Skip to the content

Adaptive neuro-fuzzy inference system for real-time monitoring of integrated constructed wetlands

Dzakpasu, M, Scholz, M, McCarthy, V, Jordan S, S and Sani, A 2015, 'Adaptive neuro-fuzzy inference system for real-time monitoring of integrated constructed wetlands' , Water Science and Technology, 71 (1) , pp. 22-30.

Full text not available from this repository. (Request a copy)

Abstract

Monitoring large-scale treatment wetlands is costly and time-consuming, but required by regulators. Some analytical results are available only after 5 days or even longer. Thus, adaptive neuro-fuzzy inference system (ANFIS) models were developed to predict the effluent concentrations of 5-day biochemical oxygen demand (BOD5) and NH4-N from a full-scale integrated constructed wetland (ICW) treating domestic wastewater. The ANFIS models were developed and validated with a 4-year data set from the ICW system. Cost-effective, quicker and easier to measure variables were selected as the possible predictors based on their goodness of correlation with the outputs. A self-organizing neural network was applied to extract the most relevant input variables from all the possible input variables. Fuzzy subtractive clustering was used to identify the architecture of the ANFIS models and to optimize fuzzy rules, overall, improving the network performance. According to the findings, ANFIS could predict the effluent quality variation quite strongly. Effluent BOD5 and NH4-N concentrations were predicted relatively accurately by other effluent water quality parameters, which can be measured within a few hours. The simulated effluent BOD5 and NH4-N concentrations well fitted the measured concentrations, which was also supported by relatively low mean squared error. Thus, ANFIS can be useful for real-time monitoring and control of ICW systems.

Item Type: Article
Themes: Built and Human Environment
Schools: Schools > School of Computing, Science and Engineering > Salford Innovation Research Centre (SIRC)
Journal or Publication Title: Water Science and Technology
Publisher: IWA Publishing
Refereed: Yes
ISSN: 0273-1223
Related URLs:
Funders: Funder not known
Depositing User: B Li
Date Deposited: 16 Mar 2015 17:02
Last Modified: 29 Oct 2015 00:18
URI: http://usir.salford.ac.uk/id/eprint/33786

Actions (login required)

Edit record (repository staff only) Edit record (repository staff only)