Evaluation of ANN-Based Dynamic Modulus Models of Asphalt Mixtures: Fid-Bau Portal

Fachinformationsdienst BAUdigital

Eine Plattform für die Wissenschaft: Bauingenieurwesen, Architektur und Urbanistik

Evaluation of ANN-Based Dynamic Modulus Models of Asphalt Mixtures

Barugahare, Javilla / Amirkhanian, Armen N. / Xiao, Feipeng / Amirkhanian, Serji N.

Artificial neural network (ANN)-based dynamic modulus $| E^{*} |$ models were evaluated on South Carolina’s asphalt mixtures, the majority of which contained recycled asphalt pavement (RAP). These ANNs contained similar input variables as the NCHRP 1-40D and Hirsch regression models and were implemented in the neural network toolbox of MATLAB version R2018b. Two previously published ANN-based $| E^{*} |$ models were also evaluated on the same database. Most ANNs in the literature have been shown to predict $| E^{*} |$ with good success; however, they have not been validated outside of their original studies. The results showed that (1) ANN-based $| E^{*} |$ models performed significantly better than regression models; (2) ANNs with few input variables (either $V_{a}$ , $V_{b e f f}$ , and $G_{b}^{*}$ or VMA, VFA, and $G_{b}^{*}$ ) highly predicted $| E^{*} |$ with $R^{2} > 0.99$ on testing; (3) ANNs can accurately predict $| E^{*} |$ of recycled asphalt mixtures; (4) the validation performance of the two published ANNs on South Carolina’s asphalt mixtures was ranked fair; and (5) locally customized ANNs are more accurate in the estimation of $| E^{*} |$ than globally calibrated ANNs or regression models.

Zugriff

Zugriff prüfen

Verfügbarkeit in meiner Bibliothek prüfen

Bestellung bei Subito €

Seitennavigation

Dokumentinformationen

Ähnliche Titel

Exportieren, teilen und zitieren

Evaluation of ANN-Based Dynamic Modulus Models of Asphalt Mixtures

Barugahare, Javilla / Amirkhanian, Armen N. / Xiao, Feipeng / Amirkhanian, Serji N.

Artificial neural network (ANN)-based dynamic modulus $| E^{*} |$ models were evaluated on South Carolina’s asphalt mixtures, the majority of which contained recycled asphalt pavement (RAP). These ANNs contained similar input variables as the NCHRP 1-40D and Hirsch regression models and were implemented in the neural network toolbox of MATLAB version R2018b. Two previously published ANN-based $| E^{*} |$ models were also evaluated on the same database. Most ANNs in the literature have been shown to predict $| E^{*} |$ with good success; however, they have not been validated outside of their original studies. The results showed that (1) ANN-based $| E^{*} |$ models performed significantly better than regression models; (2) ANNs with few input variables (either $V_{a}$ , $V_{b e f f}$ , and $G_{b}^{*}$ or VMA, VFA, and $G_{b}^{*}$ ) highly predicted $| E^{*} |$ with $R^{2} > 0.99$ on testing; (3) ANNs can accurately predict $| E^{*} |$ of recycled asphalt mixtures; (4) the validation performance of the two published ANNs on South Carolina’s asphalt mixtures was ranked fair; and (5) locally customized ANNs are more accurate in the estimation of $| E^{*} |$ than globally calibrated ANNs or regression models.

Evaluation of ANN-Based Dynamic Modulus Models of Asphalt Mixtures

Barugahare, Javilla / Amirkhanian, Armen N. / Xiao, Feipeng / Amirkhanian, Serji N.

Artificial neural network (ANN)-based dynamic modulus $| E^{*} |$ models were evaluated on South Carolina’s asphalt mixtures, the majority of which contained recycled asphalt pavement (RAP). These ANNs contained similar input variables as the NCHRP 1-40D and Hirsch regression models and were implemented in the neural network toolbox of MATLAB version R2018b. Two previously published ANN-based $| E^{*} |$ models were also evaluated on the same database. Most ANNs in the literature have been shown to predict $| E^{*} |$ with good success; however, they have not been validated outside of their original studies. The results showed that (1) ANN-based $| E^{*} |$ models performed significantly better than regression models; (2) ANNs with few input variables (either $V_{a}$ , $V_{b e f f}$ , and $G_{b}^{*}$ or VMA, VFA, and $G_{b}^{*}$ ) highly predicted $| E^{*} |$ with $R^{2} > 0.99$ on testing; (3) ANNs can accurately predict $| E^{*} |$ of recycled asphalt mixtures; (4) the validation performance of the two published ANNs on South Carolina’s asphalt mixtures was ranked fair; and (5) locally customized ANNs are more accurate in the estimation of $| E^{*} |$ than globally calibrated ANNs or regression models.

Zugriff

Zugriff prüfen

Verfügbarkeit in meiner Bibliothek prüfen

Bestellung bei Subito €

Seitennavigation

Dokumentinformationen

Ähnliche Titel

Exportieren, teilen und zitieren

Dokumentinformationen

Titel:

Evaluation of ANN-Based Dynamic Modulus Models of Asphalt Mixtures

Beteiligte:

Barugahare, Javilla (Autor:in) / Amirkhanian, Armen N. (Autor:in) / Xiao, Feipeng (Autor:in) / Amirkhanian, Serji N. (Autor:in)

Erschienen in:

Journal of Materials in Civil Engineering ; 33

Erscheinungsdatum:

23.03.2021

ISSN:

0899-1561 , 1943-5533

DOI:

https://doi.org/10.1061/(ASCE)MT.1943-5533.0003721

Medientyp:

Aufsatz (Zeitschrift)

Format:

Elektronische Ressource

Sprache:

Unbekannt

Ähnliche Titel

Evaluation of Micromechanical Models for Predicting Dynamic Modulus of Asphalt Mixtures

Shu, Xiang / Huang, Baoshan | ASCE | 2010

Evaluation of Micromechanical Models for Predicting Dynamic Modulus of Asphalt Mixtures

Shu, X. / Huang, B. / American Society of Civil Engineers | British Library Conference Proceedings | 2010

Dynamic Modulus of Asphalt Treated Mixtures

Xiaoge, Tian / Bin, Huang | ASCE | 2009

Evaluation of the MEPDG Dynamic Modulus Prediction Models for Asphalt Concrete Mixtures

El-Badawy, S. M. / Awed, A. / Bayomy, F. M. | ASCE | 2011

Dynamic Modulus of Asphalt Treated Mixtures

Xiaoge, T. / Bin, H. / American Society of Civil Engineers | British Library Conference Proceedings | 2009