Analysis of the Mechanical Behaviour of Asphalt Concretes Using Artificial Neural Networks

Abstract

The current paper deals with the numerical prediction of the mechanical response of asphalt concretes for road pavements, using artificial neural networks (ANNs). The asphalt concrete mixes considered in this study have been prepared with a diabase aggregate skeleton and two different types of bitumen, namely, a conventional bituminous binder and a polymer-modified one. The asphalt concretes were produced both in a road materials laboratory and in an asphalt concrete production plant. The mechanical behaviour of the mixes was investigated in terms of Marshall stability, flow, quotient, and moreover by the stiffness modulus. The artificial neural networks used for the numerical analysis of the experimental data, of the feedforward type, were characterized by one hidden layer and 10 artificial neurons. The results have been extremely satisfactory, with coefficients of correlation in the testing phase within the range 0.98798–0.91024, depending on the considered model, thus demonstrating the feasibility to apply ANN modelization to predict the mechanical and performance response of the asphalt concretes investigated. Furthermore, a closed-form equation has been provided for each of the four ANN models developed, assuming as input parameters the production process, the bitumen type and content, the filler/bitumen ratio, and the volumetric properties of the mixes. Such equations allow any other researcher to predict the mechanical parameter of interest, within the framework of the present study.

Stiffness Modulus and Marshall Parameters of Hot Mix Asphalts: Laboratory Data Modeling by Artificial Neural Networks Characterized by Cross-Validation

“…With such an approach, the artificial network learns to recognize the implicit relationship between the input and target and can provide a solution to new input data. A detailed description of the structure of feedforward networks, the computational process performed by the neuron, and the supervised learning has previously been discussed [66].…”

“…In general, the closer the value of R is to the unity, the stronger the results of the linear relation between t and y, thus confirming that the training has been completed successfully (if R 1 for the training data set) and that the degree of generalization achieved can be considered optimal (if R 1 for the testing data set). The mean squared error and the correlation coefficient have already been used in previous performance analysis of some ANNs designed to predict the mechanical parameters of HMA mixtures [65,66,[72][73][74][75][76]90].…”

“…Indeed, in recent years, ANNs have arisen in scientific research as a powerful numerical technique for data analysis [64], even in the pavement-engineering field. Tapkın et al [65] and Baldo et al [66] verified the possibility of fitting Marshall test results of bituminous mixes to provide predictive equations that can be used to quicken the empirical Marshall mix design; nevertheless, such neural models are not mechanistically based and for this reason, they are considered as "black box" methods. However, the so called "black box" principle is basically based on a nonlinear fitting approach, as it has previously been widely discussed [66].…”

“…Tapkın et al [65] and Baldo et al [66] verified the possibility of fitting Marshall test results of bituminous mixes to provide predictive equations that can be used to quicken the empirical Marshall mix design; nevertheless, such neural models are not mechanistically based and for this reason, they are considered as "black box" methods. However, the so called "black box" principle is basically based on a nonlinear fitting approach, as it has previously been widely discussed [66]. Furthermore, even without a physical basis, such approaches can be useful to reduce the number of laboratory tests required by the Marshall mix design, which is still widely adopted in many asphalt laboratories [67][68][69][70][71].…”

Symmetric Performance Analysis for Mechanical Properties of Sustainable Asphalt Materials under Varying Temperature Conditions: An Application of DT and NDT Digital Techniques

“…A fast and effective method has been developed to analyzed the elastic behavior of the top layer of the road surface [16]. The stability of asphalt concrete can be analyzed by the application of Marshall stability [17] and ultrasonic pulse velocity methods [18]. Marshall stability is an extensively used method throughout the world, which is although an insurmountable limitation, expensive and time-consuming process [19,20].The non-destructive technique (NDT) has one of the most reliable methods to determine the expected quality of the constructed pavement.…”