MODELING PROCESS DYNAMICS USING A NOVEL NEURAL NETWORK
ARCHITECTURE: APPLICATION TO STIRRED CELL MICROFILTRATION

J 2010

MODELING PROCESS DYNAMICS USING A NOVEL NEURAL NETWORK ARCHITECTURE: APPLICATION TO STIRRED CELL MICROFILTRATION

MHURCHU, Jenny Ni; Greg FOLEY a Josef HAVEL

Základní údaje

Originální název

MODELING PROCESS DYNAMICS USING A NOVEL NEURAL NETWORK ARCHITECTURE: APPLICATION TO STIRRED CELL MICROFILTRATION

Autoři

MHURCHU, Jenny Ni; Greg FOLEY a Josef HAVEL

Vydání

CHEMICAL ENGINEERING COMMUNICATIONS, TAYLOR & FRANCIS INC, 2010, 0098-6445

Další údaje

Jazyk

angličtina

Typ výsledku

Článek v odborném periodiku

Obor

10400 1.4 Chemical sciences

Stát vydavatele

Spojené státy

Utajení

není předmětem státního či obchodního tajemství

Odkazy

URL

Impakt faktor

Impact factor: 0.913

Označené pro přenos do RIV

Ano

Organizační jednotka

Přírodovědecká fakulta

Klíčová slova anglicky

Artificial neural network; Dynamic modeling; Flux; Fouling; Stirred cell microfiltration

Štítky

rivok

Příznaky

Mezinárodní význam, Recenzováno

Změněno: 20. 8. 2020 11:18, Mgr. Marie Novosadová Šípková, DiS.

Anotace

V originále

A novel neural network architecture is presented for dynamic process modeling, using stirred cell microfiltration of bentonite suspensions as a model system. Unlike previous studies that include time explicitly as a network input and have a single output at that time, the network architecture presented contains the process variables as inputs and many outputs representing the output (filtrate flux in this case) at different selected times. The network is shown to represent the stirred cell microfiltration of bentonite suspensions over a range of pressures (0.2-1.5bar), initial concentrations (0.5-2.0g/L), stirrer tip speeds (0.04-0.17m/s), membrane resistances (3.09x1010-6.85x1010m-1), pH values (2.5-10.4), and temperatures (20 degrees-24 degrees C) with good accuracy (R2=0.91 on network test data). With this network architecture, it becomes easy to track the time dependence of the relative effect of the various process parameters on the system output. Thus, for example, the network weights show that the effect of stirring rate on flux increases as time progresses, while the opposite effect is seen for membrane resistance, as expected.

Citovat

MHURCHU, Jenny Ni; Greg FOLEY a Josef HAVEL. MODELING PROCESS DYNAMICS USING A NOVEL NEURAL NETWORK ARCHITECTURE: APPLICATION TO STIRRED CELL MICROFILTRATION. CHEMICAL ENGINEERING COMMUNICATIONS. TAYLOR & FRANCIS INC, 2010, roč. 197, č. 8, s. 1152-1162. ISSN 0098-6445. Dostupné z: https://doi.org/10.1080/00986440903359442.

@article{1674848,
   author = {Mhurchu, Jenny Ni and Foley, Greg and Havel, Josef},
   article_number = {8},
   doi = {https://doi.org/10.1080/00986440903359442},
   keywords = {Artificial neural network; Dynamic modeling; Flux; Fouling; Stirred cell microfiltration},
   language = {eng},
   issn = {0098-6445},
   journal = {CHEMICAL ENGINEERING COMMUNICATIONS},
   title = {MODELING PROCESS DYNAMICS USING A NOVEL NEURAL NETWORK ARCHITECTURE: APPLICATION TO STIRRED CELL MICROFILTRATION},
   url = {https://doi.org/10.1080/00986440903359442},
   volume = {197},
   year = {2010}
}

TY  - JOUR
ID  - 1674848
AU  - Mhurchu, Jenny Ni - Foley, Greg - Havel, Josef
PY  - 2010
TI  - MODELING PROCESS DYNAMICS USING A NOVEL NEURAL NETWORK ARCHITECTURE: APPLICATION TO STIRRED CELL MICROFILTRATION
JF  - CHEMICAL ENGINEERING COMMUNICATIONS
VL  - 197
IS  - 8
SP  - 1152-1162
EP  - 1152-1162
PB  - TAYLOR & FRANCIS INC
SN  - 00986445
KW  - Artificial neural network
KW  - Dynamic modeling
KW  - Flux
KW  - Fouling
KW  - Stirred cell microfiltration
UR  - https://doi.org/10.1080/00986440903359442
L2  - https://doi.org/10.1080/00986440903359442
N2  - A novel neural network architecture is presented for dynamic process modeling, using stirred cell microfiltration of bentonite suspensions as a model system. Unlike previous studies that include time explicitly as a network input and have a single output at that time, the network architecture presented contains the process variables as inputs and many outputs representing the output (filtrate flux in this case) at different selected times. The network is shown to represent the stirred cell microfiltration of bentonite suspensions over a range of pressures (0.2-1.5bar), initial concentrations (0.5-2.0g/L), stirrer tip speeds (0.04-0.17m/s), membrane resistances (3.09x1010-6.85x1010m-1), pH values (2.5-10.4), and temperatures (20 degrees-24 degrees C) with good accuracy (R2=0.91 on network test data). With this network architecture, it becomes easy to track the time dependence of the relative effect of the various process parameters on the system output. Thus, for example, the network weights show that the effect of stirring rate on flux increases as time progresses, while the opposite effect is seen for membrane resistance, as expected.
ER  -

MHURCHU, Jenny Ni; Greg FOLEY a Josef HAVEL. MODELING PROCESS DYNAMICS USING A NOVEL NEURAL NETWORK ARCHITECTURE: APPLICATION TO STIRRED CELL MICROFILTRATION. \textit{CHEMICAL ENGINEERING COMMUNICATIONS}. TAYLOR \&{} FRANCIS INC, 2010, roč.~197, č.~8, s.~1152-1162. ISSN~0098-6445. Dostupné z: https://doi.org/10.1080/00986440903359442.

Přehled o publikaci