A stochastic neural network based approach for metamodelling of mechanical asphalt concrete properties. Issue 1 (6th December 2023)

• Record Type: Journal Article
• Authors: Emig, Julius; Reuter, Uwe; Bolz, Paul Gustav; Leischner, Sabine; Canon Falla, Gustavo
• Is Part Of: International journal of pavement engineering. Volume 24:Issue 1(2023)
• Publication Date: 2023-12-06
• Subjects: Convolutional neural networks -- machine learning -- asphalt concrete -- dynamic modulus -- phase angle -- stochastic metamodelling; Pavements -- Design and construction -- Periodicals; Highway engineering -- Periodicals; 625.805
• DOI: 10.1080/10298436.2023.2177650
• Languages: English
• ISSNs: 1029-8436

Abstract

ABSTRACT: This study introduces a stochastic approach based on Convolutional Neural Networks (CNNs) for predicting mechanical Asphalt Concrete (AC) properties with dependency on the mixture composition, temperature and loading frequency. The underlying CNN metamodels were evaluated by a comprehensive database of AC properties with a total of 7400 dynamic modulus records. The CNN approach shows an improved accuracy compared to other state of the art machine learning approaches found in literature. Stochastic CNN based metamodels were developed to take into account the uncertainty of mechanical properties resulting from arbitrarily arranged aggregates and air voids in AC. The data used for the stochastic metamodels contain a total of 3645 dynamic modulus and phase angle values. They were obtained from microscale Finite Element (FE) simulations considering a heterogenous material composition and viscoelastic material behaviour of the AC binder. The developed stochastic CNN metamodels provide highly accurate predictions for the statistical characteristics such as mean values, standard deviations and empirical distribution functions of the dynamic modulus and the phase angle.