Evaluation of micromixing in helically coiled microreactors using artificial intelligence approaches

Izadi, Mahtab; Rahimi, Masoud; Beigzadeh, Reza

doi:10.1016/j.cej.2018.09.052

Cited by 34 publications

(17 citation statements)

References 45 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The fitness functions (Eqs. (13) and 14) were minimized using GA to optimize the constants of the power-law correlations (Eqs. (11) and (12)) and the following relations were obtained:…”

Section: Resultsmentioning

confidence: 99%

“…Therefore, better mixing and heat transfer performance can be expected in such channels in comparison with the straight ones. Numerous researchers examined various curved microchannels, including serpentine [11,12], helically coiled [13], and spiral [14] microchannels. The mass transfer rates in a liquid-liquid reaction were evaluated in a serpentine microchannel by Plouffe et al [11].…”

Section: Introductionmentioning

confidence: 99%

“…Izadi et al [13] proposed artificial intelligence models such as neural network and neuro-fuzzy model to estimate the mixing characteristics in helically coiled microreactors. The Villermaux/Dushman reaction was employed and analyzed in the experiments.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Optimization of Helical Microreactors by a Genetic Algorithm Technique

2020

Self Cite

View full text Add to dashboard Cite

Micromixing in coiled microreactors is attained by a higher pressure drop and more pumping power. The optimum geometries of helically coiled microreactors were determined by multiobjective optimization based on a genetic algorithm (GA). The segregation index (X s) values of the Villermaux/Dushman reaction were measured in twelve coiled microchannels. The effects of the geometries including curvature diameter and coil pitch on the mixing performance and pressure drop were investigated. The mixing performance of the microreactors and the pressure drop were considered as the GA objectives. The optimum geometries of the studied coiled microchannels with a trade-off between X s and friction factors were obtained using GA-based multiobjective optimization.

show abstract

“…The fitness functions (Eqs. (13) and 14) were minimized using GA to optimize the constants of the power-law correlations (Eqs. (11) and (12)) and the following relations were obtained:…”

Section: Resultsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Optimization of Helical Microreactors by a Genetic Algorithm Technique

2020

Self Cite

View full text Add to dashboard Cite

show abstract

“…The key process in the modeling is to determine the appropriate number of hidden layers as well as hidden neurons. Many hidden layers and neurons can lead to network complexity and overfitting [21]. Therefore, an ANN with one hidden layer was considered in which the number of hidden neurons was determined through the trial-and-error approach.…”

Section: Ann Modelingmentioning

confidence: 99%

Assessment of Cr(VI) Biosorption from Aqueous Solution by Artificial Intelligence

Beigzadeh

Rastegar

2020

Chem. Methodol.

View full text Add to dashboard Cite

This work investigates the efficiency of date palm fiber as a biosorbent to the removal of Cr(VI) from aqueous solution. The effect of four main factors including, the initial pH, initial Cr(VI) concentration, biosorbent dosage, and time were assessed. The results revealed that, the maximum 89% removal of Cr(VI) at time 50 min, initial pH 3.2, initial Cr(VI) 181 ppm, and biosorbent dosage 0.8% (w/v) was obtained. The artificial neural network (ANN) model was developed to predict the Cr(VI) removal as a function of the studied variables. A number of data points were considered as test data to validate the model. The results indicated a high accuracy of the ANN modeling in estimating the target variable.

show abstract

“…The analyses of the contribution of input variables in the ANN model showed that the curvature ratio could not impact the simulative accuracy of void fraction under the current conditions. Izadi et al [43] employed ANN and adaptive neuro-fuzzy inference system (ANFIS) models to evaluate micromixing in micro-helically coiled tubes. It was found that ANN approach has higher precision than ANFIS in segregation index modelling in micro-helically coiled tubes.…”

Section: Introductionmentioning

confidence: 99%