Engineering characteristics of nanosilica/polymer-modified bitumen and predicting their rheological properties using multilayer perceptron neural network model

Nur Izzi Md Yusoff, Dhawo Ibrahim Alhamali, Ahmad Nazrul Hakimi Ibrahim, Sri Atmaja P. Rosyidi, Norhidayah Abdul Hassan

Research output: Contribution to journalArticle

4 Citations (Scopus)

Abstract

This study examines the effect of mixing varying percentages of nano-silica (NS), i.e. 2, 4 and 6% (by weight of polymer-modified bitumen, PMB) with PMB, in unaged and aged conditions. The Fourier transform infrared spectroscopy, x-ray diffraction, scanning electron microscopy and dynamic shear rheometer were used to determine chemical, microstructure and rheological properties of the binders, respectively. An artificial neural network (ANN) model, known as the multilayer perceptron neural networks model with three different algorithms namely; Levenberg-Marquardt (LM), scaled conjugate gradient (SCG), and gradient descent with adaptive back propagation (GDA) were used to predict the rheological properties of binders. The results indicate that adding NS to PMB may weaken the binders and delay their ageing. The amorphous structures of NS-PMBs remain unchanged and no new crystalline phase was formed when varying percentages of NS was added to PMB. Extreme heat caused a marked increase in the complex modulus of NS-PMB6 while low temperatures reduced its complex modulus. This resulted in enhanced resistance to the rutting and fatigue parameters. Adding higher amounts of NS particles to PMB also improved the viscoelastic properties and resistance to the ageing conditions of NS-PMB6. In terms of modeling, it was found that the most suitable algorithms and neurons number in the hidden layer for the ANN-Unaged model is LM algorithm and 11 neurons. For ANN-RTFOT and ANN-PAV models, the optimum algorithms and neurons number in hidden layer is SGC algorithm with 11 neurons and LM with 9 neurons respectively. The R-value (>0.95) for all models show a good agreement between measured and predicted data. It was concluded that the ANNs could be used as an accurate, fast and practical method for researchers and engineers to predict the phase angle and complex modulus of NS-PMBs.

Original languageEnglish
Pages (from-to)781-799
Number of pages19
JournalConstruction and Building Materials
Volume204
DOIs
Publication statusPublished - 20 Apr 2019

Fingerprint

asphalt
Multilayer neural networks
Silicon Dioxide
Polymers
Silica
Neural networks
Neurons
Binders
Aging of materials
Rheometers
Backpropagation

Keywords

  • Artificial neural network (ANN)
  • Chemical
  • Microstructure
  • Nanosilica
  • Polymer-modified bitumen (PMB)
  • Rheology

ASJC Scopus subject areas

  • Civil and Structural Engineering
  • Building and Construction
  • Materials Science(all)

Cite this

Engineering characteristics of nanosilica/polymer-modified bitumen and predicting their rheological properties using multilayer perceptron neural network model. / Md Yusoff, Nur Izzi; Ibrahim Alhamali, Dhawo; Ibrahim, Ahmad Nazrul Hakimi; Rosyidi, Sri Atmaja P.; Abdul Hassan, Norhidayah.

In: Construction and Building Materials, Vol. 204, 20.04.2019, p. 781-799.

Research output: Contribution to journalArticle

Md Yusoff, Nur Izzi ; Ibrahim Alhamali, Dhawo ; Ibrahim, Ahmad Nazrul Hakimi ; Rosyidi, Sri Atmaja P. ; Abdul Hassan, Norhidayah. / Engineering characteristics of nanosilica/polymer-modified bitumen and predicting their rheological properties using multilayer perceptron neural network model. In: Construction and Building Materials. 2019 ; Vol. 204. pp. 781-799.
@article{1a5762f92c154da18174cb4abb7240c9,
title = "Engineering characteristics of nanosilica/polymer-modified bitumen and predicting their rheological properties using multilayer perceptron neural network model",
abstract = "This study examines the effect of mixing varying percentages of nano-silica (NS), i.e. 2, 4 and 6{\%} (by weight of polymer-modified bitumen, PMB) with PMB, in unaged and aged conditions. The Fourier transform infrared spectroscopy, x-ray diffraction, scanning electron microscopy and dynamic shear rheometer were used to determine chemical, microstructure and rheological properties of the binders, respectively. An artificial neural network (ANN) model, known as the multilayer perceptron neural networks model with three different algorithms namely; Levenberg-Marquardt (LM), scaled conjugate gradient (SCG), and gradient descent with adaptive back propagation (GDA) were used to predict the rheological properties of binders. The results indicate that adding NS to PMB may weaken the binders and delay their ageing. The amorphous structures of NS-PMBs remain unchanged and no new crystalline phase was formed when varying percentages of NS was added to PMB. Extreme heat caused a marked increase in the complex modulus of NS-PMB6 while low temperatures reduced its complex modulus. This resulted in enhanced resistance to the rutting and fatigue parameters. Adding higher amounts of NS particles to PMB also improved the viscoelastic properties and resistance to the ageing conditions of NS-PMB6. In terms of modeling, it was found that the most suitable algorithms and neurons number in the hidden layer for the ANN-Unaged model is LM algorithm and 11 neurons. For ANN-RTFOT and ANN-PAV models, the optimum algorithms and neurons number in hidden layer is SGC algorithm with 11 neurons and LM with 9 neurons respectively. The R-value (>0.95) for all models show a good agreement between measured and predicted data. It was concluded that the ANNs could be used as an accurate, fast and practical method for researchers and engineers to predict the phase angle and complex modulus of NS-PMBs.",
keywords = "Artificial neural network (ANN), Chemical, Microstructure, Nanosilica, Polymer-modified bitumen (PMB), Rheology",
author = "{Md Yusoff}, {Nur Izzi} and {Ibrahim Alhamali}, Dhawo and Ibrahim, {Ahmad Nazrul Hakimi} and Rosyidi, {Sri Atmaja P.} and {Abdul Hassan}, Norhidayah",
year = "2019",
month = "4",
day = "20",
doi = "10.1016/j.conbuildmat.2019.01.203",
language = "English",
volume = "204",
pages = "781--799",
journal = "Construction and Building Materials",
issn = "0950-0618",
publisher = "Elsevier Limited",

}

TY - JOUR

T1 - Engineering characteristics of nanosilica/polymer-modified bitumen and predicting their rheological properties using multilayer perceptron neural network model

AU - Md Yusoff, Nur Izzi

AU - Ibrahim Alhamali, Dhawo

AU - Ibrahim, Ahmad Nazrul Hakimi

AU - Rosyidi, Sri Atmaja P.

AU - Abdul Hassan, Norhidayah

PY - 2019/4/20

Y1 - 2019/4/20

N2 - This study examines the effect of mixing varying percentages of nano-silica (NS), i.e. 2, 4 and 6% (by weight of polymer-modified bitumen, PMB) with PMB, in unaged and aged conditions. The Fourier transform infrared spectroscopy, x-ray diffraction, scanning electron microscopy and dynamic shear rheometer were used to determine chemical, microstructure and rheological properties of the binders, respectively. An artificial neural network (ANN) model, known as the multilayer perceptron neural networks model with three different algorithms namely; Levenberg-Marquardt (LM), scaled conjugate gradient (SCG), and gradient descent with adaptive back propagation (GDA) were used to predict the rheological properties of binders. The results indicate that adding NS to PMB may weaken the binders and delay their ageing. The amorphous structures of NS-PMBs remain unchanged and no new crystalline phase was formed when varying percentages of NS was added to PMB. Extreme heat caused a marked increase in the complex modulus of NS-PMB6 while low temperatures reduced its complex modulus. This resulted in enhanced resistance to the rutting and fatigue parameters. Adding higher amounts of NS particles to PMB also improved the viscoelastic properties and resistance to the ageing conditions of NS-PMB6. In terms of modeling, it was found that the most suitable algorithms and neurons number in the hidden layer for the ANN-Unaged model is LM algorithm and 11 neurons. For ANN-RTFOT and ANN-PAV models, the optimum algorithms and neurons number in hidden layer is SGC algorithm with 11 neurons and LM with 9 neurons respectively. The R-value (>0.95) for all models show a good agreement between measured and predicted data. It was concluded that the ANNs could be used as an accurate, fast and practical method for researchers and engineers to predict the phase angle and complex modulus of NS-PMBs.

AB - This study examines the effect of mixing varying percentages of nano-silica (NS), i.e. 2, 4 and 6% (by weight of polymer-modified bitumen, PMB) with PMB, in unaged and aged conditions. The Fourier transform infrared spectroscopy, x-ray diffraction, scanning electron microscopy and dynamic shear rheometer were used to determine chemical, microstructure and rheological properties of the binders, respectively. An artificial neural network (ANN) model, known as the multilayer perceptron neural networks model with three different algorithms namely; Levenberg-Marquardt (LM), scaled conjugate gradient (SCG), and gradient descent with adaptive back propagation (GDA) were used to predict the rheological properties of binders. The results indicate that adding NS to PMB may weaken the binders and delay their ageing. The amorphous structures of NS-PMBs remain unchanged and no new crystalline phase was formed when varying percentages of NS was added to PMB. Extreme heat caused a marked increase in the complex modulus of NS-PMB6 while low temperatures reduced its complex modulus. This resulted in enhanced resistance to the rutting and fatigue parameters. Adding higher amounts of NS particles to PMB also improved the viscoelastic properties and resistance to the ageing conditions of NS-PMB6. In terms of modeling, it was found that the most suitable algorithms and neurons number in the hidden layer for the ANN-Unaged model is LM algorithm and 11 neurons. For ANN-RTFOT and ANN-PAV models, the optimum algorithms and neurons number in hidden layer is SGC algorithm with 11 neurons and LM with 9 neurons respectively. The R-value (>0.95) for all models show a good agreement between measured and predicted data. It was concluded that the ANNs could be used as an accurate, fast and practical method for researchers and engineers to predict the phase angle and complex modulus of NS-PMBs.

KW - Artificial neural network (ANN)

KW - Chemical

KW - Microstructure

KW - Nanosilica

KW - Polymer-modified bitumen (PMB)

KW - Rheology

UR - http://www.scopus.com/inward/record.url?scp=85061079833&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85061079833&partnerID=8YFLogxK

U2 - 10.1016/j.conbuildmat.2019.01.203

DO - 10.1016/j.conbuildmat.2019.01.203

M3 - Article

AN - SCOPUS:85061079833

VL - 204

SP - 781

EP - 799

JO - Construction and Building Materials

JF - Construction and Building Materials

SN - 0950-0618

ER -