Predicting total trihalomethane formation in finished water using artificial neural networks

Abstract

This paper reports on the application of artificial neural network (ANN) techniques for predicting the concentration of trihalomethanes (THMs) in finished water at the E.L. Smith Water Treatment Plant (WTP) in Edmonton, Alberta, Canada. The formation of THMs in finished water involves many complex chemical reactions and interactions that are difficult to model using conventional methods. The formation of THMs has been found to be correlated to raw and treated water quality characteristics such as colour, pH, and temperature and chemical addition such as chlorine, alum, and powder activated carbon (PAC). Three models were derived using raw water, post clarification water, and a combination of raw and post clarification water parameter inputs. The model that most successfully predicted the concentration of THMs in finished water is the model that uses clarifier effluent parameter inputs. This model can be used at the E.L. Smith WTP for early detection of potentially high THM concentrations in finished water and gives plant operators enough advanced warning to reduce THM precursors. With an adequate understanding of water treatment plant processes and THM formation potential it will be fairly easy for any water treatment facility, which has a few years of historical plant data, to develop its own ANN model for predicting the formation of THM in finished water. Key words: artificial neural networks, water treatment process, water treatment modeling, trihalomethane formation.

Artificial neural network real‐time process control system for small utilities

“…For the hidden layer design, the authors compared many structures through a systematic factorial selection approach. This approach was discussed in detail by Zhang et al (2004) and in the project report for AwwaRF. The authors would like to point out that water treatment process data tend to have lots of noisy data.…”

“…The ANN model is created with a systematic ANN‐modeling approach to map the relationship between process input and output variables. The recent successful applications of ANNs in the water industry include water demand and consumption forecasting (Zhang et al, 2004a), ANN direct process control (Shariff et al, 2004a; Baxter et al, 2002), modeling of coagulant dosage (Maier et al, 2004; Gagnon et al, 1997), modeling of lime softening dosage (Shariff et al, 2004), modeling of filtration performance (Tupas et al, 2000), chlorination and trihalomethane (THM) dosage and control (Rodriguez & Serodes, 2004; Lewin et al, 2004), and water quality prediction (Bowden et al, 2005; Zhang et al, 2004). ANN has become a modeling technique of choice for the water industry.…”

“…Reports are free and available to AwwaRF subscribers by calling 303-347-6121 or from www.awwarf.org. Serodes, 2004;Lewin et al, 2004), and water quality prediction (Bowden et al, 2005;Zhang et al, 2004). ANN has become a modeling technique of choice for the water industry.…”

Coagulation modeling using artificial neural networks to predict both turbidity and DOM-PARAFAC component removal

“…In recent years, artificial neural networks (ANN) have emerged as a viable method for modeling complex water treatment processes [1][2][3][4][5][6]. ANN offers several advantages over traditional modeling approaches (e.g.…”