A Neural Networks Model for Accurate Prediction of the Flash Point of Chemical Compounds

Flashpoint is one of the most important flammability characteristics of chemical compounds. In the present study, we developed a neural network model for accurate prediction of the flashpoint of chemical compounds, using the number of hydrogen and carbon atoms, critical temperature, normal boiling p...

Full description

Bibliographic Details
Main Authors:	Hamid Reza Mirshahvalad, Ramin Ghasemiasl, Nahid Raufi, Mehrdad Malekzadeh Dirin
Format:	Article
Language:	English
Published:	Iranian Institute of Research and Development in Chemical Industries (IRDCI)-ACECR 2020-08-01
Series:	Iranian Journal of Chemistry & Chemical Engineering
Subjects:	flashpoint predictive models neural networks qspr group contribution method
Online Access:	http://www.ijcce.ac.ir/article_35001_0f67bbe6da986ee179162112b04db4d2.pdf

id	doaj-d7612ea52b04462eae3915541f6ca450
record_format	Article
spelling	doaj-d7612ea52b04462eae3915541f6ca4502021-01-23T19:52:30ZengIranian Institute of Research and Development in Chemical Industries (IRDCI)-ACECRIranian Journal of Chemistry & Chemical Engineering 1021-99861021-99862020-08-0139429730410.30492/ijcce.2019.3500135001A Neural Networks Model for Accurate Prediction of the Flash Point of Chemical CompoundsHamid Reza Mirshahvalad0Ramin Ghasemiasl,1Nahid Raufi2Mehrdad Malekzadeh Dirin3Department of Mechanical Engineering, West Tehran Branch, Islamic Azad University, Tehran, I.R. IRANDepartment of Mechanical Engineering, West Tehran Branch, Islamic Azad University, Tehran, I.R. IRANDepartment of Chemical Engineering, South Tehran Branch, Islamic Azad University, Tehran, I.R. IRANDepartment of Mechanical Engineering, West Tehran Branch, Islamic Azad University, Tehran, I.R. IRANFlashpoint is one of the most important flammability characteristics of chemical compounds. In the present study, we developed a neural network model for accurate prediction of the flashpoint of chemical compounds, using the number of hydrogen and carbon atoms, critical temperature, normal boiling point, acentric factor, and enthalpy of formation as model inputs. Using a robust strategy to efficiently assign neural network parameters and evaluate the authentic performance of the neural networks, we could achieve an accurate model that yielded average absolute relative errors of 0. 97, 0. 96, 0.99 and 1.0% and correlation coefficients of 0.9984, 0.9985, 0.9981 and 0.9979 for the overall, training, validation and test sets, respectively. These results are among the most accurate ever reported ones, to date.http://www.ijcce.ac.ir/article_35001_0f67bbe6da986ee179162112b04db4d2.pdfflashpointpredictive modelsneural networksqsprgroup contribution method
collection	DOAJ
language	English
format	Article
sources	DOAJ
author	Hamid Reza Mirshahvalad Ramin Ghasemiasl, Nahid Raufi Mehrdad Malekzadeh Dirin
spellingShingle	Hamid Reza Mirshahvalad Ramin Ghasemiasl, Nahid Raufi Mehrdad Malekzadeh Dirin A Neural Networks Model for Accurate Prediction of the Flash Point of Chemical Compounds Iranian Journal of Chemistry & Chemical Engineering flashpoint predictive models neural networks qspr group contribution method
author_facet	Hamid Reza Mirshahvalad Ramin Ghasemiasl, Nahid Raufi Mehrdad Malekzadeh Dirin
author_sort	Hamid Reza Mirshahvalad
title	A Neural Networks Model for Accurate Prediction of the Flash Point of Chemical Compounds
title_short	A Neural Networks Model for Accurate Prediction of the Flash Point of Chemical Compounds
title_full	A Neural Networks Model for Accurate Prediction of the Flash Point of Chemical Compounds
title_fullStr	A Neural Networks Model for Accurate Prediction of the Flash Point of Chemical Compounds
title_full_unstemmed	A Neural Networks Model for Accurate Prediction of the Flash Point of Chemical Compounds
title_sort	neural networks model for accurate prediction of the flash point of chemical compounds
publisher	Iranian Institute of Research and Development in Chemical Industries (IRDCI)-ACECR
series	Iranian Journal of Chemistry & Chemical Engineering
issn	1021-9986 1021-9986
publishDate	2020-08-01
description	Flashpoint is one of the most important flammability characteristics of chemical compounds. In the present study, we developed a neural network model for accurate prediction of the flashpoint of chemical compounds, using the number of hydrogen and carbon atoms, critical temperature, normal boiling point, acentric factor, and enthalpy of formation as model inputs. Using a robust strategy to efficiently assign neural network parameters and evaluate the authentic performance of the neural networks, we could achieve an accurate model that yielded average absolute relative errors of 0. 97, 0. 96, 0.99 and 1.0% and correlation coefficients of 0.9984, 0.9985, 0.9981 and 0.9979 for the overall, training, validation and test sets, respectively. These results are among the most accurate ever reported ones, to date.
topic	flashpoint predictive models neural networks qspr group contribution method
url	http://www.ijcce.ac.ir/article_35001_0f67bbe6da986ee179162112b04db4d2.pdf
work_keys_str_mv	AT hamidrezamirshahvalad aneuralnetworksmodelforaccuratepredictionoftheflashpointofchemicalcompounds AT raminghasemiasl aneuralnetworksmodelforaccuratepredictionoftheflashpointofchemicalcompounds AT nahidraufi aneuralnetworksmodelforaccuratepredictionoftheflashpointofchemicalcompounds AT mehrdadmalekzadehdirin aneuralnetworksmodelforaccuratepredictionoftheflashpointofchemicalcompounds AT hamidrezamirshahvalad neuralnetworksmodelforaccuratepredictionoftheflashpointofchemicalcompounds AT raminghasemiasl neuralnetworksmodelforaccuratepredictionoftheflashpointofchemicalcompounds AT nahidraufi neuralnetworksmodelforaccuratepredictionoftheflashpointofchemicalcompounds AT mehrdadmalekzadehdirin neuralnetworksmodelforaccuratepredictionoftheflashpointofchemicalcompounds
_version_	1724327049616687104

A Neural Networks Model for Accurate Prediction of the Flash Point of Chemical Compounds

Similar Items