Modelling drying kinetics of paddy in swirling fluidized bed dryer

Sitorus, Agustami; Novrinaldi,; Putra, Satya Andika; Cebro, Irwin Syahri; Bulan, Ramayanty

doi:10.1016/j.csite.2021.101572

Cited by 23 publications

(13 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To validate the predictability of the ANN model, standard statistical parameters like root mean square error (RMSE), Mean absolute error (MAE), and Coefficient of determination (R 2 ) were employed to verify the accuracy of the prediction [31]. After using various ANN topologies to the testing data, it was found that the network with TANSIGMOID -TANSIGMOID activation function combinations and 5 neurons in the input hidden layer gave the best result with maximum values of R 2 , RMSE, and MAE of 0.9976, 0.0360, and 0.0034 were in accordance with the range reported in literature, R 2 ranged from 0.981 to 0.999, RMSE ranged from 0.0333 to 0.1475 and MAE ranged from 0.05318 to 0.0088 [19,32].…”

Section: Moisture Ratio Processing By Ann Predictive Modelingsupporting

confidence: 86%

“…The number of processing elements and iterations (epoch) for each topology was recorded. After applying different ANN topologies to the testing data, it was found that the network with TANSIGMOID -TANSIGMOID activation function combinations and 9 neurons in the input hidden layer produced the best results, with R 2 , RMSE, and MAE values of 0.9696, 0.0916, and 0.0028 were in accordance with the range reported in literature, R 2 ranged from 0.981 to 0.999, RMSE ranged from 0.0333 to 0.1475 and MAE ranged from 0.05318 to 0.0088 [19,32].…”

Section: Drying Rate Processing By Ann Predictive Modelingsupporting

confidence: 85%

See 1 more Smart Citation

Artificial neural network modeling for drying kinetics of paddy using a cabinet tray dryer

Subramanyam

Narayanan

2023

CI&CEQ

View full text Add to dashboard Cite

The study of drying kinetics and characteristics of agricultural products is essential for drying time estimation, designing dryers, and optimizing the drying process. Moisture diffusivity under different drying conditions is crucial to process and equipment design. The drying kinetics of paddy using a cabinet tray dryer was modeled using an Artificial Neural Network (ANN) technique. For predicting moisture ratio and drying rate, the Levenberg-Marquardt (L.M.) training algorithm with TANSIGMOID and TANSIGMOID hidden layer activation function provided superior results. A comparative evaluation of the predicting abilities of ANN and 12 different mathematical drying models was also carried out. The Midilli model was found to be adequate for fitting the experimental data with an R2 comparable to that of the ANN. However, the RMSE observed for ANN (0.0360) was significantly lower than that of the midilli model (0.1673 to 0.712). Effective moisture diffusivity increased with an increase in temperature from 15.05 to 28.5 x 10-9 m2/s. The activation energy for drying paddy grains varied between 6.8 to 7.3 kJ/mol, which showed a moderate energy requirement for moisture diffusion.

show abstract

Section: Moisture Ratio Processing By Ann Predictive Modelingsupporting

confidence: 86%

Section: Drying Rate Processing By Ann Predictive Modelingsupporting

confidence: 85%

Artificial neural network modeling for drying kinetics of paddy using a cabinet tray dryer

Subramanyam

Narayanan

2023

CI&CEQ

View full text Add to dashboard Cite

show abstract

“…According to Mohapatra and Rao [22], coefficients of determination (R 2 ) higher than 90% are satisfactory in the drying process. Sitorus et al [33] used the same parameters to choose the best model that fitted the kinetic drying of paddy in a fluidized bed. Madamba et al [34] reported that this parameter alone does not constitute a good index for the selection of nonlinear models.…”

Section: Resultsmentioning

confidence: 99%

Analysis of Volatiles of Rose Pepper Fruits by GC/MS: Drying Kinetics, Essential Oil Yield, and External Color Analysis

Oliveira

Carocho

Finimundy

et al. 2022

Journal of Food Quality

View full text Add to dashboard Cite

Condiments and culinary supplements are subjected to long-term storage and may undergo physical, chemical, and biological changes that can influence their quality. Thus, the objective of the present study was to analyze the drying kinetics of rose pepper (Schinus terebinthifolius Raddi) fruits in an oven with forced air circulation at different temperatures, namely, 45, 55, 65, and 75°C, and determine the effective diffusion coefficient and activation energy using different mathematical models. Furthermore, the effects of the different drying temperatures were analyzed for external color parameters and yield of essential oil contents by gas chromatography coupled to a mass spectrometer. Of the ten models used for fitting, Thompson’s model was one with the best fitting to represent the drying of rose pepper fruits. The diffusion coefficient increases with the elevation of drying air temperature, described by the Arrhenius equation, with activation energy of 53.579 kJ·mol−1. The color of the fruits decreased in lightness (L ∗ ) with the increase in temperature. Of the thirty-eight terpenes identified, α-pinene and cis-ocimene were the most abundant, with the overall highest yield being found at a drying temperature of 45°C.

show abstract

“…The model with the highest R 2 and lowest RMSE and X 2 was chosen as the best model to fit the experimental data. Numerous researchers used the evaluation criteria of the highest R 2 and the lowest RMSE and X 2 (Kingsly and Singh 2007;Roberts et al 2008;Phanphanich and Mani 2010;Erbay and Icier 2010;Yun et al 2013;Manikantan et al 2014;Sundaram et al 2016;Sadaka and Atungulu 2018;Owusu-Sekyere et al 2021;Sitorus et al 2021). The RMSE and X 2 were calculated according to Eqs.…”

Section: Model Fitting To the Experimental Datamentioning

confidence: 99%

Determination of short-grain rough rice drying kinetics under isothermal conditions using an integrated model

Sadaka

2022

BioRes

View full text Add to dashboard Cite

The constants of the drying kinetics models of short-grain rough rice were determined under isothermal conditions between a temperature of 40 °C and 100 °C. The initial moisture content of the rough rice was 28.2% dry basis. The results revealed that increasing the drying temperature and drying duration decreased the moisture content of the rough rice. The lowest rough rice moisture content (15.58% dry basis) was achieved at a drying temperature of 100 °C and a drying duration of 6 h. Four well-known models, i.e., Page, Newton, Logarithmic, and Henderson and Pabis, were evaluated. The models were evaluated based on the highest coefficient of determination value; the lowest root means square error, and the Chi-square value. The Page and Logarithmic models fit four and three cases of the seven drying curves, respectively, among the four evaluated models. Accordingly, combining the Page and Logarithmic models in an integrated model resulted in a model that fits all the seven studied curves. Furthermore, increasing the air temperature from 40 °C to 100 °C increased the moisture diffusivity from 1.5517 × 10-9 m2/s to 4.2698 × 10-9 m2/s. As a result, the activation energy value reached 16.43 kJ/mol for short-grain rough rice under the studied drying conditions.

show abstract

Modelling drying kinetics of paddy in swirling fluidized bed dryer

Cited by 23 publications

References 15 publications

Artificial neural network modeling for drying kinetics of paddy using a cabinet tray dryer

Artificial neural network modeling for drying kinetics of paddy using a cabinet tray dryer

Analysis of Volatiles of Rose Pepper Fruits by GC/MS: Drying Kinetics, Essential Oil Yield, and External Color Analysis

Determination of short-grain rough rice drying kinetics under isothermal conditions using an integrated model

Contact Info

Product

Resources

About