IIUM Repository

Wastewater treatment plant performance analysis and prediction using artificial intelligence (AI)

Nagimeldin, Olla and Jami, Mohammed Saedi (2021) Wastewater treatment plant performance analysis and prediction using artificial intelligence (AI). In: 6th International Conference on Biotechnology Engineering 2021, Kuala Lumpur, Malaysia (Virtual). (Unpublished)

[img] PDF (Unpublished) - Accepted Version
Restricted to Repository staff only

Download (1MB) | Request a copy

Abstract

Several potential environmental impacts associated with wastewater effluents such as pollution effects on aquatic and terrestrial ecosystems increase the onus on wastewater treatment plants (WWTP) to discharge an effluent that complies with local regulatory standards such as by the Department of Environment (DOE). This leads to the continuous need for control and management improvement in WWTPs systems. This study aims to develop artificial intelligence (AI)-based model that examines specific parameters, including pH, biochemical oxygen demand (BOD5), total suspended solids (TSS) to predict ammoniacal nitrogen (NH3-N) and chemical oxygen demand (COD), and accordingly, provide the system with continuous improvements. Raw data was collected from Indah Water Konsortium (IWK) Bandar Tun Razak sewage treatment plant (STP) in Malaysia. It was then introduced to six different AI models using Orange data mining software which is a commercially available, open-source data mining software. Models used in this study, which are, Artificial Neural Network (ANN), Support Vector Machine (SVM), K-Nearest Neighbours (KNN), Gradient Boosting, Random Forest, and Linear Regression were further optimized and the best model to predict the Ammoniacal Nitrogen and Chemical Oxygen Demand (COD) effluents from the STP was chosen. Results showed the outperformance of the Gradient Boosting model compared to the rest, with a correlation coefficient (R2) and a mean absolute error (MAE) of 0.999 and 0.167, respectively for Ammoniacal Nitrogen, and 0.999 and 0.214 for COD.

Item Type: Conference or Workshop Item (Invited Papers)
Additional Information: 5545/90838
Uncontrolled Keywords: Wastewater treatment plant, performance analysis, prediction using artificial intelligence (AI)
Subjects: T Technology > TP Chemical technology > TP155 Chemical engineering
Kulliyyahs/Centres/Divisions/Institutes (Can select more than one option. Press CONTROL button): Kulliyyah of Engineering > Department of Biotechnology Engineering
Depositing User: Professor Dr. Mohammed Saedi Jami, PhD CEng MIChemE
Date Deposited: 22 Jul 2021 15:35
Last Modified: 22 Jul 2021 15:35
URI: http://irep.iium.edu.my/id/eprint/90838

Actions (login required)

View Item View Item

Downloads

Downloads per month over past year