The present paper discusses the analysis and modeling of laboratory data regarding the mechanical characterization of hot mix asphalt (HMA) mixtures for road pavements, by means of artificial neural networks (ANNs). The HMAs investigated were produced using aggregate and bitumen of different types. Stiffness modulus (ITSM) and Marshall stability (MS) and quotient (MQ) were assumed as mechanical parameters to analyze and predict. The ANN modeling approach was characterized by multiple layers, the k-fold cross validation (CV) method, and the positive linear transfer function. The effectiveness of such an approach was verified in terms of the coeffcients of correlation (R) and mean square errors; in particular, R values were within the range 0.965–0.919 in the training phase and 0.881–0.834 in the CV testing phase, depending on the predicted parameters.
Stiffness modulus and marshall parameters of hot mix asphalts: Laboratory data modeling by artificial neural networks characterized by cross-validation
Baldo N.
Primo
;
2019-01-01
Abstract
The present paper discusses the analysis and modeling of laboratory data regarding the mechanical characterization of hot mix asphalt (HMA) mixtures for road pavements, by means of artificial neural networks (ANNs). The HMAs investigated were produced using aggregate and bitumen of different types. Stiffness modulus (ITSM) and Marshall stability (MS) and quotient (MQ) were assumed as mechanical parameters to analyze and predict. The ANN modeling approach was characterized by multiple layers, the k-fold cross validation (CV) method, and the positive linear transfer function. The effectiveness of such an approach was verified in terms of the coeffcients of correlation (R) and mean square errors; in particular, R values were within the range 0.965–0.919 in the training phase and 0.881–0.834 in the CV testing phase, depending on the predicted parameters.File | Dimensione | Formato | |
---|---|---|---|
applsci-09-03502.pdf
accesso aperto
Tipologia:
Versione Editoriale (PDF)
Licenza:
Creative commons
Dimensione
4.13 MB
Formato
Adobe PDF
|
4.13 MB | Adobe PDF | Visualizza/Apri |
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.