|
Modeling the drying kinetics of onion in a fluidized bed drier equipped with a moisture controller using regression, fuzzy logic and artificial neural networks methods
|
M Ganjeh   , M Jafari * , F Ghanbari , M Dezyani , R Ezzati , M Soleimani |
|
|
|
Abstract: (9150 Views) |
| Background and Objective: Kinetic modeling of drying through novel modeling techniques including fuzzy logic and artificial neural networks can help optimization of the process and reduce energy consumption. Our main goal was to apply combined modeling methods for the drying process of onions.
Materials and Methods: In this research, thin layers of onion were dried in a laboratorial fluidized bed drier using three temperatures of 40, 50 and 60 C and two airflow speeds of 2 and 3 m/s in a constant air moisture. Three modeling methods including regression, fuzzy logic and artificial neural networks were applied to investigate the drying kinetics of the thin layer of this food.
Results: In the empirical modeling, the curve fitting tool of MATLAB software and nonlinear regression technique were used. According to the obtained results, the Diffusion Approximation with the correlation coefficient of 0.9999, root mean square error of 0.004157 and sum of squares error of 0.0005702 showed the best fit with the experimental data among the 9 fitted model. For simulation, interpolation and increase of the measured moisture ratios, fuzzy logic tool of MATLAB software with the Mamdani fuzzy model in the form of If-Then rules and triangular membership function was used. By entering the obtained results from fuzzy model into the neural network tool, the Feed-Forward-Back-Propagation network with the topology of 2-5-1 and the correlation coefficient of 0.99956 and mean square error of 0.000039385 with application of hyperbolic tangent sigmoid transfer function, Levenberg–Marquardt learning algorithm and 1000 epoch was determined as the best neural model.
Conclusion: In general, we can conclude, the combination of fuzzy logic and neural networks is a suitable and reliable method for modeling and prediction of drying kinetics of onion and similar product.
Keywords: Fluidized bed drier, Regression, Artificial neural networks, Modeling, Fuzzy logic |
|
| Keywords: Fluidized bed drier, Regression, Artificial neural networks, Modeling, Fuzzy logic |
|
|
Full-Text [PDF 540 kb]
(4064 Downloads)
|
Article type: Research |
Subject:
Food Science
Received: 2013/03/4 | Accepted: 2013/11/19 | Published: 2013/11/19
|
|
|
|
|
|
|
| Add your comments about this article |
|
|
|
