Development of adaptive neuro-fuzzy inference system model for predict trihalomethane formation potential in distributio

  • PDF / 800,229 Bytes
  • 13 Pages / 595.276 x 790.866 pts Page_size
  • 103 Downloads / 160 Views

DOWNLOAD

REPORT


RESEARCH ARTICLE

Development of adaptive neuro-fuzzy inference system model for predict trihalomethane formation potential in distribution network simulation test Alper Alver 1

&

Emine Baştürk 1

&

Ahmet Kılıç 1

Received: 26 July 2020 / Accepted: 23 November 2020 # Springer-Verlag GmbH Germany, part of Springer Nature 2020

Abstract Trihalomethanes (THMs), which is one of the major classes of DBP known to be highly cytotoxic and genotoxic, were formed and modeled under controlled conditions by laboratory-scale distribution network simulation test. The formation potentials of THM depending on the parameters such as natural organic matter, bromide, chlorine, pH, and contact time were determined. Subsequently, the Adaptive Neuro-Fuzzy Inference System (ANFIS) model was developed using these parameters as inputs and THM formation potentials as output, and the correlation coefficient was 0.9817. In the range of the inputs, the ANFIS model representing the simulation test results were compared with THM formations of an actual distribution network system in dry and wet seasons. As a result, the predictions of the ANFIS model were little affected by the unidentified factors that were not used in model training but are known to affect THM formations in real waters and gave more consistent results than the EPA model. Keywords Natural organic matter . Disinfection by-products . Trihalomethanes . Simulation test . Adaptive neuro-fuzzy inference system

Introduction Disinfection by-products (DBPs) are formed as a result of the reactions of the residual disinfectant with precursor substances such as natural organic matter (NOM), bromide (Br), iodine (I), and nitrite (NO2) after the disinfection process (Benson et al. 2017; Li et al. 2018). These reactions develop depending on the conditions of water tanks and pipelines, which are called the drinking water distribution network system and poses health risks for inhabitants (Hunter et al. 2010). There are two major

Responsible editor: Marcus Schulz * Alper Alver [email protected] Emine Baştürk [email protected] Ahmet Kılıç [email protected] 1

Department of Environmental Engineering, Engineering Faculty, Science Institute, Aksaray University, 68100 Aksaray, Turkey

classes of DBPs: trihalomethanes (THMs) and haloacetic acids (HAAs) (Bond et al. 2012; Gopal et al. 2007). Since THMs are carcinogenic and have adverse effects on the liver, kidney, and digestive systems, the maximum pollutant level is determined as 100 and 80 μg/L by the World Health Organization (WHO) and the US Environmental Protection Organization (USEPA), respectively (Ding et al. 2019; Zainudin et al. 2018; Zhang et al. 2018). It is necessary to know the effects that limit the formation of THMs to control them (Hu et al. 2018). For this reason, laboratory studies that simulate distribution network conditions are carried out. In this way, the behavior of the reactants under different conditions can be determined, and prevention can be taken (Chen and Westerhoff 2010). The characterization of natural