Coagulant Dosage Determination in a Water Treatment Plant Using Dynamic Neural Network Models

2015 ◽  
Vol 14 (03) ◽  
pp. 1550013 ◽  
Author(s):  
Leonaldo Silva Gomes ◽  
Francisco Alexandre A. Souza ◽  
Ricardo Silva Thé Pontes ◽  
Tobias R. Fernandes Neto ◽  
Rui Alexandre M. Araújo
Keyword(s):  
Neural Network ◽  
Water Treatment ◽  
Treatment Plant ◽  
Network Models ◽  
Water Treatment Plant ◽  
Raw Water ◽  
Neural Network Models ◽  
Dynamic Neural Network ◽  
Input Variables

A common step in most of water treatment plants is the chemical coagulation. The chemical coagulation is the process of destabilizing the colloidal particles suspended in raw water by the addition of coagulants. Generally, the determination of the quantity of coagulant to be added to water is made manually by jar tests. However, the manual control has slow response to changes of raw water and it requires intensive laboratory analysis. To reduce the manual effort and to improve the response to change in raw water quality, this work proposes the determination of the coagulant dosage using dynamic neural network modeling using the available sensors as input of the model. The case of study is a large scale water treatment plant in Ceará, Brazil, where the kinds of coagulants added to water are the aluminum sulphate (AS) and poly aluminum chloride (PAC). Several dynamic neural network models with different combinations of the input variables have been evaluated. The best solution found is composed by a nonlinear autoregressive with exogenous input (NARX) model having three input variables, the pH in raw and coagulated water, and the turbidity in the coagulated water, with coefficient of determination of R2 = 0.95 and R2 = 0.91 for the AS and PAC dosage prediction, respectively.

scholarly journals Intelligent system for improving dosage control

2017 ◽  
Vol 39 (1) ◽  
pp. 33 ◽  
Author(s):  
Fabio Cosme Rodrigues dos Santos ◽  
André Felipe Henriques Librantz ◽  
Cleber Gustavo Dias ◽  
Sheila Gozzo Rodrigues
Keyword(s):  
Neural Network ◽  
Water Treatment ◽  
Intelligent System ◽  
Treatment Plant ◽  
Drinking Water Treatment ◽  
Water Treatment Plant ◽  
Test Method ◽  
Raw Water ◽  
Water Turbidity ◽  
Coagulant Dosage

Coagulation is one of the most important processes in a drinking-water treatment plant, and it is applied to destabilize impurities in water for the subsequent flocculation stage. Several techniques are currently used in the water industry to determine the best dosage of the coagulant, such as the jar-test method, zeta potential measurements, artificial intelligence methods, comprising neural networks, fuzzy and expert systems, and the combination of the above-mentioned techniques to help operators and engineers in the water treatment process. Current paper presents an artificial neural network approach to evaluate optimum coagulant dosage for various scenarios in raw water quality, using parameters such as raw water color, raw water turbidity, clarified and filtered water turbidity and a calculated Dose Rate to provide the best performance in the filtration process. Another feature in current approach is the use of a backpropagation neural network method to estimate the best coagulant dosage simultaneously at two points of the water treatment plant. Simulation results were compared to the current dosage rate and showed that the proposed system may reduce costs of raw material in water treatment plant. 

Application of artificial neural network to control the coagulant dosing in water treatment plant

2000 ◽  
Vol 42 (3-4) ◽  
pp. 403-408 ◽  
Author(s):  
R.-F. Yu ◽  
S.-F. Kang ◽  
S.-L. Liaw ◽  
M.-c. Chen
Keyword(s):  
Neural Network ◽  
Time Series ◽  
Artificial Neural Network ◽  
Water Treatment ◽  
Regression Model ◽  
Treatment Plant ◽  
Water Treatment Plant ◽  
Ann Model ◽  
Coagulant Dosage ◽  
Ann Models

Coagulant dosing is one of the major operation costs in water treatment plant, and conventional control of this process for most plants is generally determined by the jar test. However, this method can only provide periodic information and is difficult to apply to automatic control. This paper presents the feasibility of applying artificial neural network (ANN) to automatically control the coagulant dosing in water treatment plant. Five on-line monitoring variables including turbidity (NTUin), pH (pHin) and conductivity (Conin) in raw water, effluent turbidity (NTUout) of settling tank, and alum dosage (Dos) were used to build the coagulant dosing prediction model. Three methods including regression model, time series model and ANN models were used to predict alum dosage. According to the result of this study, the regression model performed a poor prediction on coagulant dosage. Both time-series and ANN models performed precise prediction results of dosage. The ANN model with ahead coagulant dosage performed the best prediction of alum dosage with a R2 of 0.97 (RMS=0.016), very low average predicted error of 0.75 mg/L of alum were also found in the ANN model. Consequently, the application of ANN model to control the coagulant dosing is feasible in water treatment.

Neural Network-Based Stock Market Return Forecasting Using Data Mining for Variable Reduction

2008 ◽  
pp. 2476-2493 ◽  
Author(s):  
David Encke
Keyword(s):  
Neural Network ◽  
Information Gain ◽  
Network Models ◽  
Linear Regression Models ◽  
Market Returns ◽  
Neural Network Models ◽  
The Neural Network ◽  
Variable Reduction ◽  
Input Variables ◽  
Using Data

Researchers have known for some time that nonlinearity exists in the financial markets and that neural networks can be used to forecast market returns. Unfortunately, many of these studies fail to consider alternative forecasting techniques, or the relevance of the input variables. The following research utilizes an information-gain technique from machine learning to evaluate the predictive relationships of numerous financial and economic input variables. Neural network models for level estimation and classification are then examined for their ability to provide an effective forecast of future values. A cross-validation technique is also employed to improve the generalization ability of the models. The results show that the classification models generate higher accuracy in forecasting ability than the buy-and-hold strategy, as well as those guided by the level-estimation-based forecasts of the neural network and benchmark linear regression models.

Sign in / Sign up

Export Citation Format

Share Document