Nonlinear model of a rice drying process using neural networks
DOI:
https://doi.org/10.17533/udea.vitae.v25n3a02Keywords:
drying, rice, modeling, neural networks, nonlinear.Abstract
Background: The production quality of rice is highly depended on the drying process as drying weakens the rice kernel. A look at the production process of rice in the industry was taken. The drying of rice influences the storage capacity of the grain, the energy consumption, the final mass of the grain and the percentage of whole grains at the end of the process. Objective: The main objective was to analyse the drying of rice by making an artificial neural network to model and simulate it. Methods: The modeling of a rice drying process using neural networks was presented. These models are suitable to be used in combination with model-based control strategies in order to improve the drying process. The implementation, preprocessing and data retrieval for the design of an artificial neural system was analyzed. Controlling the drying factors is of major importance. Feedforward and dynamic neural networks were compared based on their performance. Results: It was concluded that when some part of the dataset is given as training, even with one dataset, a back-propagation network simulates very well the other parts of the drying curve. It can be said that the approximations done by the networks to obtain a nonlinear model of the rice drying process are quiet good. Conclusions: Firstly, because of the too little data available for training, the networks were not as good as expected. More data is needed to realy have a powerfull network capable of approximated very well the drying curve. Secondly, a backpropagation network can be a good solution for modelling and for use in a controller if more data is available, in contrast a linear network gave bad results. thirdly, a network with little number of layers is the best option. A perfect mapping from the input to the output is impossible due the differences in each test and the imperfect sensors.
Downloads
References
Garreiro JM, Kahan S, Zecchi B, Gerla P, Clavijo L, Rodríguez A, editors. A SIMPLE MODEL FOR RICE GRAINS IN A
DEEP-BED DRYER. 4th MERCOSUR Congress on Process Systems Engineering: 2nd MERCOSUR Congress on Chemical Engineering : Proceedings of ENPROMER 2005; 2005; Rio de Janeiro. 1 p.
Brooker DB, Bakker-Arkema FW, Hall CW. Drying cereal grains. 4 ed. USA: American Association of Cereal Chemists; 1992.
Eckert ERG, Drake Jr RM. Analysis of heat and mass transfer. 1987.
Thompson T, Peart R, Foster G. Mathematical simulation of corn drying—a new model. Transactions of the ASAE.
;11(4):582-0586.
Stone M, Kranzler G. A microprocessor controlled thin-layer dryer [Down-draft-cross-flow design]. Paper-American Society of Agricultural Engineers (Microfiche collection)(USA) No fiche No 81-5028. 1981.
Wafler P, Warnock W. A microprocessor controlled crossflow grain dryer test unit [Monitors dry bulb and dew point temperatures, hardware, software]. Microfiche collection. 1982.
Mittal G, Otten L. Microprocessor controlled low-temperature corn drying system. Agricultural Systems. 1983;10(1):1-19.
Omid M, Yadollahinia A, Rafiee S, editors. A thin-layer drying model for paddy dryer. Proc of the International conference on Innovations in Food and Bioprocess Technologies, AIT, Pathumthani, Thailand, 12th; 2006. 202-11 p.
Liu X, Chen X, Wu W, Peng G. A neural network for predicting moisture content of grain drying process using genetic algorithm. Food Control. 2007;18(8):928-33.
Amiri Chayjan R, Moazez Y. Estimation of paddy equilibrium moisture sorption using ANNs. Journal of Applied Sciences. 2008;8:346-51.
Freeman JA, Skapura DM. Algorithms, applications, and programming techniques: Addison-Wesley Publishing Company, USA; 1991. 414 p.
Demuth H, Beale M. Neural Network Toolbox For Use with Matlab--User’S Guide Version 3.0. 1993.
Thyagarajan T, Panda R, Shanmugan J, Rao V, Ponnavaikko M. Development of ANN model for non-linear drying process. Drying technology. 1997;15(10):2527-2540.
Tohidi M, Sadeghi M, Mousavi SR, Mireei SA. Artificial neural network modeling of process and product indices in deep bed drying of rough rice. Turkish Journal of Agriculture and Forestry. 2012;36(6):738-748.
Beigi M, Torki-Harchegani M, Tohidi M. Experimental and ANN modeling investigations of energy traits for rough rice drying. Energy. 2017;141:2196-205.
Chokphoemphun S, Chokphoemphun S. Moisture content prediction of paddy drying in a fluidized-bed drier with a vortex flow generator using an artificial neural network. Applied Thermal Engineering. 2018;145:630-636.
Alam MA, Saha CK, Alam MM, Ashraf MA, Bala BK, Harvey J. Neural network modeling of drying of rice in BAU-STR dryer. Heat and Mass Transfer. 2018:1-9.
Thant PP, Robi P, Mahanta P. ANN Modelling for Prediction of Moisture Content and Drying Characteristics of Paddy in Fluidized Bed. International Journal of Engineering and Applied Sciences (IJEAS).3(3):118-23
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2018 Vitae
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
Copyright Notice and Open Access Statement
The Journal Vitae works under the Open Access license, and the published manuscripts remain available for the public, both on the Journal's website and in databases, under the Creative Commons license, "Noncommercial Attribution" and "Share alike" systems, adopted in Colombia. Hence, when the authors agree to publish in the Journal Vitae, they will not have the right to economic retributions on publications and reproductions through different diffusion media. The documents are freely available to the internet public, permitting users to read, download, copy, distribute, print, search, or link to the full texts and pass them as data to software. The only constraint on reproduction and distribution, should be to give authors control over the integrity of their work and the right to be appropriately acknowledged and cited.
Authors declare that:
-
They are the intellectual property owners and are responsible for all the information stated in the article.
-
This manuscript has not been submitted or published in other printed or digital media. They accept the responsibility for the judgments, opinions, and points of view expressed in the published article and, therefore, they exonerate Universidad de Antioquia and Journal Vitae from any process.
-
They exempt Universidad de Antioquia and Journal Vitae from settling conflicts or disputes related to the authorship of the referred article.
-
They accept the revision of the original manuscript by suitable personnel, and they bind themselves to perform the corrections appointed or suggested by the assessors.
-
Therefore, they know the editorial process and will not bind the Editorial Board of the Journal to assume any obligations regarding the volume and issue in which the article is published.
-
They transfer the rights of publication, reprinting, and distribution of the article from the moment of its approval, in print and digital format, without the right to economic rewards, and under the licensing conditions considered relevant by Journal Vitae.
-
They fully authorize Universidad de Antioquia and Journal Vitae to submit the published material to the diverse databases and indexing systems where the Journal can be found to comply with the requirements of the regulatory authorities to maintain the national classification of journals.
-
They will assume the article publication costs established for the current issue, and they will make the payment as soon as they are informed about the volume and the issue in which the final version of the article is published.
-
After the article is published, you can share digital or printed copies in a noncommercial manner. You will be able to use the paper in your institution or company for educational or research purposes, including the use in course programs.
Conflict of interest: Authors are responsible for recognizing and disclosing any financial or other benefits that could be perceived to bias their work, acknowledging all financial support and any personal connections with potential sponsors. Examples of such conflicts include receiving research funds or honoraria, serving on advisory boards, stock ownership, or employment and consulting arrangements. Authors without such connections should clearly state that they have no financial support or personal relationships that could be perceived to bias their work. All conflicts of interest should be disclosed on the author's identification page of the manuscript.
