1st South East European Congress of Chemical Engineering , 2005-09-20

Title : ( Adaptive neural fuzzy interface system to modeling of flux and fouling during UF of skimmed milk )

Authors: , محمد خوشنودی , Nasser Saghatoleslami , Seyed Mohammad Ali Razavi ,

Citation: BibTeX | EndNote

Abstract

A neural fuzzy inference system (ANFIS) is simply a neural network- learning algorithm. The ability of ANFIS was investigated for the dynamic modeling of cross flow ultrafiltration of milk. This paper presents application of a class of hybrid neuro-fuzzy network to the solution of a nonlinear complex process. It aims to predict permeate flux and total hydraulic resistance as a function of transmembrane pressure, PH, temperature, fat, molecular weight cut off, and processing time. Dynamic modeling of ultrafiltration performance of colloidal systems (such as milk) is very important for designing of a new process and better understanding of the present process. Such processes show complex non-linear behavior due to unknown interactions between compounds of a colloidal system. The ANFIS approximation gave advantages over the other methods. The results showed that there is an excellent agreement between the checked data (not used in training) and modeled data, with average errors very low. Also the trained ANFIS is able to accurately capture the non-linear dynamics of milk ultrafiltration even for a new condition that has not been used in the training process (tested data). In addition, the results show that neural fuzzy systems are efficient in terms of better performance time and lower error rates while compared to pure neural network approach. The primary objectives are both to investigate the capability of adaptive neuro-fuzzy networks and to justify their application to predict the Jp and Rt characteristics of milk ultrafiltration. Successful implementations of neurofuzzy predictors are described and their performances are illustrated using the results obtained from adaptive neuro-fuzzy networks and showed data in figures. In this paper, ANFIS is compared to Multilayer perceptron. The results of modeling showed that the protein rejection at each value of condition is almost constant with time, but the rejection of other components has increased significantly with time. In addition, the fouling has been increased at first and then decreased with the TMP, because the membrane pores were closed. Nevertheless, the fat rejection at each value of PH is constant with time.

Keywords

, Adaptive neural fuzzy, modeling, flux, fouling, UF, skimmed milk
برای دانلود از شناسه و رمز عبور پرتال پویا استفاده کنید.

@inproceedings{paperid:1009305,
author = {, and محمد خوشنودی and Saghatoleslami, Nasser and Razavi, Seyed Mohammad Ali},
title = {Adaptive neural fuzzy interface system to modeling of flux and fouling during UF of skimmed milk},
booktitle = {1st South East European Congress of Chemical Engineering},
year = {2005},
location = {بلگراد},
keywords = {Adaptive neural fuzzy; modeling; flux; fouling; UF; skimmed milk},
}

[Download]

%0 Conference Proceedings
%T Adaptive neural fuzzy interface system to modeling of flux and fouling during UF of skimmed milk
%A ,
%A محمد خوشنودی
%A Saghatoleslami, Nasser
%A Razavi, Seyed Mohammad Ali
%J 1st South East European Congress of Chemical Engineering
%D 2005

[Download]