Modeling of sugarcane bagasse conversion to levulinic acid using response surface methodology (RSM), artificial neural networks (ANN), and fuzzy inference system (FIS): A comparative evaluation

Ogedjo, Marcelina; Kapoor, Ashish; Kumar, P. Senthil; Rangasamy, Gayathri; Ponnuchamy, Muthamilselvi; Rajagopal, Manjula; Banerjee, Protibha Nath

doi:10.1016/j.fuel.2022.125409

Cited by 18 publications

(5 citation statements)

References 52 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Their overall comparison is summarized in Table . Low magnitude in error values indicates better predictive capacity . MSE, which is a measure of how close a fitted line is to a data point, was determined for the three models.…”

Section: Resultsmentioning

confidence: 99%

See 1 more Smart Citation

Performance Evaluation of Benzyl Alcohol Oxidation with tert-Butyl Hydroperoxide to Benzaldehyde Using the Response Surface Methodology, Artificial Neural Network, and Adaptive Neuro-Fuzzy Inference System Model

Emeji,

Kumi,

Meijboom

2024

ACS Omega

View full text Add to dashboard Cite

The adaptive neuro-fuzzy inference system (ANFIS), central composite experimental design (CCD)-response surface methodology (RSM), and artificial neural network (ANN) are used to model the oxidation of benzyl alcohol using the tert-butyl hydroperoxide (TBHP) oxidant to selectively yield benzaldehyde over a mesoporous ceria-zirconia catalyst. Characterization reveals that the produced catalyst has hysteresis loops, a sponge-like structure, and structurally induced reactivity. Three independent variables were taken into consideration while analyzing the ANN, RSM, and ANFIS models: the amount of catalyst (A), reaction temperature (B), and reaction time (C). With the application of optimum conditions, along with a constant (45 mmol) TBHP oxidant amount, (30 mmol) benzyl alcohol amount, and rigorous refluxing of 450 rpm, a maximum optimal benzaldehyde yield of 98.4% was obtained. To examine the acceptability of the models, further sensitivity studies including statistical error functions, analysis of variance (ANOVA) results, and the lack-of-fit test, among others, were employed. The obtained results show that the ANFIS model is the most suited to predicting benzaldehyde yield, followed by RSM. Green chemistry matrix calculations for the reaction reveal lower values of the E-factor (1.57), mass intensity (MI, 2.57), and mass productivity (MP, 38%), which are highly desirable for green and sustainable reactions. Therefore, utilizing a ceria-zirconia catalyst synthesized via the inverse micelle method for the oxidation of benzyl alcohol provides a green and sustainable methodology for the synthesis of benzaldehyde under mild conditions.

show abstract

Section: Resultsmentioning

confidence: 99%

“…Low magnitude in error values indicates better predictive capacity. 105 MSE, which is a measure of how close a fitted line is to a data point, was determined for the three models. In addition, the RMSE, which is the square root of the MSE, was also calculated.…”

Section: Comparison Performance Between Rsm Ann and Anfis Modelmentioning

confidence: 99%

Performance Evaluation of Benzyl Alcohol Oxidation with tert-Butyl Hydroperoxide to Benzaldehyde Using the Response Surface Methodology, Artificial Neural Network, and Adaptive Neuro-Fuzzy Inference System Model

Emeji,

Kumi,

Meijboom

2024

ACS Omega

View full text Add to dashboard Cite

show abstract

“…Rengel et al 70 optimized the starch hydrolysis conditions obtained from microalgae using central composite design to get LA and HMF. The conversion of sugarcane bagasse into LA catalyzed by H 2 SO 4 was modeled by Ogedjo et al 71 using response surface methodology and artificial intelligence techniques, including artificial neural networks and fuzzy inference systems. The authors also compared the experimental values obtained with those predicted by the models, increasing the process efficiency.…”

Section: New Perspectives On the Use Of Biomass For La Synthesismentioning

confidence: 99%

Recent advances, perspectives and challenges on levulinic acid production from residual biomass

Bazoti

Bonatto

Scapini

et al. 2023

Biofuels Bioprod Bioref

View full text Add to dashboard Cite

Over the years, several studies have focused on integrally exploring lignocellulosic biomass to achieve satisfactory yields of different bioproducts and establish economically viable industrial processes. Among the bioproducts, levulinic acid (LA) has emerged as one of the top platform products derived from biomass, mainly owing to its expanding market economic position, which can stimulate viability and attract the attention of investors in the field. Considered a building block because of its versatile intermediate chemical structure, it can be used to synthesize many compounds with applications in fuels, pharmaceutical and cosmetics industries, food additives and solvents. The main synthesis route for obtaining LA is the degradation of cellulose via acid catalysis. In this context, lignocellulosic biomass is a promising and sustainable way of getting LA. Recent research has explored a potential path to full technological development associated with LA from various biomass and different catalysts. In this scenario, a comprehensive review concerning biomass for LA production and the challenges in the synthesis process is proposed. The primary studies conducted over the years and approaches to using and appreciating residual biomass are also discussed. This work also considers the use of technological tools to optimize the production of LA and seeks to contribute sustainable proposals still little explored, such as the intensification of the process and the use of fruit residues in the synthesis of this promising building block.

show abstract

“…It constructs and maps a non-linear correlation between input and output, predicting an output when the training error falls within an acceptable limit. 20 This study investigates the efficacy of iron-doped cocoa husk biochar (Fe-CHB) as a novel cathode catalyst in bio-electro-Fenton (BEF) systems for removing azo dyes. Physicochemical characterization revealed Fe-CHB's remarkable attributes, including its intricate mesoporous structure, enriched iron content, and presence of oxygen-containing functional groups.…”

Section: Introductionmentioning

confidence: 99%

Performance of iron – doped activated carbon synthesised from cocoa husk as a cathode catalyst in microbial fuel cell powered Fenton process

John,

Ajit,

Krishnan

et al. 2024

J of Chemical Tech & Biotech

View full text Add to dashboard Cite

BACKGROUNDBio‐electro‐Fenton (BEF) systems, specifically microbial fuel cell (MFC) driven electro‐Fenton (EF) systems, have gained significant attention in wastewater treatment in recent years. The role of the cathode catalyst in BEF is crucial, as it undergoes O2 reduction via a 2e− oxygen reduction reaction (ORR) to produce H2O2. In this study, we have harnessed the abundant lignocellulosic composition of cocoa pod husk (CPH) to prepare a novel iron‐doped heterogeneous Fenton catalyst for the BEF system. Cocoa is typically grown for its wet beans, which constitute only one third of cocoa fruit by weight, while CPH makes up about two‐thirds of the weight and is often discarded as by‐product or waste. As a result, approximately 10 million tons of CPH are produced globally each year, highlighting the potential for transforming it into a value‐added product. To date, CPH has been utilised as a natural fertiliser, soil amendment, biomass fuel, poultry and livestock feed ingredient, and more.RESULTSThe presence of mesoporous structure, iron content, oxygen containing functional groups, and prominent reduction peaks in cyclic voltammetry validated the Fe‐doped cocoa husk biochar's (Fe‐CHB) potential to act as an ORR catalyst. The BEF system achieved an open circuit voltage, current, and power densities of 0.697 V, 0.15 A/m2, and 0.040 W/m2, respectively, at an optimum resistance of 350 Ω. Optimisation of the process parameters using RSM and ANN predicted maximum dye removal efficiencies of 93.34% and 92.45%, respectively, at dye and substrate concentrations of 10 mg/L and 1 g/L. These predictions closely aligned with the experimental findings of 92.5%.CONCLUSIONThe synthesised catalyst provided large surface area, electrical conductivity, superior ORR catalytic efficiencies, and ample sites for H2O2 activation. Hence, Fe‐CHB can serve as a highly effective electrocatalyst in BEF systems. © 2024 Society of Chemical Industry (SCI).

show abstract

Modeling of sugarcane bagasse conversion to levulinic acid using response surface methodology (RSM), artificial neural networks (ANN), and fuzzy inference system (FIS): A comparative evaluation

Cited by 18 publications

References 52 publications

Performance Evaluation of Benzyl Alcohol Oxidation with tert-Butyl Hydroperoxide to Benzaldehyde Using the Response Surface Methodology, Artificial Neural Network, and Adaptive Neuro-Fuzzy Inference System Model

Performance Evaluation of Benzyl Alcohol Oxidation with tert-Butyl Hydroperoxide to Benzaldehyde Using the Response Surface Methodology, Artificial Neural Network, and Adaptive Neuro-Fuzzy Inference System Model

Recent advances, perspectives and challenges on levulinic acid production from residual biomass

Performance of iron – doped activated carbon synthesised from cocoa husk as a cathode catalyst in microbial fuel cell powered Fenton process

Contact Info

Product

Resources

About