Application of artificial neural network (ANN) for the prediction of water treatment plant influent characteristics
Application of a reliable forecasting model for any water treatment plant (WTP) is essential in order to provide a tool for predicting influent water quality and to form a basis for controlling the operation of the process. This would minimize the operation and analysis costs, and assess the stabili...
Main Authors: | , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Kurdistan University of Medical Sciences
2013-07-01
|
Series: | Journal of Advances in Environmental Health Research |
Subjects: | |
Online Access: | http://jaehr.muk.ac.ir/article_40130_1bfb2c62f6263703f6b2258b94609435.pdf |
id |
doaj-9c52bd9c86d34ca8b4d551fae8e057af |
---|---|
record_format |
Article |
spelling |
doaj-9c52bd9c86d34ca8b4d551fae8e057af2021-07-14T05:41:11ZengKurdistan University of Medical SciencesJournal of Advances in Environmental Health Research2345-39902345-39902013-07-01128910010.22102/jaehr.2013.4013040130Application of artificial neural network (ANN) for the prediction of water treatment plant influent characteristicsMehri Solaimany-Aminabad0Afshin Maleki1Mahdi Hadi2Kurdistan Environmental Health Research Center, School of Health, Kurdistan University of Medical Sciences, Sanandaj, IranKurdistan Environmental Health Research Center, School of Health, Kurdistan University of Medical Sciences, Sanandaj, IranCenter for Water Quality Research (CWQR), Institute for Environmental Research (IER), Tehran University of Medical Sciences, Tehran, IranApplication of a reliable forecasting model for any water treatment plant (WTP) is essential in order to provide a tool for predicting influent water quality and to form a basis for controlling the operation of the process. This would minimize the operation and analysis costs, and assess the stability of WTP performances. This paper focuses on applying an artificial neural network (ANN) approach with a feed-forward back-propagation non-linear autoregressive neural network to predict the influent water quality of Sanandaj WTP. Influent water quality data gathered over a 2-year period were used to building the prediction model. The study signifies that the ANN can predict the influent water quality parameters with a correlation coefficient (R) between the observed and predicted output variables reaching up to 0.93. The prediction models developed in this work for Alkalinity, pH, calcium, carbon dioxide, temperature, total hardness, turbidity, total dissolved solids, and electrical conductivity have an acceptable generalization capability and accuracy with coefficient of determination (R2) ranging from 0.86 for alkalinity to 0.54 for electrical conductivity. The predicting ANN model provides an effective analyzing and diagnosing tool to understand and simulate the non-linear behavior of the influent water characteristics. The developed predicting models can be used by WTP operators and decision makers.http://jaehr.muk.ac.ir/article_40130_1bfb2c62f6263703f6b2258b94609435.pdfneural networktime seriesinfluent water characteristicsforecasting |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Mehri Solaimany-Aminabad Afshin Maleki Mahdi Hadi |
spellingShingle |
Mehri Solaimany-Aminabad Afshin Maleki Mahdi Hadi Application of artificial neural network (ANN) for the prediction of water treatment plant influent characteristics Journal of Advances in Environmental Health Research neural network time series influent water characteristics forecasting |
author_facet |
Mehri Solaimany-Aminabad Afshin Maleki Mahdi Hadi |
author_sort |
Mehri Solaimany-Aminabad |
title |
Application of artificial neural network (ANN) for the prediction of water treatment plant influent characteristics |
title_short |
Application of artificial neural network (ANN) for the prediction of water treatment plant influent characteristics |
title_full |
Application of artificial neural network (ANN) for the prediction of water treatment plant influent characteristics |
title_fullStr |
Application of artificial neural network (ANN) for the prediction of water treatment plant influent characteristics |
title_full_unstemmed |
Application of artificial neural network (ANN) for the prediction of water treatment plant influent characteristics |
title_sort |
application of artificial neural network (ann) for the prediction of water treatment plant influent characteristics |
publisher |
Kurdistan University of Medical Sciences |
series |
Journal of Advances in Environmental Health Research |
issn |
2345-3990 2345-3990 |
publishDate |
2013-07-01 |
description |
Application of a reliable forecasting model for any water treatment plant (WTP) is essential in order to provide a tool for predicting influent water quality and to form a basis for controlling the operation of the process. This would minimize the operation and analysis costs, and assess the stability of WTP performances. This paper focuses on applying an artificial neural network (ANN) approach with a feed-forward back-propagation non-linear autoregressive neural network to predict the influent water quality of Sanandaj WTP. Influent water quality data gathered over a 2-year period were used to building the prediction model. The study signifies that the ANN can predict the influent water quality parameters with a correlation coefficient (R) between the observed and predicted output variables reaching up to 0.93. The prediction models developed in this work for Alkalinity, pH, calcium, carbon dioxide, temperature, total hardness, turbidity, total dissolved solids, and electrical conductivity have an acceptable generalization capability and accuracy with coefficient of determination (R2) ranging from 0.86 for alkalinity to 0.54 for electrical conductivity. The predicting ANN model provides an effective analyzing and diagnosing tool to understand and simulate the non-linear behavior of the influent water characteristics. The developed predicting models can be used by WTP operators and decision makers. |
topic |
neural network time series influent water characteristics forecasting |
url |
http://jaehr.muk.ac.ir/article_40130_1bfb2c62f6263703f6b2258b94609435.pdf |
work_keys_str_mv |
AT mehrisolaimanyaminabad applicationofartificialneuralnetworkannforthepredictionofwatertreatmentplantinfluentcharacteristics AT afshinmaleki applicationofartificialneuralnetworkannforthepredictionofwatertreatmentplantinfluentcharacteristics AT mahdihadi applicationofartificialneuralnetworkannforthepredictionofwatertreatmentplantinfluentcharacteristics |
_version_ |
1721304305120575488 |