Advanced approaches to hot-mix asphalt dynamic modulus prediction

The dynamic modulus (|E*|) is one of the primary hot-mix asphalt (HMA) material property inputs at all three hierarchical levels in the new Mechanistic-empirical pavement design guide (MEPDG). The existing |E*| prediction mod- els were developed mainly from regression analysis of an |E*| database obtained from laboratory testing over many years and, in general, lack the necessary accuracy for making reliable predictions. This paper describes the development of a simplified HMA |E*| prediction model employing artificial neural network (ANN) methodology. The intelligent |E*| pre- diction models were developed using the latest comprehensive |E*| database that is available to researchers (from National Cooperative Highway Research Program Report 547) containing 7400 data points from 346 HMA mixtures. The ANN model predictions were compared with the Hirsch |E*| prediction model, which has a logical structure and a relatively sim- ple prediction model in terms of the number of input parameters needed with respect to the existing |E*| models. The ANN-based |E*| predictions showed significantly higher accuracy compared with the Hirsch model predictions. The sensi- tivity of input variables to the ANN model predictions were also examined and discussed. Resume´ : Le module dynamique (|E*|) est l'une des principales proprietesd u melange d'asphalte achaud utilisee en en- tree aux trois niveaux hierarchiques dans le nouveau guide de conception mecanisto-empirique des chaussees (« Mechanis- tic-empirical pavement design guide »). Les modeles actuels de prediction de |E*| sont principalement developpesal'aide d'analyses de regression de bases de donnees de |E*| obtenues apartir de tests en laboratoire sur de nombreuses annees. Ils manquent en general de la precision necessaire pour faire des predictions fiables. Cet article decrit la mise au point d'un modele de prediction simplifiedu |E*| du melange d'asphalte achaud qui emploie la methodologie des reseaux de neurones artificiels (RNA). Les modeles de prediction intelligents de |E*| ont etedeveloppes en utilisant la base de don- nees complete de |E*| la plus recente (rapport n o 547 du National Cooperative Highway Research Program) ala disposition des chercheurs et contenant 7400 exemples provenant de 346 melanges d'asphalte a chaud. Les predictions de |E*| a partir du modele des RNA ont etecomparees acelles du modele de Hirsch, lequel a une structure logique et un modele de pre´- diction relativement simple en termes du nombre de parametres necessaires en entree comparativement aux autres modeles de prediction de |E*| existants. Les predictions de |E*| fondees sur le modele des RNA ont montreune precision significa- tivement plus elevee comparativement acelles du modele de Hirsch. La sensibilitedes variables d'entree aux predictions du modele des RNA a aussi eteexaminee et discutee. Mots-cles: module dynamique (|E*|), asphalte, reseaux de neurones artificiels, modele de prediction, guide de conception mecanisto-empirique des chaussees. (Traduit par la Redaction)