Application of artificial neural networks for evaluation and management of water quality at intakes of the water treatment plants in Baghdad

Other Title(s)

تطبيق الشبكات العصبية الاصطناعية لتقييم و إدارة نوعية المياه عند مآخذ محطات تصفية المياه في بغداد

Dissertant

Yunus, Yusuf Muhammad

Thesis advisor

Qasim, Walid Muhammad Salih

Comitee Members

Muhammad, Ahmad A.
al-Suhayli, Rafa Hashim
al-Shaarbaf, Ihsan Ali Saib

University

University of Baghdad

Faculty

College of Engineering

Department

Environmental Engineering Department

University Country

Iraq

Degree

Master

Degree Date

2007

English Abstract

In this research, Artificial Neural Networks (ANNs) technique was applied in an attempt to predict some of the water quality parameters at the intakes of the water treatment plants (WTP) in Baghdad.

These predictions are useful in the planning, evaluation, management, and operation of such projects, which may results in produce water with better quality.

The running conventional water treatment plants in Baghdad are (Karkh, Sharq Dijlah, Karama, Wathba, Qadisiya, Dora, and Rasheed).

Four models were built for the prediction, one for the Turbidity at Al-Wathba WTP from (1991-2000) of monthly maximum values for raw water (river water near intakes of the water treatment plants).

The second model for the turbidity at Al-Rasheed WTP for the same period of model 1.

The third model for Total Coliform Bacteria at Al-Wathba WTP from (1993-2004), while the fourth model for the Total Hardness at Al-Wathba WTP from (1991-2000).

The data used in these models were collected from Baghdad Water Authority (Amanat Baghdad), and prepared in an appropriate format by (Barazanjy, 2007).

Multi-layer perceptron trainings using the back-propagation algorithm were used.

In this work, the feasibility of ANNs technique for modeling these water quality parameters was investigated.

A number of issues in relation to ANNs construction such as the effect of ANNs geometry and internal parameters on the performance of ANNs models were investigated.

Information on the relative importance of the factors affecting the above water quality parameters predictions were presented and practical equations for the predictions of the above parameters were developed.

It was found that ANNs have the ability to predict the Turbidity at Al-Wathba WTP and Al-Rasheed WTP and the Total Hardness at Al- Wathba WTP with a good degree of accuracy (the coefficient of determination (R 2 ) was 0.9687, 0.6962, and 0.8685 respectively), while it was found that ANNs has a moderate degree of accuracy for predict of the Total Coliform Bacteria at Al-Wathba WTP (R 2 = 0.5519).

The ANNs models developed to study the impact of the internal network parameters on model performance indicate that ANNs performance was relatively insensitive to the number of hidden layer nodes, momentum term, and learning rate.

Main Subjects

Earth Sciences, Water and Environment

No. of Pages

121

Table of Contents

• APA
• MLA
• AMA

Language

English

Data Type

Arab Theses

Record ID

BIM-736860