Application of artificial neural networks for estimating dynamic modulus of asphalt concrete

Maryam Sadat Sakhaei Far, B. Shane Underwood, S. Ranji Ranjithan, Y. Richard Kim, Newton Jackson

Research output: Contribution to journalArticle

30 Citations (Scopus)

Abstract

This paper presents outcomes from a research effort to develop models for estimating the dynamic modulus (|E*|) of hot-mix asphalt (HMA) layers on long-term pavement performance test sections. The goal of the work is the development of a new, rational, and effective set of dynamic modulus |E *| predictive models for HMA mixtures. These predictive models use artificial neural networks (ANNs) trained with the same set of parameters used in other popular predictive equations: the modified Witczak and Hirsch models. The main advantage of using ANNs for predicting |E*| is that an ANN can be created for different sets of variables without knowing the form of the predictive relationship a priori. The primary disadvantage of ANNs is the difficulty in predicting responses when the inputs are outside of the training database (i.e., extrapolation). To overcome this shortcoming, a large data set that covers the complete range of potential input conditions is needed. For this study, modulus values from multiple mixtures and binders were required and were assembled from existing national efforts and from data obtained at North Carolina State University. The data consisted of measured moduli from both modified and unmodified mixtures from numerous geographical locations across the United States. Prediction models were developed by using a portion of the data from these databases and then verified by using the remaining data in the databases. When these new ANN models are used, the results show that the predicted and measured |E*| values are in close agreement.

Original languageEnglish (US)
Pages (from-to)173-186
Number of pages14
JournalTransportation Research Record
Issue number2127
DOIs
StatePublished - 2009
Externally publishedYes

Fingerprint

Asphalt concrete
Neural networks
Asphalt mixtures
Asphalt
Extrapolation
Pavements
Binders

ASJC Scopus subject areas

  • Civil and Structural Engineering
  • Mechanical Engineering

Cite this

Far, M. S. S., Underwood, B. S., Ranjithan, S. R., Kim, Y. R., & Jackson, N. (2009). Application of artificial neural networks for estimating dynamic modulus of asphalt concrete. Transportation Research Record, (2127), 173-186. https://doi.org/10.3141/2127-20

Application of artificial neural networks for estimating dynamic modulus of asphalt concrete. / Far, Maryam Sadat Sakhaei; Underwood, B. Shane; Ranjithan, S. Ranji; Kim, Y. Richard; Jackson, Newton.

In: Transportation Research Record, No. 2127, 2009, p. 173-186.

Research output: Contribution to journalArticle

Far, Maryam Sadat Sakhaei ; Underwood, B. Shane ; Ranjithan, S. Ranji ; Kim, Y. Richard ; Jackson, Newton. / Application of artificial neural networks for estimating dynamic modulus of asphalt concrete. In: Transportation Research Record. 2009 ; No. 2127. pp. 173-186.
@article{ee182e6db437435b8103409161cac50a,
title = "Application of artificial neural networks for estimating dynamic modulus of asphalt concrete",
abstract = "This paper presents outcomes from a research effort to develop models for estimating the dynamic modulus (|E*|) of hot-mix asphalt (HMA) layers on long-term pavement performance test sections. The goal of the work is the development of a new, rational, and effective set of dynamic modulus |E *| predictive models for HMA mixtures. These predictive models use artificial neural networks (ANNs) trained with the same set of parameters used in other popular predictive equations: the modified Witczak and Hirsch models. The main advantage of using ANNs for predicting |E*| is that an ANN can be created for different sets of variables without knowing the form of the predictive relationship a priori. The primary disadvantage of ANNs is the difficulty in predicting responses when the inputs are outside of the training database (i.e., extrapolation). To overcome this shortcoming, a large data set that covers the complete range of potential input conditions is needed. For this study, modulus values from multiple mixtures and binders were required and were assembled from existing national efforts and from data obtained at North Carolina State University. The data consisted of measured moduli from both modified and unmodified mixtures from numerous geographical locations across the United States. Prediction models were developed by using a portion of the data from these databases and then verified by using the remaining data in the databases. When these new ANN models are used, the results show that the predicted and measured |E*| values are in close agreement.",
author = "Far, {Maryam Sadat Sakhaei} and Underwood, {B. Shane} and Ranjithan, {S. Ranji} and Kim, {Y. Richard} and Newton Jackson",
year = "2009",
doi = "10.3141/2127-20",
language = "English (US)",
pages = "173--186",
journal = "Transportation Research Record",
issn = "0361-1981",
publisher = "US National Research Council",
number = "2127",

}

TY - JOUR

T1 - Application of artificial neural networks for estimating dynamic modulus of asphalt concrete

AU - Far, Maryam Sadat Sakhaei

AU - Underwood, B. Shane

AU - Ranjithan, S. Ranji

AU - Kim, Y. Richard

AU - Jackson, Newton

PY - 2009

Y1 - 2009

N2 - This paper presents outcomes from a research effort to develop models for estimating the dynamic modulus (|E*|) of hot-mix asphalt (HMA) layers on long-term pavement performance test sections. The goal of the work is the development of a new, rational, and effective set of dynamic modulus |E *| predictive models for HMA mixtures. These predictive models use artificial neural networks (ANNs) trained with the same set of parameters used in other popular predictive equations: the modified Witczak and Hirsch models. The main advantage of using ANNs for predicting |E*| is that an ANN can be created for different sets of variables without knowing the form of the predictive relationship a priori. The primary disadvantage of ANNs is the difficulty in predicting responses when the inputs are outside of the training database (i.e., extrapolation). To overcome this shortcoming, a large data set that covers the complete range of potential input conditions is needed. For this study, modulus values from multiple mixtures and binders were required and were assembled from existing national efforts and from data obtained at North Carolina State University. The data consisted of measured moduli from both modified and unmodified mixtures from numerous geographical locations across the United States. Prediction models were developed by using a portion of the data from these databases and then verified by using the remaining data in the databases. When these new ANN models are used, the results show that the predicted and measured |E*| values are in close agreement.

AB - This paper presents outcomes from a research effort to develop models for estimating the dynamic modulus (|E*|) of hot-mix asphalt (HMA) layers on long-term pavement performance test sections. The goal of the work is the development of a new, rational, and effective set of dynamic modulus |E *| predictive models for HMA mixtures. These predictive models use artificial neural networks (ANNs) trained with the same set of parameters used in other popular predictive equations: the modified Witczak and Hirsch models. The main advantage of using ANNs for predicting |E*| is that an ANN can be created for different sets of variables without knowing the form of the predictive relationship a priori. The primary disadvantage of ANNs is the difficulty in predicting responses when the inputs are outside of the training database (i.e., extrapolation). To overcome this shortcoming, a large data set that covers the complete range of potential input conditions is needed. For this study, modulus values from multiple mixtures and binders were required and were assembled from existing national efforts and from data obtained at North Carolina State University. The data consisted of measured moduli from both modified and unmodified mixtures from numerous geographical locations across the United States. Prediction models were developed by using a portion of the data from these databases and then verified by using the remaining data in the databases. When these new ANN models are used, the results show that the predicted and measured |E*| values are in close agreement.

UR - http://www.scopus.com/inward/record.url?scp=76149113625&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=76149113625&partnerID=8YFLogxK

U2 - 10.3141/2127-20

DO - 10.3141/2127-20

M3 - Article

AN - SCOPUS:76149113625

SP - 173

EP - 186

JO - Transportation Research Record

JF - Transportation Research Record

SN - 0361-1981

IS - 2127

ER -