Metrika članka

  • citati u SCindeksu: [1]
  • citati u CrossRef-u:[2]
  • citati u Google Scholaru:[=>]
  • posete u poslednjih 30 dana:16
  • preuzimanja u poslednjih 30 dana:7
članak: 6 od 6  
Back povratak na rezultate
Journal on Processing and Energy in Agriculture
2017, vol. 21, br. 2, str. 66-70
jezik rada: engleski
vrsta rada: pregledni članak
objavljeno: 12/06/2017
doi: 10.5937/JPEA1702066P
Primena veštačkih neuronskih mreža u modelovanju i optimizaciji proizvodnje biogoriva
Univerzitet u Novom Sadu, Tehnološki fakultet

e-adresa: paj@tf.uns.ac.rs

Projekat

Unapređenje proizvodnje bioetanola iz proizvoda prerade šećerne repe (MPNTR - 31002)

Sažetak

Veštačke neuronske mreže, kao sistemi veštačke inteligencije koji oponašaju funkcije ljudskog mozga i bioloških neurona, nalaze sve veću primenu u različitim oblastima usled svoje raznovrsnosti i sposobnosti prilagođavanja određenoj nameni. Kada je u pitanju primena veštačkih neuronskih mreža u modelovanju bioprocesa, njihov zadatak u najvećem broju slučajeva predstavlja predviđanje ili prognoziranje vrednosti zavisnih promenljivih (izlaza) na osnovu poznatih vrednosti nezavisnih promenljivih (ulaza). Model bioprocesa uslovljen je strukturom neuronske mreže, koja obuhvata arhitekturu neuronske mreže (broj slojeva, broj neurona u svakom sloju i način povezivanja neurona), vrednosti sinaptičkih težina i odabrane aktivacione funkcije. Iako sam model bioprocesa predstavlja 'crnu kutiju' i ostaje nepoznat, što može da predstavlja poteškoću u analizi bioprocesa, veštačke neuronske mreže su pokazale znatno bolju sposobnost modelovanja, to jest predviđanja rezultata bioprocesa u poređenju sa drugim metodima modelovanja, kao što su metodologija odzivne površine i matematičko modelovanje. Dobijeni model dalje može da se koristi za optimizaciju bioprocesa, koja se najščešće vrši primenom genetičkih algoritama. Genetički algoritmi koriste model bioprocesa kao ciljnu funkciju, a process optimizacije predstavlja minimizaciju ili maksimizaciju date ciljne funkcije. Ovaj rad daje pregled osnovnih karakteristika i primene veštačkih neuronskih mreža u modelovanju i optimizaciji biotehnoloških procesa proizvodnje biogoriva, sa posebnim osvrtom na procese proizvodnje bioetanola, biogasa i biovodonika.

Ključne reči

Reference

Dach, J., Koszela, K., Boniecki, P., Zaborowicz, M., Lewicki, A., Czekała, W., Skwarcz, J., Qiao, W., Piekarska-Boniecka, H., Białobrzewski, I. (2016) The use of neural modelling to estimate the methane production from slurry fermentation processes. Renewable and Sustainable Energy Reviews, 56: 603-610
Dodić, J.M., Vučurović, D.G., Dodić, S.N., Grahovac, J.A., Popov, S.D., Nedeljković, N.M. (2012) Kinetic modelling of batch ethanol production from sugar beet raw juice. Applied Energy, 99: 192-197
Dželetović, Ž., Mihailović, N. (2011) Status, development and prospects of using bioenergy crops in the World and in Serbia. Journal on Processing and Energy in Agriculture, vol. 15, br. 2, str. 90-93
El-Shafie, A. (2014) Neural network nonlinear modeling for hydrogen production using anaerobic fermentation. Neural Computing and Applications, 24(3-4): 539-547
Fakharudin, A.S., Sulaiman, M.N., Salihon, J., Zainol, N. (2013) Implementing artificial neural networks and genetic algorithms to solve modeling and optimisation of biogas production. u: 4th International Conference on Computing and Informatics, Kuching, Sarawak, Malaysia, 121-126
Grahovac, J., Dodić, J., Jokić, A., Popov, S., Dodić, S., Vučurović, D., Grahovac, M. (2012) Neural network modelling of sugar beet juices fermentation with different starter cultures. u: The 7th Conference on Sustainable Development of Energy, Water and Environment Systems - SDEWES, Ohrid, Macedonia
Grahovac, J.A., Dodić, J.M., Dodić, S.N., Popov, S.D., Jokić, A.I., Zavargo, Z.Z. (2011) Optimisation of bioethanol production from intermediates of sugar beet processing by response surface methodology. Biomass & Bioenergy, 4290-4296; 35
Grahovac, J., Jokić, A., Dodić, J., Vučurović, D., Dodić, S. (2016) Modelling and prediction of bioethanol production from intermediates and byproduct of sugar beet processing using neural networks. Renewable Energy, 85: 953-958
Grahovac, J., Dodić, J., Jokić, A., Dodić, S., Popov, S. (2012) Optimization of ethanol production from thick juice: A response surface methodology approach. Fuel, 93: 221-228
Jain, A.K., Jianchang, M., Mohiuddin, K.M. (1996) Artificial neural networks: a tutorial. Computer, 29(3): 31-44
Jokić, A.I., Grahovac, J.A., Dodić, J.M., Dodić, S.N., Popov, S.D., Zavargo, Z.Z., Vučurović, D.G. (2012) Artificial neural network approach to modeling of alcoholic fermentation of thick juice from sugar beet processing. Hemijska industrija, vol. 66, br. 2, str. 211-221
Jokić, A.I., Grahovac, J.A., Dodić, J.M., Zavargo, Z.Z., Dodić, S.N., Popov, S.D., Vučurović, D.G. (2011) Interpreting the neural networkfor prediction of fermentation of thick juice from sugar beet processing. Acta periodica technologica, br. 42, str. 241-249
Kanat, G., Saral, A. (2009) Estimation of Biogas Production Rate in a Thermophilic UASB Reactor Using Artificial Neural Networks. Environmental Modeling & Assessment, 14(5): 607-614
Mojović, L., Pejin, D., Rakin, M., Vukašinović, M., Pejin, J., Grujić, O., Nikolić, S., Radosavljević, M. (2010) Investigations of the possibilities of stillage utilization from the bioethanol production on corn. Journal on Processing and Energy in Agriculture, vol. 14, br. 1, str. 54-57
Olsson, L. (2007) Biofuels. Berlin, Germany: Springer-Verlag
Pal, M.P., Vaidya, B.K., Desai, K.M., Joshi, R.M., Nene, S.N., Kulkarni, B.D. (2009) Media optimization for biosurfactant production by Rhodococcus erythropolis MTCC 2794: artificial intelligence versus a statistical approach. Journal of Industrial Microbiology & Biotechnology, 36(5): 747-756
Popov, S., Ranković, J., Dodić, J., Dodić, S., Jokić, A. (2010) Bioethanol production from raw juice as intermediate of sugar beet processing: A response surface methodology approach. Food Technology and Biotechnology, 376-383; 48
Pramanik, K. (2004) Use of artificial neural networks for prediction of cell mass and ethanol concentration in batch fermentation using Saccharomyces cerevisiae yeast. IE (I) Journal, CH 85, 31-35
Ranković, J., Dodić, J., Dodić, S., Popov, S. (2009) Bioethanol production from intermediate products of sugar beet processing with different types of Saccharomyces cerevisiae. Chemical Industry and Chemical Engineering Quarterly, vol. 15, br. 1, str. 13-16
Saraceno, A., Curcio, S., Calabro, V., Iorio, G. (2010) A hybrid neural approach to model batch fermentation of "ricotta cheese whey" to ethanol. Computers & Chemical Engineering, 34(10), 1590-1596
Talebnia, F., Mighani, M., Rahimnejad, M., Angelidaki, I. (2015) Ethanol production from steam exploded rapeseed straw and the process simulation using artificial neural networks. Biotechnology and Bioprocess Engineering, 20(1): 139-147
Wang, J., Wan, W. (2009) Optimization of fermentative hydrogen production process using genetic algorithm based on neural network and response surface methodology. International Journal of Hydrogen Energy, 34(1): 255-261
Whiteman, J. K., Gueguim, K.E. B. (2014) Comparative Assessment of the Artificial Neural Network and Response Surface Modelling Efficiencies for Biohydrogen Production on Sugar Cane Molasses. BioEnergy Research, 7(1): 295-305
Witek-Krowiak, A., Chojnacka, K., Podstawczyk, D., Dawiec, A., Pokomeda, K. (2014) Application of response surface methodology and artificial neural network methods in modelling and optimization of biosorption process. Bioresource Technology, 160: 150-160