Modeling water flux in osmotic membrane bioreactor by adaptive network-based fuzzy inference system and artificial neural network

Ahmad Hosseinzadeh; John L Zhou; Ali Altaee; Mansour Baziar; Xiaowei Li

doi:10.1016/j.biortech.2020.123391

Modeling water flux in osmotic membrane bioreactor by adaptive network-based fuzzy inference system and artificial neural network

Bioresour Technol. 2020 Aug:310:123391. doi: 10.1016/j.biortech.2020.123391. Epub 2020 Apr 18.

Authors

Ahmad Hosseinzadeh¹, John L Zhou², Ali Altaee¹, Mansour Baziar³, Xiaowei Li⁴

Affiliations

¹ Centre for Green Technology, School of Civil and Environmental Engineering, University of Technology Sydney, NSW 2007, Australia.
² Centre for Green Technology, School of Civil and Environmental Engineering, University of Technology Sydney, NSW 2007, Australia. Electronic address: Junliang.zhou@uts.edu.au.
³ Ferdows School of Paramedical and Health, Birjand University of Medical Sciences, Birjand, Iran.
⁴ School of Environmental and Chemical Engineering, Organic Compound Pollution Control Engineering, Ministry of Education, Institute for the Conservation of Cultural Heritage, Shanghai University, Shanghai 200444, PR China.

PMID: 32344239
DOI: 10.1016/j.biortech.2020.123391

Abstract

Osmotic Membrane Bioreactor (OMBR) is an emerging technology for wastewater treatment with membrane fouling as a major challenge. This study aims to develop Adaptive Network-based Fuzzy Inference System (ANFIS) and Artificial Neural Network (ANN) models in simulating and predicting water flux in OMBR. Mixed liquor suspended solid (MLSS), electrical conductivity (EC) and dissolved oxygen (DO) were used as model inputs. Good prediction was demonstrated by both ANFIS models with R² of 0.9755 and 0.9861, and ANN models with R² of 0.9404 and 0.9817, for thin film composite (TFC) and cellulose triacetate (CTA) membranes, respectively. The root mean square error for TFC (0.2527) and CTA (0.1230) in ANFIS models was lower than in ANN models at 0.4049 and 0.1449. Sensitivity analysis showed that EC was the most important factor for both TFC and CTA membranes in ANN models, while EC (TFC) and MLSS (CTA) are key parameters in ANFIS models.

Keywords: ANFIS; ANN; Membrane process; Modeling; OMBR; Water flux.

MeSH terms

Bioreactors
Fuzzy Logic
Membranes, Artificial
Neural Networks, Computer*
Osmosis
Wastewater
Water*

Substances

Membranes, Artificial
Waste Water
Water