CFP last date
22 April 2024
Reseach Article

Machine Learning Application in Process on Extra Virgin Olive Oil Elaboration Disk Stack Vertical Centrifuge Modeling

by A. Jiménez Márquez, G. Beltrán Maza
International Journal of Computer Applications
Foundation of Computer Science (FCS), NY, USA
Volume 176 - Number 37
Year of Publication: 2020
Authors: A. Jiménez Márquez, G. Beltrán Maza
10.5120/ijca2020920511

A. Jiménez Márquez, G. Beltrán Maza . Machine Learning Application in Process on Extra Virgin Olive Oil Elaboration Disk Stack Vertical Centrifuge Modeling. International Journal of Computer Applications. 176, 37 ( Jul 2020), 30-35. DOI=10.5120/ijca2020920511

@article{ 10.5120/ijca2020920511,
author = { A. Jiménez Márquez, G. Beltrán Maza },
title = { Machine Learning Application in Process on Extra Virgin Olive Oil Elaboration Disk Stack Vertical Centrifuge Modeling },
journal = { International Journal of Computer Applications },
issue_date = { Jul 2020 },
volume = { 176 },
number = { 37 },
month = { Jul },
year = { 2020 },
issn = { 0975-8887 },
pages = { 30-35 },
numpages = {9},
url = { https://ijcaonline.org/archives/volume176/number37/31446-2020920511/ },
doi = { 10.5120/ijca2020920511 },
publisher = {Foundation of Computer Science (FCS), NY, USA},
address = {New York, USA}
}
%0 Journal Article
%1 2024-02-07T00:44:28.141547+05:30
%A A. Jiménez Márquez
%A G. Beltrán Maza
%T Machine Learning Application in Process on Extra Virgin Olive Oil Elaboration Disk Stack Vertical Centrifuge Modeling
%J International Journal of Computer Applications
%@ 0975-8887
%V 176
%N 37
%P 30-35
%D 2020
%I Foundation of Computer Science (FCS), NY, USA
Abstract

Machine learning through the Artificial Neural Networks Supervised Learning technique was applied for modelling the clarification process of Virgin Olive Oil by a disk stack centrifuge equipment. The neural network obtained was trained and validated by a real database generated from different experiments to analyze the performance of the centrifuge. Compositional variability of oil, the water/oil relations flow rates, and both temperatures to the centrifuge inlet were the technological variables that were checked about the oil loss in the waters process outlet as parameter indicator of the effectiveness on solid-liquid-liquid separation. The results obtained in validation indicate a good predictive capacity, with a correlation coefficient r> 0.85 and an error of 0.30 kg h-1, which allows this neural model to become an excellent tool to optimize the centrifuge. A ‘Simulink’ model was designed for performance verification of the Network by checking the predictions obtained from another data set that not intervened in its build. A t-Test was applied and the results indicate they are not a significant difference between predicted and real mean values for P = 0.05 and 60 degrees of freedom.

References
  1. P. Harrington. Machine Learning in action. Manning Publication Co., Shelter Island. New York. 2012.
  2. K.G. Liakos, P. Busato, D. Moshou, S. Pearson, D. Bochtis, Machine Learning in Agriculture: A Review, Sensor, 18 (2018) 2674. 2018.
  3. K.J. Hunt, D. Sbarbaro, R. Zbikowski, P.J. Gawthrop, Neural network for control system, Automatica, 28 (1992).
  4. S. Linko, Y.H. Zhu, P. Linko, Applying neural networks as software sensors for enzyme engineering, Trends in Biotechnology, 17(4) (1999) 155-162. DOI:10.1016/S0167-7799(98)01299-2.
  5. C. Ahilan, J.E. Raja Dash, K. Somasundaram, N. Sivakumara. Performance assessment of heat exchanger using intellingent decision making tools. Applied Soft Computing 26 (2015) 474-482. DOI:10.1016/j.asoc.2014.10.018.
  6. J.M. Zamarreño, P. Vega, Identification and predictive control of a melter unit used in the sugar industry, Artificial Intelligence in Engineering, 11 (4) (1997) 365-373.
  7. I. Ceylan, I. Aktaş, Modeling of a hazenut dryer assisted heat pump by using artificial neural networks, Applied Energy, 85 (2008) 841-854.
  8. V.C. Mircea, R. Raluca, P.A. Şerban, Neural networks based model predictive control of the drying process In: Andrzej Kraslawski and Ilkka Turunen (Eds), Computer Aided Chemical Engineering, Elsevier,2003, pp. 389-394.
  9. J.P. Steyer, I. Queinnec, D. Simoes, Biotech: a real-time application of artificial intelligence for fermentation processes, Control Eng. Practice 1(2) (1993) 315-321.
  10. M. Uceda, G. Beltrán, A. Jiménez, Olive oil extraction and quality, Grasas Aceites 57 (2006) 25–31.
  11. A. Jiménez, M. Hermoso, M. Uceda, Extraction of virgin olive oil by two-phases continuous system. Influence of different variables of the process on certain parameters related to oil quality, Grasas y Aceites 4-5 (1995) 299-303.
  12. [R. Furferi, M. Carfagni, M. Daou, Artificial neural network software for real-time estimation of olive oil qualitative parameters during continuous extraction, Computers and Electronics in Agriculture 55(2) (2007) 115–131. DOI:10.1016/j.compag.2006.12.006.
  13. A. Jimenez, G. Beltran, M.P. Aguilera, M. Uceda, A sensor-software based on artificial neural network for the optimization of olive oil elaboration process, Sensors and Actuators B 129 (2008) ,985–990. DOI:10.1016/j.snb.2007.09.030.
  14. A. Jiménez, M.P. Aguilera, M. Uceda, G. Beltrán, Neural network as tool for virgin olive oil elaboration process optimization, Journal of Food Engineering 95 (2009) 135–141. DOI:10.1016/j.jfoodeng.2009.04.021.
  15. E. Funes, Y. Allouche, G. Beltrán, A. Jiménez, A Review: Artificial Neural Netwokrs as Tool for Control Food Industry Process, Journal of Sensor Technology 5 (2015) 28-43.. DOI:10,4236/jst2015,51004.
  16. Y. Allouche, E. Funes, G. Beltrán, A. Jiménez, Near infrared spectroscopy and artificial neural network to characterise olive fruit and oil on line for process optimization, Journal of Near Infrared Spectroscopy 23 (2015) 111-121. DOI: 10,1255/jnirs.1155.
  17. E. Funes, Y. Allouche, G. Beltrán, M.P. Aguilera, A. Jiménez, Predictive ANN models for the optimization of extra virgin olive oil clarification by means of vertical centrifugation. Journal of Food Process Engineering 41(1) (2017) 1-8. DOI:10,1111/jfpe,12593.
  18. E. Funes, Y. Allouche, G. Beltrán, M.P. Aguilera, A. Jiménez, A predictive artificial neural network model as a simulator of the extra virgin olive oil elaboration process. Journal of Near Infrared Spectroscopy 25(4) (2017) 278-285. DOI: 10,1177/0967033517725639.
  19. H. Demuth, M. Beale, Neural Network Toolbox. For use with MATLAB. User`s Guide Rev 4. (2001).
  20. Matlab 7.0, The MathWorks Inc., Natick, MA, USA.
  21. P. Masella, A. Parenti, P. Spugnoli, L.Calamai, Vertical centrifugation of virgin olive oil under inert gas, Eur J Lipid Sci Technol 114 (2012) 1094–1096
Index Terms

Computer Science
Information Sciences

Keywords

Machine Learning Neuronal Network Optimization Olive oil elaboration process Disk Stack Centrifuge.