Advanced computational techniques for solving desalination plant models using neural and genetic based methods

Farouq S. Mjalli, Nabil Abdel-Jabbar, Hisham Ettouney, Hazim A M Qiblawey

Research output: Contribution to journalArticle

4 Citations (Scopus)

Abstract

Simulation of multi-stage flash (MSF) desalination processes that have a production capacity range between 50,000 to 75,000 m3/d is an intensive computational problem that requires high computer processing speed despite the availability of advanced processing computer power in hand nowadays. In this work, a comparative study is conducted to explore the performance of different numerical techniques to solve large set of nonlinear equations generated by large scale MSF models. These algorithms can be categorized into three groups, namely: conventional numerical approximation methods, multi-objective optimization based methods, and the last group comprises artificial neural networks (ANN) based models and genetic algorithms (GA) based methods. The problem of solving large sets of nonlinear equations with upper and lower constraints is accomplished successfully using all algorithms with different prediction efficiency and speed. The idea of using GA and ANN based algorithms in simulating the MSF model is basically used to generate feasible initial solution estimates that were used as starting guesses for other numerical methods in the former case and to eliminate the step of providing these initial guesses in the later case. Significant reduction of computation effort was attained using ANN-based techniques. The outcome of this work can be utilized to develop new generations of process simulators that are based on well-trained ANNs in order to achieve speedup of computations and to generate more reliable predictions without detracting from accuracy.

Original languageEnglish
Article number29
JournalChemical Product and Process Modeling
Volume2
Issue number3
Publication statusPublished - May 17 2007

Fingerprint

Computational Techniques
Flash
Desalination
Artificial Neural Network
Guess
Neural networks
Nonlinear equations
Large Set
Nonlinear Equations
Genetic algorithms
Numerical Methods
Genetic Algorithm
Prediction
Processing
Multiobjective optimization
Numerical Techniques
Numerical Approximation
Multi-objective Optimization
Approximation Methods
Comparative Study

Keywords

  • ANN
  • Genetic Algorithms
  • MSF
  • Optimization
  • Simulation

ASJC Scopus subject areas

  • Chemical Engineering(all)
  • Modelling and Simulation

Cite this

Advanced computational techniques for solving desalination plant models using neural and genetic based methods. / Mjalli, Farouq S.; Abdel-Jabbar, Nabil; Ettouney, Hisham; Qiblawey, Hazim A M.

In: Chemical Product and Process Modeling, Vol. 2, No. 3, 29, 17.05.2007.

Research output: Contribution to journalArticle

@article{614e792281064f1b9ea9c218841a09e6,
title = "Advanced computational techniques for solving desalination plant models using neural and genetic based methods",
abstract = "Simulation of multi-stage flash (MSF) desalination processes that have a production capacity range between 50,000 to 75,000 m3/d is an intensive computational problem that requires high computer processing speed despite the availability of advanced processing computer power in hand nowadays. In this work, a comparative study is conducted to explore the performance of different numerical techniques to solve large set of nonlinear equations generated by large scale MSF models. These algorithms can be categorized into three groups, namely: conventional numerical approximation methods, multi-objective optimization based methods, and the last group comprises artificial neural networks (ANN) based models and genetic algorithms (GA) based methods. The problem of solving large sets of nonlinear equations with upper and lower constraints is accomplished successfully using all algorithms with different prediction efficiency and speed. The idea of using GA and ANN based algorithms in simulating the MSF model is basically used to generate feasible initial solution estimates that were used as starting guesses for other numerical methods in the former case and to eliminate the step of providing these initial guesses in the later case. Significant reduction of computation effort was attained using ANN-based techniques. The outcome of this work can be utilized to develop new generations of process simulators that are based on well-trained ANNs in order to achieve speedup of computations and to generate more reliable predictions without detracting from accuracy.",
keywords = "ANN, Genetic Algorithms, MSF, Optimization, Simulation",
author = "Mjalli, {Farouq S.} and Nabil Abdel-Jabbar and Hisham Ettouney and Qiblawey, {Hazim A M}",
year = "2007",
month = "5",
day = "17",
language = "English",
volume = "2",
journal = "Chemical Product and Process Modeling",
issn = "2194-6159",
publisher = "Berkeley Electronic Press",
number = "3",

}

TY - JOUR

T1 - Advanced computational techniques for solving desalination plant models using neural and genetic based methods

AU - Mjalli, Farouq S.

AU - Abdel-Jabbar, Nabil

AU - Ettouney, Hisham

AU - Qiblawey, Hazim A M

PY - 2007/5/17

Y1 - 2007/5/17

N2 - Simulation of multi-stage flash (MSF) desalination processes that have a production capacity range between 50,000 to 75,000 m3/d is an intensive computational problem that requires high computer processing speed despite the availability of advanced processing computer power in hand nowadays. In this work, a comparative study is conducted to explore the performance of different numerical techniques to solve large set of nonlinear equations generated by large scale MSF models. These algorithms can be categorized into three groups, namely: conventional numerical approximation methods, multi-objective optimization based methods, and the last group comprises artificial neural networks (ANN) based models and genetic algorithms (GA) based methods. The problem of solving large sets of nonlinear equations with upper and lower constraints is accomplished successfully using all algorithms with different prediction efficiency and speed. The idea of using GA and ANN based algorithms in simulating the MSF model is basically used to generate feasible initial solution estimates that were used as starting guesses for other numerical methods in the former case and to eliminate the step of providing these initial guesses in the later case. Significant reduction of computation effort was attained using ANN-based techniques. The outcome of this work can be utilized to develop new generations of process simulators that are based on well-trained ANNs in order to achieve speedup of computations and to generate more reliable predictions without detracting from accuracy.

AB - Simulation of multi-stage flash (MSF) desalination processes that have a production capacity range between 50,000 to 75,000 m3/d is an intensive computational problem that requires high computer processing speed despite the availability of advanced processing computer power in hand nowadays. In this work, a comparative study is conducted to explore the performance of different numerical techniques to solve large set of nonlinear equations generated by large scale MSF models. These algorithms can be categorized into three groups, namely: conventional numerical approximation methods, multi-objective optimization based methods, and the last group comprises artificial neural networks (ANN) based models and genetic algorithms (GA) based methods. The problem of solving large sets of nonlinear equations with upper and lower constraints is accomplished successfully using all algorithms with different prediction efficiency and speed. The idea of using GA and ANN based algorithms in simulating the MSF model is basically used to generate feasible initial solution estimates that were used as starting guesses for other numerical methods in the former case and to eliminate the step of providing these initial guesses in the later case. Significant reduction of computation effort was attained using ANN-based techniques. The outcome of this work can be utilized to develop new generations of process simulators that are based on well-trained ANNs in order to achieve speedup of computations and to generate more reliable predictions without detracting from accuracy.

KW - ANN

KW - Genetic Algorithms

KW - MSF

KW - Optimization

KW - Simulation

UR - http://www.scopus.com/inward/record.url?scp=38849204309&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=38849204309&partnerID=8YFLogxK

M3 - Article

VL - 2

JO - Chemical Product and Process Modeling

JF - Chemical Product and Process Modeling

SN - 2194-6159

IS - 3

M1 - 29

ER -