Response surface methodology for carbon dioxide reforming of natural gas

The performance of 0.5% wt Rh/γ-AL₂O₃ catalyst for the dry reforming of natural gas using carbon dioxide has been studied. The response surface methodology (RSM) is used to study the effect of two different operating parameters, namely the hourly space velocity at the levels 18,000, 36,000, 45,000, and 60,000 ccg^?1 h^?1 and the reaction temperature at the levels 600, 700, and 800°C, on the conversion of the different components comprising commercial natural gas. The RSM is used to illustrate such effect in the three dimensions and shows the location of the optimum for the conversion or production of each component.     

Optimization of hydrogen production via toluene steam reforming over Ni–Co supported modified-activated carbon using ANN coupled GA and RSM

Hydrogen (H₂) is a clean fuel that can be produced from various resources including biomass. Optimization of H₂ production from catalytic steam reforming of toluene using response surface methodology (RSM) and artificial neural network coupled genetic algorithm (ANN-GA) models has been investigated. In RSM model, the central composite design (CCD) is employed in the experimental design. The CCD conditions are temperature (500–900 °C), feed flow rate (0.006–0.034 ml/min), catalyst weight (0.1–0.5 g) and steam-to-carbon molar ratio (1–9). ANN model employs a three-layered feed-forward backpropagation neural network in conjugation with the tangent sigmoid (tansig) and linear (purelin) as the transfer functions and Levenberg-Marquardt training algorithm. Best network structure of 4-14-1 is developed and utilized in the GA optimization for determining the optimum conditions. An optimum H₂ yield of 92.6% and 81.4% with 1.19% and 6.02% prediction error are obtained from ANN-GA and RSM models, respectively. The predictive capabilities of the two models are evaluated by statistical parameters, including the coefficient of determination (R²) and root mean square error (RMSE). Higher R² and lower RSME values are reported for ANN-GA model (R² = 0.95, RMSE = 4.09) demonstrating the superiority of ANN-GA in determining the nonlinear behavior compared to RSM model (R² = 0.87, RMSE = 6.92). These results infer that ANN-GA is a more reliable and robust predictive steam reforming modelling tool for H₂ production optimization compared to RSM model.     

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

This 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, H₂SO₄ 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 (R²) 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.     

Gas permeation through H2-selective mixed matrix membranes: Experimental and neural network modeling

Gas permeability through synthesized polydimethylsiloxane (PDMS)/zeolite 4A mixed matrix membranes (MMMs) were investigated with the aid of artificial neural network (ANN) approach. Kinetic diameter and critical temperature of permeating components (e.g. H₂, CH₄, CO₂ and C₃H₈), zeolite content and upstream pressure as input variables and gas permeability as output were inspected. Collected data of the experimental operation was used to ANN training and optimum numbers of hidden layers and neurons were obtained by trial-error method. The selected ANN architecture (4:10:1) was used to predict gas permeability for different inputs in the domain of training data. Based on the results, the predicted values demonstrate an excellent agreement with the experimental data, with high correlation (R² = 0.9944) and less error (RMSE = 1.33E−4). Furthermore, using sensitivity analysis, kinetic diameter and critical temperature were found as the most significant effective variables on gas permeability. As a result, ANN can be recommended for the modeling of gas transport through MMMs.     

Investigation of optimum H2 production from date palm waste leaves using different modeling tools

Globally, the productive utilization of biomass has paid serious attention to fulfilling the energy requirements laid out by the international standards, as to reduce related carbon footprints. Therefore, this study investigates date palm waste leaves which aims to produce environment friendly H₂ gas using gasification technology. The results of 25 experimental runs exhibited that the higher H₂ produced at higher temperature which was mainly supported by water-gas-shift and steam-methane reforming reactions. H₂ prediction was modeled using response surface methodology (RSM) and artificial neural network (ANN). The RSM model exhibited a strong interaction with the regression coefficient (R²) and p-value of 0.89 and 0.000000, respectively. ANN data was disseminated thru K-fold contrivance with back-propagation algorithm. Hence, the training (80% data) and validation (20% data) datasets were found with R² and root mean squared error (RSME) of 0.90 and 0.28, and 0.86 and 0.39, respectively. Kinetics of the process estimated the activation energies (Ea) using Ozawa-Flynn-Wall (OFW), Starink (STK), and Kissinger-Akahira-Sunose (KAS) models. Hence, the values of Ea and R² at conversion degrees (α) 0.1 to 0.8 were ranged between 129.40 and 326.64 kJ/mol and 0.92 to 0.97, respectively. Optimum H₂ production of 49.03 vol% (with LHV of 11.10 MJ/Nm³) was produced. This finding is thought to be a better source of energy which can be an appropriate fuel for Fischer Tropsch process for manufacturing of transportation fuels.     

Comparison of Response Surface Methodology (RSM) and Artificial Neural Network (ANN) in modelling of waste coconut oil ethyl esters production

The attributes of renewability and environmental friendliness have made ethanol a preferable alternative to methanol in the production of biodiesel from lipid feedstocks. For the first time, this study adopted Response Surface Methodology (RSM) and Artificial Neural Network (ANN) to model coconut oil ethyl ester (CNOEE) yield. Transesterification parameters such as reaction temperature and ethanol/coconut oil molar ratio and catalyst dosage were varied. Maximum CNOEE yield of 96.70% was attained at 73 °C reaction temperature, 11.9:1 molar ratio, and catalyst dosage of 1.25 wt. %. The experimental yield was in agreement with the predicted yield. Central Composite Design was adopted to develop the RSM while feed-forward back propagation neural network algorithm was employed for the ANN model. Statistical indices were employed to compare the models. The computed coefficient of determination (R²) of 0.9564, root-mean-squarce-error (RMSE) of 0.72739, standard error of prediction (SEP) of 0.008021, mean average error (MAE) of 0.612, and average absolute deviation (AAD) of 0.674901 for RSM model compared to those of R² (0.9980), RMSE (0.68615), SEP (0.007567), MAE (0.325), and AAD (0.3877) for ANN indicated the superiority of the ANN model over the RSM model. The key fuel properties of the CNOEE met with those of biodiesel international standards.     

Prediction of natural gas hydrate inhibitor vaporization rate using particle swarm optimization approach

Natural gas is a very important source of energy. In natural gas processing, accurate prediction of methanol loss to the vapor phase during natural gas hydrate inhibition is necessary to compute the total methanol injection rate required to effectively prevent the formation of natural gas hydrate. A reliable prediction tool that has the capability to accurately predict methanol losses to the vapor phase is thus needed. In order to address this matter, the current research was aimed at assessing the ability and feasibility of a robust computational intelligence paradigm. Based on a total of 326 dataset collected from the reliable literature, methanol loss to the vapor phase was predicted using artificial neural network (ANN) linked with particle swarm optimization (PSO) which is employed to determine the optimal values of the ANN weights. Success of the introduced hybrid intelligence model (or PSO-ANN) was confirmed with overall mean squared error (MSE), mean absolute error (MAE), and coefficient of determination (R²) values of 0.16421, 0.33210, and 0.99696, respectively.     

Performance comparison of the mass transfer models with internal reforming for solid oxide fuel cell anodes

In this work, models describing multicomponent gas diffusion process in an electrode of a porous solid oxide fuel cell (SOFC) anode coupled with internal reforming reactions were developed. The performances of three different types of models, the dusty-gas model (DGM), the binary-friction model (BFM) and the cylindrical pore interpolation model (CPIM), were compared in 1D. All these models take into account Knudsen diffusion and molecule–molecule diffusion can be used in transition region which is generally the case in a SOFC electrode. The developed models are able to predict the fuel components’ molar fraction distributions in the anode electrode, and the concentration overpotential. They are capable of simulating the internal reforming process for hydrocarbon fuel, such as natural gas, with kinetic models considering both methane-steam reforming (MSR), and water–gas shift reaction (WSR). The effects of pressure gradient, pore size, current density, are studied. It was found that three models give similar results in difference cases using the same “tuned” tortuosity factor (τ²). The difference caused using the isobaric assumption is negligible for the H₂–H₂O–Ar and CO–CO₂ system, expect at small pore sizes (under 1 μm) and high current density (above 1 A/cm²). For a system fed with hydrocarbon fuel, the isobaric assumption will change the molar fraction distribution by up to 10% for different gas mixture components for the CPIM and the BFM, and up to 25% for the DGM at small pore sizes. However, the reaction rates for both MSR and WSR remain the same when the pressure variation is neglected.     

Response surface optimization of syngas production from greenhouse gases via DRM over high performance Ni–W catalyst

The process parameters for dry reforming of methane (DRM) over Ni–W/Al₂O₃–MgO catalyst are optimized using response surface methodology (RSM). The Ni–W bimetallic catalyst is synthesized by co-precipitation method followed by impregnation. The catalysts are characterized by BET, XRD, FESEM, EDX and TEM; to study physicochemical properties, morphology, composition, crystallite size and deposited carbon. The effect of process parameters, i.e., reaction temperature (600^oC–800 °C) and feed gas ratio (0.5–1.5) on the CH₄, CO₂ conversions and syngas ratio are studied. A temperature of 777.29 °C with CH₄: CO₂ of 1.11 at GHSV of 36,000 cm³gm.cat^?1h^?1, delivered the CH₄ and CO₂ conversions of 87.6% and 93.3%, respectively along with H₂:CO of 1. The predicted process parameters were verified through actual experimental analysis at the optimized conditions, and results agreed with CCD of the RSM model with insignificant error. The MWCNT formed during DRM avoided catalyst deactivation and delivered stable performance over 12 h of reaction test at the optimized conditions.     

Optimization of hydrogen production from steam reforming of biomass tar over Ni/dolomite/La2O3 catalysts

Industrially, the endothermic process of steam reforming is carried out at the lowest temperature, steam to carbon (S/C) ratio, and gas hourly space velocity (GHSV) for maximum hydrogen (H₂) production. In this study, a three-level three factorial Box-Behnken Design (BBD) of Response Surface Methodology (RSM) was applied to investigate the optimization of H₂ production from steam reforming of gasified biomass tar over Ni/dolomite/La₂O₃ (NiDLa) catalysts. Consequently, reduced quadratic regression models were developed to fit the experimental data adequately. The effects of the independent variables (temperature, S/C ratio, and GHSV) on the responses (carbon conversion to gas and H₂ yield) were examined. The results indicated that reaction temperature was the most significant factor affecting both responses. Ultimately, the optimum conditions predicted by RSM were 775 °C, S/C molar ratio of 1.02, and GHSV of 14,648 h⁻¹, resulting in 99 mol% of carbon conversion to gas and 82 mol% of H₂ yield.     

Fabrication & performance study of a palladium on alumina supported membrane reactor: Natural gas steam reforming,a case study

In this work, a synthetic mixture of natural gas is considered in a steam reforming process for generating hydrogen by using a membrane reactor housing a composite membrane constituted of a Pd-layer (13 μm) supported on alumina. The Pd/Al₂O₃ membrane separates part of the produced hydrogen through its selective permeation, although it shows a relatively low H₂/N₂ ideal selectivity (>200 at 0.5 bar of trans-membrane pressure and T = 425 °C).The steam reforming reaction is performed at 420 °C, by varying the gas hourly space velocity between 4400 h^?1 and 6900 h^?1 and by using two different mixtures containing some common impurities found within natural gas pipeline. Specifically, the effect of N₂ and CO₂ as impurities in the feed line is analyzed. The reaction pressure and steam-to-carbon ratio (S/C) are kept constant at 3.0 bar (abs.) and 3.5/1, respectively.The best performance of the Pd-based membrane reactor is obtained at 420 °C, 3.0 bar and 100 mL/min of sweep-gas, yielding a methane conversion of 55% and hydrogen recovery >90%.     

Modeling and parametric optimization of air catalytic co-gasification of wood-oil palm fronds blend for clean syngas (H2+CO) production

Syngas production from biomass gasification is a potentially sustainable and alternative means of conventional fuels. The current challenges for biomass gasification process are biomass storage and tar contamination in syngas. Co-gasification of two biomass and use of mineral catalysts as tar reformer in downdraft gasifier is addressed the issues. The optimized and parametric study of key parameters such as temperature, biomass blending ratio, and catalyst loading were made using Response Surface Methodology (RSM) and Artificial Neural Network (ANN) on tar reduction and syngas. The maximum H₂ was produced when Portland cement used as catalyst at optimum conditions, temperature of 900 °C, catalyst-loading of 30%, and biomass blending-ratio of W52:OPF48. Higher CO was yielded from dolomite catalyst and lowest tar content obtained from limestone catalyst. Both RSM and ANN are satisfactory to validate and predict the response for each type of catalytic co-gasification of two biomass for clean syngas production.     

Optimization of catalyst preparation conditions for hydrogen generation in the presence of Co–B using taguchi method

Efficient hydrogen generation is a significant prerequisite of future hydrogen economy. Therefore, the development of efficient non-noble metal catalysts for hydrolysis reaction of sodium borohydride (NaBH₄) under mild conditions has received extensive interest. Since the transition metal boride based materials are inexpensive and easy to prepare, it is feasible to use these catalysts in the construction of practical hydrogen generators. In this work, temperature, pH, reducing agent concentration, and reduction rate were selected as independent process parameters and their effects on dependent parameter, such as hydrogen generation rate, were investigated using response surface methodology (RSM). According to the obtained results of the RSM prediction, maximum hydrogen generation rate (53.69 L. min^?1g_cat^-1) was obtained at temperature of 281.18 K, pH of 5.97, reducing agent concentration of 31.47 NaBH₄/water and reduction rate of 7.16 ml min^?1. Consequently, after validation studies it was observed that the RSM together with Taguchi methods are efficient experimental designs for parameter optimization.     

Optimization of renewable hydrogen-rich syngas production from catalytic reforming of greenhouse gases (CH4 and CO2) over calcium iron oxide supported nickel catalyst

Multi-response optimization of hydrogen-rich syngas from catalytic reforming of greenhouses (methane and carbon dioxide over Calcium iron oxide supported Nickel (15 wt%Ni/CaFe₂O₄) catalyst was performed by varying reaction temperature (700–800 °C), feed ratio (0.4–1.0) and gas hourly space velocity (10,000–60,000 h^?1)) using response surface methodology. Four response surface methodology (RSM) models were obtained for the prediction of reactant conversion and the product yield. The analysis of variance (ANOVA) conducted on the model showed that the parameters have significant effect on the responses. Optimum conditions for the methane dry reforming over the 15 wt%Ni/CaFe₂O₄ catalyst were obtained at reaction temperature, feed ratio and gas hourly space velocity (GHSV) of 832.45 °C, 0.96 and 35,000 mL g^?1 h^?1 respectively with overall desirability value of 0.999 resulting in the highest methane (CH₄) and carbon dioxide (CO₂) conversions of 85.00%, 88.00% and hydrogen (H₂) and carbon monoxide (CO) yields of 77.82% and 75.76%, respectively.     

Simulation model of ANN based maximum power point tracking controller for solar PV system

In this paper the simulation model of an artificial neural network (ANN) based maximum power point tracking controller has been developed. The controller consists of an ANN tracker and the optimal control unit. The ANN tracker estimates the voltages and currents corresponding to a maximum power delivered by solar PV (photovoltaic) array for variable cell temperature and solar radiation. The cell temperature is considered as a function of ambient air temperature, wind speed and solar radiation. The tracker is trained employing a set of 124 patterns using the back propagation algorithm. The mean square error of tracker output and target values is set to be of the order of 10⁻⁵ and the successful convergent of learning process takes 1281 epochs. The accuracy of the ANN tracker has been validated by employing different test data sets. The control unit uses the estimates of the ANN tracker to adjust the duty cycle of the chopper to optimum value needed for maximum power transfer to the specified load.     

Numerical Simulation of Low NO x Combustion Technology in a 100 MWe Bituminous Coal-Fired Wall Boiler

Computational fluid dynamics (CFD) has been applied to evaluate two NO _x reducing schemes in a 100 MW_e per hour (p/h) boiler that uses double volute burners without over-fire-air (OFA). The new schemes involve: a) changing the double volute burners for centrally fuel rich (CFR) burners, and b) using the OFA system in conjunction with a). In analyzing the results of these two schemes, various conclusions were drawn: 1) gas temperatures and related rise rates in the central zone of burners were higher, O₂ and NO _x concentrations were lower; and 2) cross-sectional gas temperature distributions through the burner centers in scheme employing b) is higher than that of original furnace set-up, and lower than that of scheme employing a). Comparing the b) scheme with those of the a) scheme and the original set-up, which is 277 mg/m³ (at 6% O₂) at the furnace outlet, the peak value of NO _x concentration has decreased 571 mg/m³ (67.4%) and 436 mg/m³ (61.2%), respectively.     

An experimental study on the comparative analysis of the effect of the number of data on the error rates of artificial neural networks

In this study, the effect of the amount of data used in the design of artificial neural networks (ANNs) on the predictive accuracy of ANNs was investigated. Five different ANNs were designed using the experimentally measured specific heat data of the Al₂O₃/water nanofluid prepared at volumetric concentrations of 0.0125, 0.025, 0.05, 0.1 and 0.2 using the Al₂O₃ nanoparticle. The developed ANN is a multi‐layer perceptron, feedforward and backpropagation model. In each ANN with 15 neurons in the hidden layer, the volumetric concentration (φ) and temperature (T) values were nominated as input layer factors and the specific heat value was estimated as the output value. With the aim of survey the effect of the amount of data on the predicted results of the ANN, a different amount of datasets were used in each developed ANN. In this context, in total 260 data were used in the Model 1 ANN. Subsequently, the total amount of data was reduced by 20% in each developed neural network and 55 data were used in the ANN named Model#5. The results obtained show that ANNs are highly talented of predicting the specific heat values of Al₂O₃/water nanofluid. However, in the comparisons, it was evaluated that the amount of data used had a share on the prediction performance of the ANN and that the decrease in the amount of data with the prediction performance of the ANN decreased.     

Utilizing waste heat of the flue gas for post-combustion CO2 capture—A comparative study for different process layouts

The inlet flue gas entering the absorber column must be ~40°C and hence needs cooling. In this article, it is proposed that waste heat be recovered from the flue gas using a condensing heat exchanger. This recovered heat is utilized as partial supplement to subsequent heating in stripper during CO₂ capture. System layouts—one for base case and two others—have been conceptualized. ASPEN Plus^® simulation results for the other two layouts are discussed for energy savings with respect to the base case. Results show that, for the other two layouts, reboiler heat duty decreases though carbon capture efficiency also decreases.     

Artificial neural network models for biomass gasification in fluidized bed gasifiers

Artificial neural networks (ANNs) have been applied for modeling biomass gasification process in fluidized bed reactors. Two architectures of ANNs models are presented; one for circulating fluidized bed gasifiers (CFB) and the other for bubbling fluidized bed gasifiers (BFB). Both models determine the producer gas composition (CO, CO₂, H₂, CH₄) and gas yield. Published experimental data from other authors has been used to train the ANNs. The obtained results show that the percentage composition of the main four gas species in producer gas (CO, CO₂, H₂, CH₄) and producer gas yield for a biomass fluidized bed gasifier can be successfully predicted by applying neural networks. ANNs models use in the input layer the biomass composition and few operating parameters, two neurons in the hidden layer and the backpropagation algorithm. The results obtained by these ANNs show high agreement with published experimental data used R² > 0.98. Furthermore a sensitivity analysis has been applied in each ANN model showing that all studied input variables are important.     

Modeling solubility of sulfur in pure hydrogen sulfide and sour gas mixtures using rigorous machine learning methods

Accurate determination of sulfur solubility in pure hydrogen sulfide (H₂S) and sour gas mixtures has a leading role and a fundamental importance in handling and addressing sulfur deposition issues. In this study, rigorous paradigms based on two artificial neural network (ANN) types, namely multilayer perceptron (MLP) and cascaded forward neural network (CFNN), optimized by Levenberg–Marquardt (LM) algorithm were proposed as machine learning (ML) modeling tools to predict the solubility of sulfur in sour gas mixtures and pure H₂S. Besides, explicit and simple-to-use correlations were established using gene expression programming (GEP). The paradigms derived from the methods aforementioned were developed using widespread experimental database. The obtained results indicated that the outcomes gained from the proposed MLP, CFNN and GEP-based correlations are in a high coherence and agreement with the experimental data. In addition, it was found that among the all suggested schemes, CFNN models are the most accurate paradigms for estimating the solubility of sulfur in sour gas mixtures and pure H₂S with root mean square error (RMSE) of 0.0232 and 3.8101, respectively. Furthermore, a comparison between the performance of CFNN and the prior alternatives demonstrated that the CFNN models predict the solubility of sulfur in sour gas mixtures and pure H₂S more accurately. Moreover, based on the trend analysis, it was concluded that the predictions of CFNN follow the real tendency of sulfur solubility in pure H₂S and sour gas mixtures with respect to the input parameters. Besides, the sensitivity analysis dictated that pressure and temperature have the most significant impact on sulfur solubility calculation in pure H₂S and sour gas mixtures. The results reported in this investigation revealed that implication of the considered soft computing approaches in the estimation of sulfur solubility in sour gas mixtures and pure H₂S can lead to the generation of more reliable predictive paradigms which can be integrated in other related applications. Lastly, the findings of this study can help for effective prediction of the solubility of sulfur in sour gas mixtures and pure H₂S while simulating different natural gas processes.