Predicting hydrodynamic parameters and volumetric gas–liquid mass transfer coefficient in an external-loop airlift reactor by support vector regression

Kojić, Predrag; Omorjan, Radovan

doi:10.1016/j.cherd.2017.07.029

Cited by 21 publications

(14 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The main concept in SVR is mapping input data into higher dimensional feature space, then constructing a kernel function that permits the problem to be solved by linear regression function. SVR has a unique advantage over an artificial neural network (ANN) because it is less prone to overfitting problems due to the fact that its objective function is convex, hence global optimum is often reached [27]. Consequently, SVR results are consistent and reproducible, unlike ANN that may suffer from prediction uncertainties [28].…”

Section: Methodsmentioning

confidence: 99%

Development of a predictive model for estimating the specific heat capacity of metallic oxides/ethylene glycol-based nanofluids using support vector regression

Alade

Rahman

Bagudu³

et al. 2019

Heliyon

View full text Add to dashboard Cite

The specific heat capacity of nanofluids is a fundamental thermophysical property that measures the heat storage capacity of the nanofluids. is usually determined through experimental measurement. As it is known, experimental procedures are characterised with some complexities, which include, the challenge of preparing stable nanofluids and relatively long periods to conduct experiments. So far, two correlations have been developed to estimate the The accuracies of these models are still subject to further improvement for many nanofluid compositions. This study presents a four-input support vector regression (SVR) model hybridized with a Bayesian algorithm to predict the specific heat capacity of metallic oxides/ethylene glycol-based nanofluids. The bayesian algorithm was used to obtain the optimum SVR hyperparameters. 189 experimental data collected from published literature was used for the model development. The proposed model exhibits low average absolute relative deviation (AARD) and a high correlation coefficient (r) of 0.40 and 99.53 %, respectively. In addition, we analysed the accuracies of the existing analytical models on the considered nanofluid compositions. The model based on the thermal equilibrium between the nanoparticles and base fluid (model II) show good agreement with experimental results while the model based on simple mixing rule (model I) overestimated the specific heat capacity of the nanofluids. To further validate the superiority of the proposed technique over the existing analytical models, we compared various statistical errors for the three models. The AARD for the BSVR, model II, and model I are 0.40, 0.82 and 4.97, respectively. This clearly shows that the model developed has much better prediction accuracy than existing models in predicting the specific heat capacity of metallic oxides/ethylene glycol-based nanofluids. We believe the presented model will be important in the design of nanofluid-based applications due to its improved accuracy.

show abstract

Section: Methodsmentioning

confidence: 99%

Development of a predictive model for estimating the specific heat capacity of metallic oxides/ethylene glycol-based nanofluids using support vector regression

Alade

Rahman

Bagudu³

et al. 2019

Heliyon

View full text Add to dashboard Cite

show abstract

“…The ANN results, including the weight values, depend on the initial assumptions of parameters necessary for ANN construction and fitting. Similarly, the distinctive number of hidden neurons can give diverse ANN model outcomes (Kojić & Omorjan, ). With a specific end goal to prevent this problem each topology was run several times to avoid random correlation due to initial assumption and random initialization of the weights.…”

Section: Methodsmentioning

confidence: 99%

Multiobjective process optimization for betaine enriched spelt flour based extrudates

Kojić

Ilić

Kojić

et al. 2018

J Food Process Engineering

Self Cite

View full text Add to dashboard Cite

The main purposes of this work are successful modeling of twin‐screw extrusion process using predictive models, investigating the effect of process parameters such as screw speed, feed rate, and feed moisture content on the process and product responses and finally optimizing the process regarding betaine content in the extruded product and energy consumption. The second order polynomial approximation models and the artificial neural network were developed to predict the betaine content, showing the high accuracy in the prediction of experimental results. This study introduces the multiobjective optimization (MOO) approach in the extrusion process of spelt flour. The maximal betaine content (between 1,506.8 and 1,605.2 mg/40 g) and minimal energy consumption (between 101.3 and 108.5 W hr/kg) were indicated by MOO procedure, which were gained using the following input parameters: feed flow rate feed about 24 kg/h, screw speed about 252 RPM and moisture content from 21.6 to 23.4%. Practical applications This study introduces the multiobjective optimization (MOO) approach in the extrusion process of spelt flour, which provides the selection of optimal solution that enables the extruder to reach the optimum conditions of the process and provide decision maker with deeper understanding of the process. The present study analyzes the influence of extrusion cooking parameters like: screw speed, feed flow rate, and feed moisture content on the betaine content in the extrudate product and specific mechanical energy input during the processing of betaine enriched spelt flour based extrudates. One way to improve the intake of betaine in the general population can be to enrich foods with betaine. According to European Breakfast Cereal Association for extruded products portion sizes should be 40 g. Consuming a portion of a functional extrudate product with the addition of betaine (1,500 mg/day) could give expected health effects. Final extrudate product from this study satisfies these statements.

show abstract

“…ANN results, including the weight values depend on the initial assumptions of parameters necessary for ANN construction and fitting. 27,28 A series of various topologies were used, in which the number of hidden neurons varied from 10 to 20 and the training process of each network was run 100,000 times with random initial values of weights and biases. The optimization process was performed on the basis of validation error minimization.…”

Section: Artificial Neural Network (Ann)mentioning

confidence: 99%

Achillea clypeolata Sibth. & Sm. essential oil composition and QSRR model for predicting retention indices

Aćimović

Pezo

Cvetković

et al. 2021

JSCS

View full text Add to dashboard Cite

The aim of this study was the prediction model of retention indices of compounds from the aboveground parts of Achillea clypeolata Sibth. & Sm. essential oil, obtained by hydrodistillation and analysed by GC-MS. The quantitative structure-retention relationship analysis was applied in order to anticipate the retention time of the obtained compounds. The selection of the seven molecular descriptors was done by a genetic algorithm. The chosen descriptors were uncorrelated and were used to construct an artificial neural network. A total of 40 experimentally obtained retention indices was used to build this prediction model. The coefficient of determination for the training, testing and validation cycles were: 0.950, 0.825 and 1.000, respectively, indicating that this model could be used for prediction of retention indices for A. clypeolata, essential oil compounds.

show abstract

Predicting hydrodynamic parameters and volumetric gas–liquid mass transfer coefficient in an external-loop airlift reactor by support vector regression

Cited by 21 publications

References 33 publications

Development of a predictive model for estimating the specific heat capacity of metallic oxides/ethylene glycol-based nanofluids using support vector regression

Development of a predictive model for estimating the specific heat capacity of metallic oxides/ethylene glycol-based nanofluids using support vector regression

Multiobjective process optimization for betaine enriched spelt flour based extrudates

Achillea clypeolata Sibth. & Sm. essential oil composition and QSRR model for predicting retention indices

Contact Info

Product

Resources

About