Evaluation of the thermodynamic models UNIQUAC and UNIFAC using artificial neural networks

Leliana C. Borges, Marcelo Castier

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Citation (Scopus)

Abstract

The purpose of this paper is the formulation and implementation of a neural network for the evaluation of the thermodynamic models UNIQUAC and UNIFAC, so that their performance in the calculation of vapor-liquid equilibria, a very important aspect of chemical process design, can be estimated. A multi-layer network with feedforward connections is used. Each processing unit is a semi-linear neuron (the activation rule is a sigmoid function) and synapses do not exist between elements of the same layer. The training and prediction examples are obtained from vapor-liquid equilibrium data for several isothermal binary systems composed of hydrocarbons and alcohols. The temperature of the system, UNIFAC groups and acentric factor of the compounds and mean pressure deviation of the UNIQUAC and UNIFAC models are used in the examples. For the implementation of the network, the software NeuralWorks Professional II/Plus, NEURALWARE, Inc. is used. After training, satisfactory agreement was found between the answers calculated by the network and the output patterns presented to it. The success of the implementation is demonstrated by testing its predictive capability.

Original languageEnglish
Title of host publicationProceedings of the International Joint Conference on Neural Networks
PublisherPubl by IEEE
Pages999-1002
Number of pages4
Volume1
ISBN (Print)0780314212, 9780780314214
Publication statusPublished - 1993
Externally publishedYes
EventProceedings of 1993 International Joint Conference on Neural Networks. Part 1 (of 3) - Nagoya, Jpn
Duration: 25 Oct 199329 Oct 1993

Other

OtherProceedings of 1993 International Joint Conference on Neural Networks. Part 1 (of 3)
CityNagoya, Jpn
Period25/10/9329/10/93

Fingerprint

Phase equilibria
Thermodynamics
Neural networks
Network layers
Neurons
Process design
Alcohols
Chemical activation
Hydrocarbons
Testing
Processing
Temperature

ASJC Scopus subject areas

  • Engineering(all)

Cite this

Borges, L. C., & Castier, M. (1993). Evaluation of the thermodynamic models UNIQUAC and UNIFAC using artificial neural networks. In Proceedings of the International Joint Conference on Neural Networks (Vol. 1, pp. 999-1002). Publ by IEEE.

Evaluation of the thermodynamic models UNIQUAC and UNIFAC using artificial neural networks. / Borges, Leliana C.; Castier, Marcelo.

Proceedings of the International Joint Conference on Neural Networks. Vol. 1 Publ by IEEE, 1993. p. 999-1002.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Borges, LC & Castier, M 1993, Evaluation of the thermodynamic models UNIQUAC and UNIFAC using artificial neural networks. in Proceedings of the International Joint Conference on Neural Networks. vol. 1, Publ by IEEE, pp. 999-1002, Proceedings of 1993 International Joint Conference on Neural Networks. Part 1 (of 3), Nagoya, Jpn, 25/10/93.
Borges LC, Castier M. Evaluation of the thermodynamic models UNIQUAC and UNIFAC using artificial neural networks. In Proceedings of the International Joint Conference on Neural Networks. Vol. 1. Publ by IEEE. 1993. p. 999-1002
Borges, Leliana C. ; Castier, Marcelo. / Evaluation of the thermodynamic models UNIQUAC and UNIFAC using artificial neural networks. Proceedings of the International Joint Conference on Neural Networks. Vol. 1 Publ by IEEE, 1993. pp. 999-1002
@inproceedings{aae845a556f24ef7a1f79cf5e3de1d31,
title = "Evaluation of the thermodynamic models UNIQUAC and UNIFAC using artificial neural networks",
abstract = "The purpose of this paper is the formulation and implementation of a neural network for the evaluation of the thermodynamic models UNIQUAC and UNIFAC, so that their performance in the calculation of vapor-liquid equilibria, a very important aspect of chemical process design, can be estimated. A multi-layer network with feedforward connections is used. Each processing unit is a semi-linear neuron (the activation rule is a sigmoid function) and synapses do not exist between elements of the same layer. The training and prediction examples are obtained from vapor-liquid equilibrium data for several isothermal binary systems composed of hydrocarbons and alcohols. The temperature of the system, UNIFAC groups and acentric factor of the compounds and mean pressure deviation of the UNIQUAC and UNIFAC models are used in the examples. For the implementation of the network, the software NeuralWorks Professional II/Plus, NEURALWARE, Inc. is used. After training, satisfactory agreement was found between the answers calculated by the network and the output patterns presented to it. The success of the implementation is demonstrated by testing its predictive capability.",
author = "Borges, {Leliana C.} and Marcelo Castier",
year = "1993",
language = "English",
isbn = "0780314212",
volume = "1",
pages = "999--1002",
booktitle = "Proceedings of the International Joint Conference on Neural Networks",
publisher = "Publ by IEEE",

}

TY - GEN

T1 - Evaluation of the thermodynamic models UNIQUAC and UNIFAC using artificial neural networks

AU - Borges, Leliana C.

AU - Castier, Marcelo

PY - 1993

Y1 - 1993

N2 - The purpose of this paper is the formulation and implementation of a neural network for the evaluation of the thermodynamic models UNIQUAC and UNIFAC, so that their performance in the calculation of vapor-liquid equilibria, a very important aspect of chemical process design, can be estimated. A multi-layer network with feedforward connections is used. Each processing unit is a semi-linear neuron (the activation rule is a sigmoid function) and synapses do not exist between elements of the same layer. The training and prediction examples are obtained from vapor-liquid equilibrium data for several isothermal binary systems composed of hydrocarbons and alcohols. The temperature of the system, UNIFAC groups and acentric factor of the compounds and mean pressure deviation of the UNIQUAC and UNIFAC models are used in the examples. For the implementation of the network, the software NeuralWorks Professional II/Plus, NEURALWARE, Inc. is used. After training, satisfactory agreement was found between the answers calculated by the network and the output patterns presented to it. The success of the implementation is demonstrated by testing its predictive capability.

AB - The purpose of this paper is the formulation and implementation of a neural network for the evaluation of the thermodynamic models UNIQUAC and UNIFAC, so that their performance in the calculation of vapor-liquid equilibria, a very important aspect of chemical process design, can be estimated. A multi-layer network with feedforward connections is used. Each processing unit is a semi-linear neuron (the activation rule is a sigmoid function) and synapses do not exist between elements of the same layer. The training and prediction examples are obtained from vapor-liquid equilibrium data for several isothermal binary systems composed of hydrocarbons and alcohols. The temperature of the system, UNIFAC groups and acentric factor of the compounds and mean pressure deviation of the UNIQUAC and UNIFAC models are used in the examples. For the implementation of the network, the software NeuralWorks Professional II/Plus, NEURALWARE, Inc. is used. After training, satisfactory agreement was found between the answers calculated by the network and the output patterns presented to it. The success of the implementation is demonstrated by testing its predictive capability.

UR - http://www.scopus.com/inward/record.url?scp=0027850235&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0027850235&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:0027850235

SN - 0780314212

SN - 9780780314214

VL - 1

SP - 999

EP - 1002

BT - Proceedings of the International Joint Conference on Neural Networks

PB - Publ by IEEE

ER -