Prediction of membrane fouling using artificial neural networks for wastewater treated by membrane bioreactor technologies: bottlenecks and possibilities

Abstract

Membrane fouling is a major concern for the optimization of membrane bioreactor (MBR) technologies. Numerous studies have been led in the field of membrane fouling control in order to assess with precision the fouling mechanisms which affect membrane resistance to filtration, such as the wastewater characteristics, the mixed liquor constituents, or the operational conditions, for example. Worldwide applications of MBRs in wastewater treatment plants treating all kinds of influents require new methods to predict membrane fouling and thus optimize operating MBRs. That is why new models capable of simulating membrane fouling phenomenon were progressively developed, using mainly a mathematical or numerical approach. Faced with the limits of such models, artificial neural networks (ANNs) were progressively considered to predict membrane fouling in MBRs and showed great potential. This review summarizes fouling control methods used in MBRs and models built in order to predict membrane fouling. A critical study of the application of ANNs in the prediction of membrane fouling in MBRs was carried out with the aim of presenting the bottlenecks associated with this method and the possibilities for further investigation on the subject.

Modelling and optimization of membrane process for removal of biologics (pathogens) from water and wastewater: Current perspectives and challenges

“…Alternatively, a data-driven modelling technique can utilize extensive datasets derived from contemporary monitoring systems, employing advanced statistical inference analysis. The use of modelling techniques such as linear regression, artificial neural networks (ANN), and random forest (RF) regression has been documented in environmental research focusing on membrane technology and water/wastewater treatment [ 119 , 121 ].…”

Permeate Flux Control in SMBR System by Using Neural Network Internal Model Control

“…The RBFNN has the advantages of adaptation capability, robust ability, learning stage without any iteration of updating weights, and very fast learning process [17]. It is widely used in variety of applications and effectively solved many control problems [17][18][19]. In addition, its structure is simple and more important is able to approximate any nonlinear function [19].…”

Data Authorization and Forecasting by a Proactive Soft Sensing Tool–Anammox Based Process

“…In certain cases where online sensors are not employed, variables related to product quality are determined by offline sample analyses in a lab-scale, thus introducing significant discontinuity and delays . To mitigate these shortfalls, SSs in combination with the smart controls have been developed to estimate the primary variables based on other easily measured variables. , Recently, soft-computing models, including genetic algorithms, ANNs, fuzzy logic, and adaptive-network-based fuzzy inference systems, have experienced increasing attention and popularity in modeling of biological wastewater treatment (BWWT) processes. − Apart from the techniques mentioned above, neural networks (NNs) are among the best-known black-box predictors. Black-box programming such as the extended form of the Kalman filter and ANNs are more favored for the development of SSs because of the ease with which they can describe complicated BWWT processes , compared to mechanistic methods.…”