2020
DOI: 10.1002/ceat.202000041
|View full text |Cite
|
Sign up to set email alerts
|

Response Surface Methodology and Artificial Neural Networks for Optimization of Catalytic Esterification of Lactic Acid

Abstract: Response surface methodology (RSM) and artificial neural network (ANN) models were employed to study the esterification of lactic acid and isoamyl alcohol. A carbon-based solid acid catalyst prepared by wet impregnation was used in the esterification reaction. Experimental characterization revealed its potential to serve as catalyst for the esterification reaction. The experiments were performed based on the design of experiments provided by RSM and ANN models. Both models were compared on the basis of predict… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1

Citation Types

0
3
0

Year Published

2021
2021
2023
2023

Publication Types

Select...
5

Relationship

0
5

Authors

Journals

citations
Cited by 5 publications
(3 citation statements)
references
References 29 publications
0
3
0
Order By: Relevance
“…The normal plot (Figure 5a) revealed a straight line that expressed a decent direct agreement between normal probability (%) and externally studentized residuals (Hasanudin, Asri, Said et al, 2022). It appeared that the response transformation was not required and that there were no major problems with the data's normality (Chandane et al, 2020).…”
Section: Model Development and Anovamentioning
confidence: 94%
“…The normal plot (Figure 5a) revealed a straight line that expressed a decent direct agreement between normal probability (%) and externally studentized residuals (Hasanudin, Asri, Said et al, 2022). It appeared that the response transformation was not required and that there were no major problems with the data's normality (Chandane et al, 2020).…”
Section: Model Development and Anovamentioning
confidence: 94%
“…An important issue about the esterification reaction is that an acid-based catalyst should be used to shift the equilibrium in the forward direction. However homogeneous catalysts were found to cause corrosion problems in addition to an enormous amounts of toxic effluents [3][4][5]; and because the recovery of homogeneous catalysts was found to be expensive, heterogeneous catalysts were found to be a suitable alternative [6].…”
Section: Introductionmentioning
confidence: 99%
“…The artificial neural network (ANN) technique can be employed for solving linear and nonlinear multivariable regres-sion problems [19,20]. An ANN has several interesting features, such as finding complicated nonlinear relationships, employing multiple training algorithms, and specifying interactions between input variables [21,22]. An adaptive neuro-fuzzy inference system (ANFIS) is made by incorporating the features of a fuzzy system and a neural network.…”
Section: Introductionmentioning
confidence: 99%