Vol. 7, No 1, 2009 pp. 23 - 31
DOI 10.2298/FUPCT0901023R
UDC 591.481
MODELLING OF THE FILTER-ADSORBER TYPE
AIR CLEANER BY USING NEURAL NETWORK
Miomir Raos1, Ljiljana Živković1,
Amelija Đorđević1, Branislav Todorović2
1Faculty of Occupational Safety, University
of Niš, Serbia
2Faculty of Science and Mathematics,
University of Niš, Serbia
Abstract. It is well known that most air purifying methods imply
the passing of air flow, as a pollutant carrier, through a control unit
which retains impurities.
Properties of the air control unit and the purifying process itself
therefore differ depending on the nature of present impurities, as well
as on flow-thermal properties of air as the carrier of those impurities.
For the assumed conditions, in terms of production of a pollution source
and presence of different polluting substances in the form of dust, aerosols,
gas, vapor in the exhaust gas, etc., an integrated gas purifier has been
designed and tested, comprising a module for purification of mechanical
impurities and a module for purification of gaseous impurities.
The purifier is compact and has a universal application while simultaneously
retaining several different pollutants. These requirements were met through
application of the filtration and adsorption methods. On the formed experimental
line with an adequate system of acquisition, filter-adsorber type gas cleaners
in the function of flow-thermal parameters of gas mixture were tested simultaneously.
Experimental data were used for training the radial basis function neural
network, which was then used to model properties of the process and gas
cleaner.
Key words: flow-thermal parameters, air purification,
modelling, neural network
MODELIRANJE KARAKTERISTIKA PREČISTAČA
GASOVA
TIPA FILTER-ADSORBER NEURONSKOM MREŽOM
Poznato je da većina metoda prečišćavanja gasova podrazumeva prolazak
struje gasa kao nosioca zagađenja kroz neki prečistač koji vrši zadržavanje
nečistoća. Karakteristike prečistača i samog procesa prečišćavanja
se zato razlikuju zavisno od vrste i prirode prisutnih nečistoća kao
i od strujno termičkih osobina vazduha kao nosioca tih nečistoća. Za
predpostavljene uslove, u smislu produkcije izvora emisije, prisustva različitih
zagađujućih supstanci u obliku prašine, aerosola, gasova i para u otpadnom
gasu, itd., koncipiran je i ispitivan integrisani prečistač gasova koji
se sastoji iz modula za prečišćavanje mehaničkih nečistoća i modula
za prečišćavanje gasovitih nečistoća. Prečistač je kompaktan, i
ima univerzalnu primenu uz istovremeno zadržavanje više različitih zagađujućih
materija. Realizacija ovih zahteva ostvarena je primenom metoda filtracije
i adsorpcije. Na formiranoj eksperimentalnoj liniji sa odgovarajućim sistemom
akvizicije, simultano su izvršena ispitivanja prečistača gasova tipa
filter-adsorber u funkciji strujno termičkih parametara gasne smeše.
Eksperimentalno dobijeni podaci, iskorišćeni su za obučavanje neuronske
mreže radijalnih bazisnih funkcija, kojom je izvršeno modeliranje karakteristika
prečistača i procesa.
