ORIGINAL PAPER
Neural network development for automatic identification of the endpoint of drying barley in bulk
More details
Hide details
Journal of Research and Applications in Agricultural Engineering 2008;53(1):26-31
KEYWORDS
ABSTRACT
A thesis was proved that it is possible an automatic endpoint determination of drying barley in bulk, 1.2 meter's deep, based on a neural network, using a continuous on-line measurement of atmospheric air temperature and relative humidity, plenum air temperature and grain temperature in selected locations inside the bed - in situations in which drying air temperature and relative humidity change stochastically. The usefulness of individual input variables characterising the process as well as their influence on the quality of the obtained model were analysed. Several different topologies of the developed models were compared and the RBF type networks were selected as the best ones. The developed networks are characterised by a high, ranging from 93.3 to 99.6%, correctness of case assignment to the recognised classes in the course of the identification process and a high capability to generalise the analysed data.
REFERENCES (11)
1.
Bakhshiani M., Khazaei J., Chegini G. R.: Artificial neural networks and mathematical modeling of drying kinetics of tomato slices. Proceedings of the "International Congress on Information Technology in Agriculture, Food and Environment", Adana, Turcja, 2005, pp. 656-670.
2.
Białobrzeski I., Markowski M., Bowszys J., Myhan R.: Symulacyjny model zmian pola temperatury w silosie zbożowym. Inżynieria Rolnicza, 2005, Vol 8(68), pp. 23-30.
3.
Kahyaoglu T., Kaya S.: Use of artificial neural networks for food process control and modelling. Proceedings of the "International Congress on Information Technology in Agriculture, Food and Environment", Adana, Turcja, 2005, pp. 34-40.
4.
Korbicz J., Obuchowicz A., Uciński D.: Artificial Neural Networks; Fundamentals and Applications (in Polish). Warszawa: Akademicka Oficyna Wydawnicza PLJ, 1994.
5.
Nellist M. E.: Bulk storage drying in theory and practice. Journal of the Royal Agricultural Society of England. 1998, Vol 159, pp. 120-135.
6.
Olszewski T., Boniecki P.: Algorytmy genetyczne jako narzędzie optymalizacyjne w sieciach neuronowych. Inżynieria Rolnicza, 2005, 2(62).
7.
Neural Networks (In Polish). Sieci neuronowe. Biocybernetyka i inżynieria biomedyczna. Pod red. Duch W., Korbicz J., Rutkowski L., Tadeusiewicz R. Tom 6. Warszawa: Akademicka Oficyna Wydawnicza Exit, 2000.
8.
Ryniecki A., Gawrysiak-Witulska M., Wawrzyniak J.: Correlation for Automatic Identification of Drying Endpoint in Near Ambient Dryers; Application to Malting Barley. Biosystems Engineering, 2007, Vol 98(4), pp. 437-445.
9.
Ryniecki A., Pawłowska A., Moliński K.: Stochastic analysis of grain drying with unheated air under two different climates. Drying Technology - An International Journal, 2006, Vol 24(9), pp. 1147-1152.
10.
Tadeusiewicz R.: Wprowadzenie do praktyki stosowania sieci neuronowych. StatSoft Polska, Kraków, 1999.
11.
Wilcke W. F., Hellevang K. J.: Wheat and Barley Drying. University of Minnesota Extension Service, FS-5947, St. Paul, USA, 2002.