Prediction model development for petroleum refinery wastewater treatment

G. Hayder, M. Z. Ramli, M. A. Malek, A. Khamis, N. M. Hilmin

Research output: Contribution to journalArticle

6 Citations (Scopus)

Abstract

Multi-stage biological treatment of petroleum refinery wastewater using different biological conditions (anaerobic-anoxic-aerobic) has many advantages over other biological methods. It can result in maximum treatment for type of complex wastewater. In this study, raw data obtained from two multi-stage biological reactors (MSBR) used for treatment of different loads of petroleum refinery wastewater was used for developing mathematical model that could predict the process trend. The data consists of 160 entries and were gathered over approximately 180 days from two MSBR reactors that were continuously operated in parallel. A Matlab code was written with two configurations of artificial neural network. The configurations were compared and different number of neurons at the hidden layer were tested for optimum model that represent the process behavior under different loads. The tangent sigmoid transfer function (Tansig) at hidden layer and a linear transfer function (Purelin) at output layer with 6 neurons were selected as the optimum best model. The model was then used for prediction; highest removal efficiency observed was 98% which was repeatedly recorded for various loads. Effluent concentration below 100. mg/L as chemical oxygen demand (COD) was recorded for influent concentration ranged between 900 and 3600. mg COD/L.

Original languageEnglish
Pages (from-to)1-5
Number of pages5
JournalJournal of Water Process Engineering
Volume4
Issue numberC
DOIs
Publication statusPublished - 01 Jan 2014

Fingerprint

Petroleum refineries
Petroleum
Waste Water
Wastewater treatment
Biological Oxygen Demand Analysis
Wastewater
Chemical oxygen demand
petroleum
Neurons
Transfer functions
prediction
transfer function
wastewater
chemical oxygen demand
Sigmoid Colon
biological method
Effluents
Theoretical Models
anoxic conditions
artificial neural network

All Science Journal Classification (ASJC) codes

  • Biotechnology
  • Safety, Risk, Reliability and Quality
  • Waste Management and Disposal
  • Process Chemistry and Technology

Cite this

@article{836eeb2107814f16be8c24c4ab530187,
title = "Prediction model development for petroleum refinery wastewater treatment",
abstract = "Multi-stage biological treatment of petroleum refinery wastewater using different biological conditions (anaerobic-anoxic-aerobic) has many advantages over other biological methods. It can result in maximum treatment for type of complex wastewater. In this study, raw data obtained from two multi-stage biological reactors (MSBR) used for treatment of different loads of petroleum refinery wastewater was used for developing mathematical model that could predict the process trend. The data consists of 160 entries and were gathered over approximately 180 days from two MSBR reactors that were continuously operated in parallel. A Matlab code was written with two configurations of artificial neural network. The configurations were compared and different number of neurons at the hidden layer were tested for optimum model that represent the process behavior under different loads. The tangent sigmoid transfer function (Tansig) at hidden layer and a linear transfer function (Purelin) at output layer with 6 neurons were selected as the optimum best model. The model was then used for prediction; highest removal efficiency observed was 98{\%} which was repeatedly recorded for various loads. Effluent concentration below 100. mg/L as chemical oxygen demand (COD) was recorded for influent concentration ranged between 900 and 3600. mg COD/L.",
author = "G. Hayder and Ramli, {M. Z.} and Malek, {M. A.} and A. Khamis and Hilmin, {N. M.}",
year = "2014",
month = "1",
day = "1",
doi = "10.1016/j.jwpe.2014.08.006",
language = "English",
volume = "4",
pages = "1--5",
journal = "Journal of Water Process Engineering",
issn = "2214-7144",
publisher = "Elsevier Limited",
number = "C",

}

Prediction model development for petroleum refinery wastewater treatment. / Hayder, G.; Ramli, M. Z.; Malek, M. A.; Khamis, A.; Hilmin, N. M.

In: Journal of Water Process Engineering, Vol. 4, No. C, 01.01.2014, p. 1-5.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Prediction model development for petroleum refinery wastewater treatment

AU - Hayder, G.

AU - Ramli, M. Z.

AU - Malek, M. A.

AU - Khamis, A.

AU - Hilmin, N. M.

PY - 2014/1/1

Y1 - 2014/1/1

N2 - Multi-stage biological treatment of petroleum refinery wastewater using different biological conditions (anaerobic-anoxic-aerobic) has many advantages over other biological methods. It can result in maximum treatment for type of complex wastewater. In this study, raw data obtained from two multi-stage biological reactors (MSBR) used for treatment of different loads of petroleum refinery wastewater was used for developing mathematical model that could predict the process trend. The data consists of 160 entries and were gathered over approximately 180 days from two MSBR reactors that were continuously operated in parallel. A Matlab code was written with two configurations of artificial neural network. The configurations were compared and different number of neurons at the hidden layer were tested for optimum model that represent the process behavior under different loads. The tangent sigmoid transfer function (Tansig) at hidden layer and a linear transfer function (Purelin) at output layer with 6 neurons were selected as the optimum best model. The model was then used for prediction; highest removal efficiency observed was 98% which was repeatedly recorded for various loads. Effluent concentration below 100. mg/L as chemical oxygen demand (COD) was recorded for influent concentration ranged between 900 and 3600. mg COD/L.

AB - Multi-stage biological treatment of petroleum refinery wastewater using different biological conditions (anaerobic-anoxic-aerobic) has many advantages over other biological methods. It can result in maximum treatment for type of complex wastewater. In this study, raw data obtained from two multi-stage biological reactors (MSBR) used for treatment of different loads of petroleum refinery wastewater was used for developing mathematical model that could predict the process trend. The data consists of 160 entries and were gathered over approximately 180 days from two MSBR reactors that were continuously operated in parallel. A Matlab code was written with two configurations of artificial neural network. The configurations were compared and different number of neurons at the hidden layer were tested for optimum model that represent the process behavior under different loads. The tangent sigmoid transfer function (Tansig) at hidden layer and a linear transfer function (Purelin) at output layer with 6 neurons were selected as the optimum best model. The model was then used for prediction; highest removal efficiency observed was 98% which was repeatedly recorded for various loads. Effluent concentration below 100. mg/L as chemical oxygen demand (COD) was recorded for influent concentration ranged between 900 and 3600. mg COD/L.

UR - http://www.scopus.com/inward/record.url?scp=84926381475&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84926381475&partnerID=8YFLogxK

U2 - 10.1016/j.jwpe.2014.08.006

DO - 10.1016/j.jwpe.2014.08.006

M3 - Article

AN - SCOPUS:84926381475

VL - 4

SP - 1

EP - 5

JO - Journal of Water Process Engineering

JF - Journal of Water Process Engineering

SN - 2214-7144

IS - C

ER -