Production ◽

High Mass ◽

Molar Ratio ◽

Jatropha Oil ◽

Energy Deficiency ◽

Gel Preparation

Introduction: The utilization of biodiesel as an alternative fuel is turning out to be progressively famous these days because of worldwide energy deficiency. The enthusiasm for utilizing Jatropha as a non-edible oil feedstock is quickly developing. The performance of the base catalyzed methanolysis reaction could be improved by a continuous process through a microreactor in view of the high mass transfer coefficient of this technique. Materials & Methods: Nanozirconium tungstovanadate, which was synthetized using sol-gel preparation method, was utilized in a complementary step for biodiesel production process. The prepared material has an average diameter of 0.066 &µm. Results: First, the NaOH catalyzed methanolysis of Jatropha oil was investigated in a continuous microreactor, and the efficient mixing over different mixers and its impact on the biodiesel yield were studied under varied conditions. Second, the effect of adding the nanocatalyst as a second stage was investigated. Conclusion: The maximum percentage of produced methyl esters from Jatropha oil was 98.1% using a methanol/Jatropha oil molar ratio of 11 within 94 s using 1% NaOH at 60 &°C. The same maximum conversion ratio was recorded with the nanocatalyst via only 0.3% NaOH.

Download Full-text

Modeling and Optimization of Microwave-Based Bio-Jet Fuel from Coconut Oil: Investigation of Response Surface Methodology (RSM) and Artificial Neural Network Methodology (ANN)

Energies ◽

10.3390/en14020295 ◽

2021 ◽

Vol 14 (2) ◽

pp. 295

Author(s):

Mei Yin Ong ◽

Saifuddin Nomanbhay ◽

Fitranto Kusumo ◽

Raja Mohamad Hafriz Raja Shahruzzaman ◽

Abd Halim Shamsuddin

Keyword(s):

Statistical Tests ◽

Coconut Oil ◽

Jet Fuel ◽

Molar Ratio ◽

Ann Model ◽

Fuel Production ◽

Turbine Engine ◽

Renewable Fuel ◽

American Society ◽

Better Than

In this study, coconut oils have been transesterified with ethanol using microwave technology. The product obtained (biodiesel and FAEE) was then fractional distillated under vacuum to collect bio-kerosene or bio-jet fuel, which is a renewable fuel to operate a gas turbine engine. This process was modeled using RSM and ANN for optimization purposes. The developed models were proved to be reliable and accurate through different statistical tests and the results showed that ANN modeling was better than RSM. Based on the study, the optimum bio-jet fuel production yield of 74.45 wt% could be achieved with an ethanol–oil molar ratio of 9.25:1 under microwave irradiation with a power of 163.69 W for 12.66 min. This predicted value was obtained from the ANN model that has been optimized with ACO. Besides that, the sensitivity analysis indicated that microwave power offers a dominant impact on the results, followed by the reaction time and lastly ethanol–oil molar ratio. The properties of the bio-jet fuel obtained in this work was also measured and compared with American Society for Testing and Materials (ASTM) D1655 standard.

Download Full-text

Continuous Integrated Process of Biodiesel Production and Purification—The End of the Conventional Two-Stage Batch Process?

Energies ◽

10.3390/en14020403 ◽

2021 ◽

Vol 14 (2) ◽

pp. 403

Author(s):

Matea Bačić ◽

Anabela Ljubić ◽

Martin Gojun ◽

Anita Šalić ◽

Ana Jurinjak Tušek ◽

...

Keyword(s):

Extraction Efficiency ◽

Deep Eutectic Solvent ◽

International Standards ◽

Biodiesel Production ◽

Molar Ratio ◽

Process Conditions ◽

Integrated Process ◽

Free Glycerol ◽

Mass Ratio ◽

Glycerol Content

In this research, optimization of the integrated biodiesel production process composed of transesterification of edible sunflower oil, catalyzed by commercial lipase, with simultaneous extraction of glycerol from the reaction mixture was performed. Deep eutectic solvents (DESs) were used in this integrated process as the reaction and extraction media. For two systems, choline chloride:glycerol (ChCl:Gly) and choline chloride:ethylene glycol (ChCl:EG), respectively, the optimal water content, mass ratio of the phase containing the mixture of reactants (oil and methanol) with an enzyme and a DES phase (mass ratio of phases), and the molar ratio of deep eutectic solvent constituents were determined using response surface methodology (RSM). Experiments performed with ChCl:Gly resulted in a higher biodiesel yield and higher glycerol extraction efficiency, namely, a mass ratio of phases of 1:1, a mass fraction of water of 6.6%, and a molar ratio of the ChCl:Gly of 1:3.5 were determined to be the optimal process conditions. When the reaction was performed in a batch reactor under the optimal conditions, the process resulted in a 43.54 ± 0.2% yield and 99.54 ± 0.19% glycerol extraction efficiency (t = 2 h). Unfortunately, the free glycerol content was higher than the one defined by international standards (wG > 0.02%); therefore, the process was performed in a microsystem to enhance the mass transfer. Gaining the same yield and free glycerol content below the standards (wG = 0.0019 ± 0.003%), the microsystem proved to be a good direction for future process optimization.

Download Full-text

Calcium Methoxide Synthesis from Quick Lime Using as Solid Catalyst in Refined Palm Oil Biodiesel Production

Advanced Materials Research ◽

10.4028/www.scientific.net/amr.834-836.550 ◽

2013 ◽

Vol 834-836 ◽

pp. 550-554 ◽

Cited By ~ 1

Author(s):

Warakom Suwanthai ◽

Vittaya Punsuvon ◽

Pilanee Vaithanomsat

Keyword(s):

Palm Oil ◽

Acid Methyl Ester ◽

Biodiesel Production ◽

Molar Ratio ◽

Catalyst Loading ◽

Solid Catalyst ◽

Solid Base ◽

Quick Lime ◽

X Ray ◽

Refined Palm Oil

In this research, calcium methoxide was synthesized as solid base catalyst from quick lime for biodiesel production. The catalyst was further characterized by scanning electron microscopy (SEM), X-ray diffraction (XRD), attenuated total reflection fourier transform (ATR-FTIR) and Energy-dispersive X-ray spectroscopies (EDX) to evaluate its performance. The transesterification of refined palm oil using calcium methoxide and the process parameters affecting the fatty acid methyl ester (FAME) content such as catalyst concentration, methanol:oil molar ratio and reaction time were investigated. The results showed that the FAME content at 97% was achieved within 3 h using 3 %wt catalyst loading, 12:1 methanol:oil molar ratio and 65 °C reaction temperature. The result of FAME suggested calcium methoxide was the promising solid catalyst for substitution of the conventional liquid catalyst.

Download Full-text

Predicting Sooting Propensity of Oxygenated Fuels Using Artificial Neural Networks

Processes ◽

10.3390/pr9061070 ◽

2021 ◽

Vol 9 (6) ◽

pp. 1070

Author(s):

Abdul Gani Abdul Jameel

Keyword(s):

Neural Networks ◽

Artificial Neural Networks ◽

Functional Groups ◽

Average Error ◽

Ann Model ◽

Oh Groups ◽

Unseen Data ◽

Learning Capabilities ◽

Artificial Neural ◽

Oxygenated Fuels

The self-learning capabilities of artificial neural networks (ANNs) from large datasets have led to their deployment in the prediction of various physical and chemical phenomena. In the present work, an ANN model was developed to predict the yield sooting index (YSI) of oxygenated fuels using the functional group approach. A total of 265 pure compounds comprising six chemical classes, namely paraffins (n and iso), olefins, naphthenes, aromatics, alcohols, and ethers, were dis-assembled into eight constituent functional groups, namely paraffinic CH3 groups, paraffinic CH2 groups, paraffinic CH groups, olefinic –CH=CH2 groups, naphthenic CH-CH2 groups, aromatic C-CH groups, alcoholic OH groups, and ether O groups. These functional groups, in addition to molecular weight and branching index, were used as inputs to develop the ANN model. A neural network with two hidden layers was used to train the model using the Levenberg–Marquardt (ML) training algorithm. The developed model was tested with 15% of the random unseen data points. A regression coefficient (R2) of 0.99 was obtained when the experimental values were compared with the predicted YSI values from the test set. An average error of 3.4% was obtained, which is less than the experimental uncertainty associated with most reported YSI measurements. The developed model can be used for YSI prediction of hydrocarbon fuels containing alcohol and ether-based oxygenates as additives with a high degree of accuracy.

Download Full-text

Use of Nondestructive Testing of Ultrasound and Artificial Neural Networks to Estimate Compressive Strength of Concrete

Buildings ◽

10.3390/buildings11020044 ◽

2021 ◽

Vol 11 (2) ◽

pp. 44

Author(s):

Fernando A. N. Silva ◽

João M. P. Q. Delgado ◽

Rosely S. Cavalcanti ◽

António C. Azevedo ◽

Ana S. Guimarães ◽

...

Keyword(s):

Neural Networks ◽

Compressive Strength ◽

Artificial Neural Networks ◽

Cross Sections ◽

Influential Factors ◽

Average Error ◽

Ann Model ◽

Cement Ratio ◽

Water Cement Ratio ◽

Artificial Neural

The work presents the results of an experimental campaign carried out on concrete elements in order to investigate the potential of using artificial neural networks (ANNs) to estimate the compressive strength based on relevant parameters, such as the water–cement ratio, aggregate–cement ratio, age of testing, and percentage cement/metakaolin ratios (5% and 10%). We prepared 162 cylindrical concrete specimens with dimensions of 10 cm in diameter and 20 cm in height and 27 prismatic specimens with cross sections measuring 25 and 50 cm in length, with 9 different concrete mixture proportions. A longitudinal transducer with a frequency of 54 kHz was used to measure the ultrasonic velocities. An ANN model was developed, different ANN configurations were tested and compared to identify the best ANN model. Using this model, it was possible to assess the contribution of each input variable to the compressive strength of the tested concretes. The results indicate an excellent performance of the ANN model developed to predict compressive strength from the input parameters studied, with an average error less than 5%. Together, the water–cement ratio and the percentage of metakaolin were shown to be the most influential factors for the compressive strength value predicted by the developed ANN model.

Download Full-text