No description available.

A proprietary technology owned by Texas A

A proprietary technology owned by Texas A

<p>Fokus ove doktorske disertacije je razvijanje modela<br />zasnovanog na konceptu ve&scaron;tačkih neuronskih mreža<br />za predviđanje i projektovanje mikrofiltracije<br />kultivacionih tečnosti preko ispitivanja mogućnosti<br />primene ovog koncepta za modelovanje fluksa<br />permeata pri različitim uslovim a mikrofiltracij e, u<br />sistemima sa i bez primene hidrodinamičkih metoda<br />pobolj&scaron;anja fluksa permeata i njihove kombinacije,<br />kao i razvoj modela kojim će se objediniti<br />eksperimentalni rezultati u cilju dobijanja jedne<br />jedinstvene neuronske mreže za simulaciju svih<br />metoda pobolj&scaron;anja fluksa. Dodatan cilj predstavlja<br />razvoj modela za procenu pobolj&scaron;anja fluksa u<br />stacionarnim uslovim a usled primene metoda<br />pobolj&scaron;anja fluksa permeata čija će se adekvatnost<br />proveriti sa energetskog stanovi&scaron;ta.<br />Eksperimentalna ispitivanja su obuhvatila razvoj i<br />validaciju deset različitih modela neuronskih mreža<br />kod kojih su nezavisne ulazne promenljive i njihovi<br />rasponi (transmembranski pritisak, protok suspenzije<br />i protok vazduha) utvrđeni Box-Behnken-ovim<br />eksperimentalnim planom uz dodatne parametre<br />vreme trajanja mikrofiltracije i temperature koji su<br />varirani u zavisnosti od uslova izvođenja postupka<br />mikrofiltracije. Nasuprot tome, za razvoj dinamičkog<br />modela u svojstvu zavisno promenljive veličine<br />razmatran je pad fluksa permeata sa vremenom, dok<br />je za razvoj modela procene efikasnosti primenjenih<br />metoda pobolj&scaron;anja fluksa permeata razmatran fluks i<br />specifična potro&scaron;nja energije u stacionarnim<br />uslovima.<br />Normalizacijom eksperimentalnih podataka izbegla<br />se velika razlika u specifičnim težinskim<br />koeficijentim a pojedinih ulaznih promenljivih i predupredila opasnost da te promenljive pokažu veći<br />uticaj nego &scaron;to ga imaju u realnosti, a balansiranje<br />efekata nekontrolisanih faktora na izlaznu<br />promenljivu izvedeno je randomizacijom na grupu za<br />obučavanje (70% podataka), grupu za validaciju<br />(15% podataka) i grupu za testiranje (15% podataka).<br />Nestacionarnosti koje utiču na efikasnost algoritma<br />obuke i arhitekture neuronskih mreža izbegnute su<br />ispitivanjem m odela sa pet algoritama obuke<br />(Levenberg-M arkuardt-ov algoritam obuke<br />(trainlm), Bayes-ova regularizacija (trainbr), model<br />rezilientnog povratnog prostiranja (trainrp), model<br />skaliranog konjugovanog gradijenta (trainscg) i<br />model jednostepenog sekantnog povratnog<br />prostiranja gre&scaron;ke unazad (trainoss)) i dve<br />sigmoidalne aktivacione funkcije u skrivenom sloju<br />(logistička i hiperbolična tangensna), dok je u<br />izlaznom sloju kori&scaron;ćena linearna aktivaciona<br />funkcija. Svi modeli su optimizovani primenom<br />metode probe i gre&scaron;ke sa osnovnim ciljem dobiti &scaron;to<br />jednostavniju mrežu, odnosno mrežu sa minimalnim<br />brojem skrivenih neurona koja pokazuje najbolju<br />sposobnost generalizacije. Kao indikatori nivoa<br />generalizacije i parametara učinka obuke neuronske<br />mreže ispitivani su koeficijent determinacije (R2) i<br />srednja kvadratna gre&scaron;ka (MSE), a koeficijent<br />korelacije (r) je odabran kao dodatni parametar<br />adekvatnosti fitovanja vrednosti utvrđenog i<br />neuronskom mrežom procenjenog fluksa permeata.<br />Najbolju sposobnost generalizacije i predikcije<br />pokazao je model neuronske mreže obučavan<br />Levenberg-M arkuardt-ovim algoritmom. Optimalan<br />broj neurona u skrivenom sloju se kretao od 7 do 13<br />&scaron;to ukazuje na znatnu kom pleksnost mehanizama<br />koji utiču na fluks permeata kako je i procenjeno<br />postavljanjem hipoteze ove doktorske disertacije.<br />Analiza apsolutne relativne gre&scaron;ke pokazala je veoma<br />dobro predviđanje po&scaron;to je u rasponu od 81% do<br />100 % podataka imalo gre&scaron;ku manju od 10%, a<br />koeficijent determinacije u rasponu od 0,98091 do<br />0,99976 ukazuje da mreža ne može da objasni manje<br />od 2% varijacija u sistemu. Vrednosti koeficijenta<br />korelacije se kreću u rasponu od 0,99041 do 0,99988<br />&scaron;to sugeri&scaron;e na dobru linearnu korelaciju između<br />eksperimentalnih podataka i podataka predviđenih<br />neuronskom mrežom. Pored primene koncepta<br />fitovanja podataka ispitana je i mogućnost procene<br />uticaja pojedinih eksperimentalnih promenljivih na<br />fluks permeata primenom jednačine Garsona, a<br />komparativnom analizom dobijenih simulacionih rezultata na eksperimentalim podacima koji nisu bili predstavljeni neuronskoj mreži potvrđen je<br />generalizacijski kapacitet modela neuronske mreže.</p> / <p>Focus of this doctoral dissertation is to develop<br />a model based on the artificial neural networks<br />concept for predicting and designing cultivation<br />broth microfiltration by examining the<br />feasibility of this concept for modeling<br />permeate flux under different microfiltration<br />conditions, in systems with and without<br />hydrodynamic im provem ent methods, as well<br />the development of a model that will combine<br />the experimental results in order to obtain a<br />single neural network to simulate all methods of<br />flux improvement. An additional goal is the<br />development of a model in quasi steady state in<br />term so fadequacy of flux enhancement methods<br />application, which will be checked from the<br />energy point of view.<br />Experimental tests included the development<br />and validation of ten different models оf neural<br />networks in which the independent input<br />variables and their ranges (transmembrane<br />pressure, suspension flow and air flow) were<br />determined by Box-Behnken&#39;s experimental<br />plan with added microfiltration parameters time<br />and temperature, varied depending on the<br />conditions of the microfiltration procedure. In<br />contrast, for the development оf a dynamic<br />model as a dependent variable, the decrease in<br />permeate flux with time was considered, while<br />for the development of a model for evaluating<br />the efficiency оf applied permeate flux<br />im provement methods, flux and specific energy<br />consumption in quasi steady state conditions<br />were considered.<br />Normalization of experimental data avoided a<br />large difference in specific weight coefficients of individual input variables and prevented the<br />danger that these variables show a greater<br />impact than they have in reality, and balancing<br />the effects of uncontrolled factors on the output<br />variable was performed by randomization on the<br />training group (70% o f data), a validation group<br />(15% of data) and a testing group (15% of data).<br />Non-stationarities affecting the efficiency of the<br />training algorithm and neural network<br />architecture were avoided by testing the model<br />with five diferent training algorithms<br />(Levenberg-M arquardt training algorithm<br />(trainlm), Bayesian regularization (trainbr),<br />resilient backpropagation algorithm (trainrp),<br />scaled conjugate gradient method (trainscg) and<br />a one-step secant m ethod (trainoss)) and two<br />sigmoid activation functions in the hidden layer<br />(logistic and hyperbolic tangent), while a linear<br />activation function was used in the output layer.<br />All models are optimized by applying the trial<br />and error method with the basic goal of having<br />the simplest possible network, ie a network with<br />a minimum num ber o f hidden neurons that<br />shows the best ability to generalize.<br />Determ ination coefficient (R2) and mean square<br />error (MSE) were examined as indicators of<br />generalization level and neural network training<br />performance parameters, and correlation<br />coefficient (r) was selected as an additional<br />param eter o f adequacy оf fitting the value of<br />determined and neural network estimated<br />permeate flux.<br />The best ability to generalize and predict was<br />shown by a model of a neural network trained<br />by the Levenberg-M arquardt algorithm. The<br />optimal num ber of neurons in the hidden layer<br />ranged from 7 to 13, which indicates a<br />significant complexity of the mechanisms that<br />affect the permeate flux, as assessed by the<br />hypothesis of this doctoral dissertation.<br />Absolute relative error analysis showed very<br />good prediction as in the range of 81% to 100 %<br />of the data had an error of less than 10 %, and<br />the coefficient of determination in the range of<br />0.98091 to 0.99976 indicates that the network<br />cannot explain less than 2 % variation in the<br />system. The values оf the correlation coefficient<br />range from 0.99041 to 0.99988 suggests a good<br />linear correlation between the experimental data<br />and the data predicted by the neural network. In addition to the application of the concept of data<br />fitting, the relative importance of input variables<br />was also investigated by applying the Garson<br />equation. Comparative analysis of the obtained<br />simulation results on experimental data that<br />were not presented to the neural network<br />confirmed the generalization capacity of the<br />neural network model.</p>

Le couplage fonctionnel des opérations de séparation et de réaction ainsi que les bio-procédés sont deux axes de recherche largement explorés. Cependant, l’industrie du génie des procédés a du mal à se tourner vers des technologies de ce type car il demeure un réel manque de connaissances et d’outils de conception pour ce genre de procédés. Une méthodologie de conception générale pour l'extraction liquide-liquide réactive est introduite dans cette étude. Elle est composée de trois étapes différentes: l'analyse de faisabilité, la synthèse ou dimensionnement du procédé et la validation par simulation. Cette méthodologie conduit à des paramètres structuraux et opératoires de la colonne étudiée à partir seulement des informations concernant le comportement physico-chimique du système étudié, en exploitant les équations d’équilibre chimique et entre phase ainsi que les bilans matières. Les résultats de cette méthode sont un bon point de départ pour une étude d'optimisation ou d'un processus de calcul d'investissement. Cette méthodologie a été appliquée à différentes études de cas: regroupant deux stratégies différentes d'extraction avec plusieurs solvants pour récupérer l'acide succinique dans un milieu de fermentation / The functional coupling of separation and reaction operations and bioprocesses are two widely explored areas of research. However, process engineering industry is struggling to turn to these technologies because it remains a real lack of knowledge and design tools for this kind of processes. A general design methodology for reactive liquid-liquid extraction is introduced in this study. It is composed of three different steps: feasibility analysis, pre-design determination and simulation validation. This methodology leads to the design specifications of the units from the information concerning the physicochemical behaviour of the studied system, exploiting the equilibrium and material balance equations. The results of this methodology are a good starting point for an optimization study or for an investment calculation process. This methodology has been applied to different case studies: two different strategies of extraction and several solvents to recover succinic acid in fermentation broth.