The yield prediction of synthetic fuel production from pyrolysis of plasticwaste by Levenberg-Marquardt approach in feedforward neural networks model

Faisal Abnisa, Shafferina Dayana Anuar Sharuddin, Mohd Fauzi bin Zanil, Wan Mohd Ashri Wan Daud, Teuku Meurah Indra Mahlia

Research output: Contribution to journalArticle

Abstract

The conversion of plastic waste into fuel by pyrolysis has been recognized as a potential strategy for commercialization. The amount of plastic waste is basically different for each country which normally refers to non-recycled plastics data; consequently, the production target will also be different. This study attempted to build a model to predict fuel production from different non-recycled plastics data. The predictive model was developed via Levenberg-Marquardt approach in feed-forward neural networks model. The optimal number of hidden neurons was selected based on the lowest total of the mean square error. The proposed model was evaluated using the statistical analysis and graphical presentation for its accuracy and reliability. The results showed that the model was capable to predict product yields from pyrolysis of non-recycled plastics with high accuracy and the output values were strongly correlated with the values in literature.

Original languageEnglish
Article number1853
JournalPolymers
Volume11
Issue number11
DOIs
Publication statusPublished - 01 Nov 2019

Fingerprint

Synthetic fuels
Feedforward neural networks
Pyrolysis
Plastics
Mean square error
Neurons
Statistical methods

All Science Journal Classification (ASJC) codes

  • Chemistry(all)
  • Polymers and Plastics

Cite this

Abnisa, Faisal ; Sharuddin, Shafferina Dayana Anuar ; bin Zanil, Mohd Fauzi ; Daud, Wan Mohd Ashri Wan ; Mahlia, Teuku Meurah Indra. / The yield prediction of synthetic fuel production from pyrolysis of plasticwaste by Levenberg-Marquardt approach in feedforward neural networks model. In: Polymers. 2019 ; Vol. 11, No. 11.
@article{e51b61e9a5d44e01833b0df7a2d785cb,
title = "The yield prediction of synthetic fuel production from pyrolysis of plasticwaste by Levenberg-Marquardt approach in feedforward neural networks model",
abstract = "The conversion of plastic waste into fuel by pyrolysis has been recognized as a potential strategy for commercialization. The amount of plastic waste is basically different for each country which normally refers to non-recycled plastics data; consequently, the production target will also be different. This study attempted to build a model to predict fuel production from different non-recycled plastics data. The predictive model was developed via Levenberg-Marquardt approach in feed-forward neural networks model. The optimal number of hidden neurons was selected based on the lowest total of the mean square error. The proposed model was evaluated using the statistical analysis and graphical presentation for its accuracy and reliability. The results showed that the model was capable to predict product yields from pyrolysis of non-recycled plastics with high accuracy and the output values were strongly correlated with the values in literature.",
author = "Faisal Abnisa and Sharuddin, {Shafferina Dayana Anuar} and {bin Zanil}, {Mohd Fauzi} and Daud, {Wan Mohd Ashri Wan} and Mahlia, {Teuku Meurah Indra}",
year = "2019",
month = "11",
day = "1",
doi = "10.3390/polym11111853",
language = "English",
volume = "11",
journal = "Polymers",
issn = "2073-4360",
publisher = "MDPI AG",
number = "11",

}

The yield prediction of synthetic fuel production from pyrolysis of plasticwaste by Levenberg-Marquardt approach in feedforward neural networks model. / Abnisa, Faisal; Sharuddin, Shafferina Dayana Anuar; bin Zanil, Mohd Fauzi; Daud, Wan Mohd Ashri Wan; Mahlia, Teuku Meurah Indra.

In: Polymers, Vol. 11, No. 11, 1853, 01.11.2019.

Research output: Contribution to journalArticle

TY - JOUR

T1 - The yield prediction of synthetic fuel production from pyrolysis of plasticwaste by Levenberg-Marquardt approach in feedforward neural networks model

AU - Abnisa, Faisal

AU - Sharuddin, Shafferina Dayana Anuar

AU - bin Zanil, Mohd Fauzi

AU - Daud, Wan Mohd Ashri Wan

AU - Mahlia, Teuku Meurah Indra

PY - 2019/11/1

Y1 - 2019/11/1

N2 - The conversion of plastic waste into fuel by pyrolysis has been recognized as a potential strategy for commercialization. The amount of plastic waste is basically different for each country which normally refers to non-recycled plastics data; consequently, the production target will also be different. This study attempted to build a model to predict fuel production from different non-recycled plastics data. The predictive model was developed via Levenberg-Marquardt approach in feed-forward neural networks model. The optimal number of hidden neurons was selected based on the lowest total of the mean square error. The proposed model was evaluated using the statistical analysis and graphical presentation for its accuracy and reliability. The results showed that the model was capable to predict product yields from pyrolysis of non-recycled plastics with high accuracy and the output values were strongly correlated with the values in literature.

AB - The conversion of plastic waste into fuel by pyrolysis has been recognized as a potential strategy for commercialization. The amount of plastic waste is basically different for each country which normally refers to non-recycled plastics data; consequently, the production target will also be different. This study attempted to build a model to predict fuel production from different non-recycled plastics data. The predictive model was developed via Levenberg-Marquardt approach in feed-forward neural networks model. The optimal number of hidden neurons was selected based on the lowest total of the mean square error. The proposed model was evaluated using the statistical analysis and graphical presentation for its accuracy and reliability. The results showed that the model was capable to predict product yields from pyrolysis of non-recycled plastics with high accuracy and the output values were strongly correlated with the values in literature.

UR - http://www.scopus.com/inward/record.url?scp=85075576606&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85075576606&partnerID=8YFLogxK

U2 - 10.3390/polym11111853

DO - 10.3390/polym11111853

M3 - Article

AN - SCOPUS:85075576606

VL - 11

JO - Polymers

JF - Polymers

SN - 2073-4360

IS - 11

M1 - 1853

ER -