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

Yu, Ruey-Fang; Kang, Shyh‐Fang; Liaw, Shu Liang; Chen, M.-c.

doi:10.2166/wst.2000.0410

Cited by 32 publications

(14 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…In a comparative study of different modeling approaches, Yu et al [84] used raw water pH, conductivity, and turbidity as well as settled water turbidity from a waterworks in Taiwan as input variables and coagulant dosage as the output parameter in order to build the respective models. They found that their ANN model gave better predictions than regression or time series methods.…”

Section: Artificial Neural Network Models (Ann)mentioning

confidence: 99%

State of the Art of Online Monitoring and Control of the Coagulation Process

Ratnaweera

Fettig

2015

Water

View full text Add to dashboard Cite

Abstract:Coagulation is an essential process for the removal of suspended and colloidal material from water and wastewater. However, no comprehensive or universally accepted mathematical description of the process has been developed so far. Therefore, process optimization and control is usually based on data from jar tests and simple flow-proportional dosing concepts, while more accurate concepts based on water quality parameters that can be measured online are emerging. In addition, there have been attempts to develop software sensors and control schemes that involve advanced mathematical analyses of these parameters. The paper presents an overview of the parameters and physical sensors that are used for feed-forward and feed-backward control schemes and the experiences that have been made with their implementation. Moreover, the development and use of software sensors is described. Finally, the practical applications of different control techniques are given in order to illustrate the state of the art of coagulation control. Some thoughts about research needs conclude this review.

show abstract

Section: Artificial Neural Network Models (Ann)mentioning

confidence: 99%

State of the Art of Online Monitoring and Control of the Coagulation Process

Ratnaweera

Fettig

2015

Water

View full text Add to dashboard Cite

show abstract

“…Zhang and Stanley (1999) added the refined water turbidity factor as an input parameter to the water characteristic parameters in their ANN for anticipating the optimum amount of alum for use in the Rossdale Water Treatment Plant. Yu did the same for the Taipei water treatment plant in Taiwan by applying a greater number of parameters, preparing his three ANN models for anticipating the proper amount of alum necessary for coagulation (Yu et al, 2000). According to the studied background, this method can be used for anticipating the proper amount of coagulant that in this research will be determined using the data from the Ardabil province drinking water treatment plant and for determining the available effective factors in the ANN, including the error percentage that can be passed up, the amount of experimental expenses, and the time needed for performing the jar test, all of which can be reduced by preparing the model and using the results.…”

Section: Introductionmentioning

confidence: 99%

Optimum coagulant forecasting by modeling jar test experiments using ANNs

Haghiri

Daghighi

Moharramzadeh

2018

Drink. Water Eng. Sci.

View full text Add to dashboard Cite

Abstract. Currently, the proper utilization of water treatment plants and optimizing their use is of particular importance. Coagulation and flocculation in water treatment are the common ways through which the use of coagulants leads to instability of particles and the formation of larger and heavier particles, resulting in improvement of sedimentation and filtration processes. Determination of the optimum dose of such a coagulant is of particular significance. A high dose, in addition to adding costs, can cause the sediment to remain in the filtrate, a dangerous condition according to the standards, while a sub-adequate dose of coagulants can result in the reducing the required quality and acceptable performance of the coagulation process. Although jar tests are used for testing coagulants, such experiments face many constraints with respect to evaluating the results produced by sudden changes in input water because of their significant costs, long time requirements, and complex relationships among the many factors (turbidity, temperature, pH, alkalinity, etc.) that can influence the efficiency of coagulant and test results. Modeling can be used to overcome these limitations; in this research study, an artificial neural network (ANN) multi-layer perceptron (MLP) with one hidden layer has been used for modeling the jar test to determine the dosage level of used coagulant in water treatment processes. The data contained in this research have been obtained from the drinking water treatment plant located in Ardabil province in Iran. To evaluate the performance of the model, the mean squared error (MSE) and correlation coefficient (R 2 ) parameters have been used. The obtained values are within an acceptable range that demonstrates the high accuracy of the models with respect to the estimation of water-quality characteristics and the optimal dosages of coagulants; so using these models will allow operators to not only reduce costs and time taken to perform experimental jar tests but also to predict a proper dosage for coagulant amounts and to project the quality of the output water under real conditions.

show abstract

“…It also alters the flow of materials in the landscape, due to the involvement of exotic materials and changes levels of available resources such as water, light and nutrients [9]. The disturbance of soil during construction activity is considered as a major non-point source (NPS) of water pollution by sedimentation [10][11][12]. Thus, construction activity is ultimately liable for the exclusion of topsoil, destruction of vegetation, surface runoff and soil erosion [13][14][15][16][17].…”

Section: Introductionmentioning

confidence: 99%

Rainfall Induced Erosion Assessment on Hill Slope of GCE

Jaafar¹,

Islam²,

Hin³

et al. 2018

Preprint

View full text Add to dashboard Cite

This study investigates the effect of northeast monsoon season rainfall to erosion on the hillslope of the Guthrie corridor expressway (GCE), Malaysia. The main focus of this study is to develop a relationship among the vegetation cover, slope steepness, and soil loss. A plot scale basis study area is established on hillslope along the GCE. To account for various vegetation densities, a number of five plots are proposed with various percentage of vegetation density. Experimental equipment is set up at those plots to allow collection of rainfall and soil loss for duration of five months, i.e. from November 2014 till March 2015, with twice collection per month. Based on the collected data, the effect of vegetation associated to soil loss is examined followed by propose of a new model. There are few points to summarize based on this study; 1) the observed rainfall pattern shows that mostly the recorded rainfall depth is about 5 mm with 20 minutes duration of rainfall; 2) plot without vegetation cover (i.e. NBNM) yields greater soil loss and with maximum runoff whereas the least is exhibited by the plot having natural dense microbe (NDM). Meanwhile, the planted vegetation is found affected the rate of soil loss; 3) a positive relationship is found between runoff and slope steepness regardless of the vegetation cover type; and 4) A newly proposed model reveals that higher Fvs value implies a low density of vegetation; hence contributes to more soil loss.

show abstract

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

Cited by 32 publications

References 0 publications

State of the Art of Online Monitoring and Control of the Coagulation Process

State of the Art of Online Monitoring and Control of the Coagulation Process

Optimum coagulant forecasting by modeling jar test experiments using ANNs

Rainfall Induced Erosion Assessment on Hill Slope of GCE

Contact Info

Product

Resources

About