Premium
Mathematical and Artificial Neural Network Models to Predict the Membrane Fouling Behavior of an Intermittently‐Aerated Membrane Bioreactor Under Sub‐Critical Flux
Author(s) -
Wang Zuowei,
Wu Xiaohui
Publication year - 2015
Publication title -
clean – soil, air, water
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.444
H-Index - 66
eISSN - 1863-0669
pISSN - 1863-0650
DOI - 10.1002/clen.201400116
Subject(s) - fouling , artificial neural network , membrane fouling , filtration (mathematics) , flux (metallurgy) , membrane bioreactor , mathematical model , aeration , biological system , engineering , computer science , mathematics , environmental engineering , membrane , materials science , chemistry , artificial intelligence , wastewater , waste management , statistics , biochemistry , metallurgy , biology
This study established a mathematical model and an artificial neural network (ANN) model based on the theory of critical flux filtration to predict the membrane module fouling performance of an intermittently aerated membrane bioreactor (IAMBR) while simultaneously conducting a prediction performance evaluation of the two models. The key parameters of the mathematical model, such as constant rate, fouling propensity, and others, were determined by a short‐term step‐flux experiment and a long‐term filtration experiment. The transmembrane pressure jump point ( t sus ) of the long‐term filtration under sub‐critical flux was calculated using the key parameters. An ANN model was also established based on the critical flux theory and the initial weights of the network model were optimized using a genetic algorithm, which accelerated the convergence of the model. The evaluation results indicated that the ANN model had a better simulation performance under the intermittently aerated mode, but the mathematical model predicted t sus more steadily. Therefore, a more in‐depth investigation is required to obtain an elaborate evaluation of those two models.