Predicting the Quality of Treated Water from an Activated Carbon Based Water Purifier Using Artificial Neural Network

Article type: Research Article

Authors: Roy, Ritabrata^{; *}

Affiliations: Hydro-Informatics Engineering (under Civil Engineering Dept), National Institute of Technology Agartala, Barjala, Jirania, Tripura (W) – 799046, India

Correspondence: [*] Corresponding Author. [email protected]

Abstract: Automated water purifier is a convenient and widely used device for obtaining purified water. However, performance of a system may vary over time and therefore monitoring of the treated water is essential for ensuring the quality control. In this study, a number of input and output samples of an activated carbon based water purifying system were monitored to check its efficiency. Overall quality of the inflow and outflow of the purifying system were assessed by Weighted Arithmetic Water Quality Index with ideal permissible limits of the water quality parameters as per Indian Council of Medical Research guidelines. Results indicate that the quality of the water enhanced significantly after purification. A model was developed from the water quality data with Artificial Neural Network to predict the quality of the water, treated by the purifier. The model was tested with more water quality data and found to be successful in prediction of the overall quality of the treated water fairly accurately.

Keywords: Water quality, water purification, water quality index, activated carbon, artificial neural network

DOI: 10.3233/AJW190041

Journal: Asian Journal of Water, Environment and Pollution, vol. 16, no. 3, pp. 125-128, 2019