1,720,973 research outputs found
Stiffness modulus and marshall parameters of hot mix asphalts: Laboratory data modeling by artificial neural networks characterized by cross-validation
Full text linkThe 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
Numerical characterization of high modulus asphalt concrete containing RAP: A comparison among optimized shallow neural models
Full text linkKnowing the relationship between the stiffness modulus and the empirical mechanical characteristics of asphalt concrete, road engineers may predict the expected results of costly laboratory tests and save both time and financial resources in the mix design phase. In fact, such a model would make it possible to assess a priori whether the stiffness of a specific mixture, characterised in the laboratory only by the common Marshall test, is suitable for the level of service required by the road pavement under analysis. In this study, 54 Marshall test specimens of high modulus asphalt concrete were prepared and tested in the laboratory to determine an empirical relationship between the stiffness modulus and Marshall stability by means of shallow artificial neural networks. Part out of these mixtures was characterised by different types of bitumen (20/30 or 50/70 penetration grade) and percentages of used reclaimed asphalt (RAP at 20% or 30%); a polymer modified bitumen was used in the preparation of the remaining Marshall test specimens, which do not contain RAP. For the complex and laborious identification of the neural model hyperparameters, which define its architecture and algorithmic functioning, the Bayesian optimization approach has been adopted. Although the results of this methodology depend on the predefined hyperparameters variability ranges, it allows an unbiased definition of the optimal neural model characteristics to be performed by minimizing (or maximizing) a loss function. In this study, the mean square error on 5 validation folds was used as a loss function, in order to avoid a poor performance evaluation due to the small number of samples. In addition, 3 different neural training algorithms were applied to compare results and convergence times. The procedure presented in this study is a valuable guide for the development of predictive models of asphalt concretes' behaviour, even for different types of bitumen and aggregates considered here
A machine learning approach for the prediction of very thin wearing layers asphalt concretes volumetric properties and performance
No full textIn recent years, many researchers in the field of pavement engineering have worked with the aim of developing a model capable of predicting the mechanical behavior of a mixture starting from its composition's parameters. This has been done following two different approaches. The first involved the use of advanced constitutive laws based on the materials mechanics; the second, instead of being physically based, was data-driven. The present work belongs to this second context and aims to present, implement and apply a strategy to develop the optimal model for solving an assigned predictive problem. Specifically, a Machine Learning approach, a Feedforward Backpropagation Shallow Neural Network, was investigated. The objective was to correlate stiffness modulus, air voids and voids in the mineral aggregate to the mixture main composition's parameters identified in: bitumen content, particle size and a categorical variable distinguishing the bitumen type and production site. Since the maximum aggregate size is 10 mm, the sieves considered were of 10, 6.3, 2, 0.5 and 0.063-mm diameters. The present study focused on 92 variants of asphalt concretes for very thin road pavement wearing layers produced both in plant and in laboratory. Despite the wide variation ranges of each parameter considered, the optimal model returns fully satisfactory performance. The overall Pearson correlation coefficient is equal to 0.9490, also by virtue of the innovative algorithms implemented as k-fold Cross-Validation (CV) and Bayesian Optimization (BO). These algorithms have allowed on the one hand the improvement of the model's predictive performance making them more reliable and, on the other hand, the optimization of hyperparameters and architecture. The methodology developed can become an important reference in this field since it is independent from the specific predictive application. In this sense, it can help other researchers in the fine-tuning of neural models in the field of pavement engineering
Road Pavement Asphalt Concretes for Thin Wearing Layers: A Machine Learning Approach towards Stiffness Modulus and Volumetric Properties Prediction
Full text linkIn this study a novel procedure is presented for an efficient development of predictive models of road pavement asphalt concretes mechanical characteristics and volumetric properties, using shallow artificial neural networks. The problems of properly assessing the actual generalization feature of a model and avoiding the effects induced by a fixed training-test data split are addressed. Since machine learning models require a careful definition of the network hyperparameters, a Bayesian approach is presented to set the optimal model configuration. The case study covered a set of 92 asphalt concrete specimens for thin wearing layers
Preliminary assessment on the use of scrap glass to produce asphalt mixtures
No full textNowadays, increasing pressures to preserve natural aggregates and to minimize the amount of materials landfilled are forcing consideration of potential uses of waste materials in road construction and maintenance operations. This paper focus attention on possibility to use scrap glass as an aggregate in hot mix asphalt (namely “glassphalt”). The influence of glass on volumetric characteristics and resistance of HMA mixtures was analyzed through Marshall and gyratory compaction and indirect tensile tests. Glass is brittle, rich in silicon and have a smooth surface, so the key performance parameters of glassphalt concrete are resistance to raveling and to water damage: the bottle-rolling test, the Indirect Tensile Strength Ratio (ITSR) and the Cantabro test were used to evaluate them. Based on the results obtained it was possible to define the particularities of glassphalt concerning mix design and laboratory tests, as well as the effects induced in the mixture by different percentage of glass. © 2015 Taylor & Francis Group, London
Effects of reclaimed asphalt and warm mix asphalt on the availability of the road network
No full textThis repot reviews the EARN project, which was undertaken under CEDR Call2012 in order to investigate the effects of using reclaimed asphalt (RA) and/or lower temperature asphalt on the road network. The work consisted of a review of existing data on service lifetime and availability of road materials and structures, a site trial to evaluate varying proportions of RA, experimental evaluation of moisture damage and ageing in asphalt mixtures and development of an impact assessment model. The site trial involved four different mixtures containing varying proportions of RA and warm mix additive and was monitored for international roughness index, mean profile depth, corrected SCRIM Coefficient, indirect stiffness modulus, water sensitivity and indirect tensile strength, the latter with and without artificial ageing. The monitoring was extended to 40 months with two extensions to the project, when monitoring of the binder mechanical and other properties were also made.Green Open Access added to TU Delft Institutional Repository ‘You share, we take care!’ – Taverne project https://www.openaccess.nl/en/you-share-we-take-care Otherwise as indicated in the copyright section: the publisher is the copyright holder of this work and the author uses the Dutch legislation to make this work public.Pavement Engineerin
Impact of synthetic fibres on asphalt concrete mix
No full textThe use of synthetic fibres has been reported to enhance the performance of asphalt pavement materials in terms of permanent deformation, fatigue and thermal cracking. However, limited results about the benefits of synthetic fibres in the reinforced warm-mix asphaltic materials, and the exact mechanism of reinforcing the binding part in pavement structures is still unclear. In this contribution, a semi-circular bending test was per-formed by using various fibre amounts as well as fibre length inside the bituminous mix. The results indicate that the inclusion of fibre can improves the warm-mix performance. Tensile strength as the first criterion is en-hanced proportionally by increasing fibre dosage. The reinforcing effect brought by 38-mm fibre is higher than the one with 19-mm.Pavement Engineerin
Asphalt concrete mechanical behavior prediction by artificial neural networks
No full textThe current paper deals with the numerical prediction of the mechanical response of Asphalt Concretes (AC) for flexible pavements, using Artificial Neural Networks (ANN). The AC mixes considered in the study were consisted of diabase aggregates and two different types of bitumen; a conventional bituminous binder and a polymer modified one. The ACs were produced in the laboratory and in a production plant. The ACs mechanical behaviour was investigated in terms of Marshall Stability, Flow, Quotient and Stiffness Modulus. The ANN used had one hidden layer and 10 artificial neurons. The results have been extremely satisfactory, with correlation coefficients in the testing phase within the range 0.98798 – 0.91024, demonstrating the feasibility of ANN prediction models’ application. Furthermore, a closed form equation has been with input parameters the production process, the bitumen type and content, the filler/bitumen ratio and the volumetric properties of the mixes
Going Beyond Counting First Authors in Author Co-citation Analysis
Full text linkThe present study examines one of the fundamental aspects of author co-citation analysis (ACA) - the way co-citation
counts are defined. Co-citation counting provides the data on which all subsequent statistical analyses and mappings
are based, and we compare ACA results based on two different types of co-citation counting - the traditional type that
only counts the first one among a cited work's authors on the one hand and a non-traditional type that takes into
account the first 5 authors of a cited work on the other hand. Results indicate that the picture produced through this non-traditional author co-citation counting contains more coherent author groups and is therefore considerably clearer. However, this picture represents fewer specialties in the research field being studied than that produced through the traditional first-author co-citation counting when the same number of top-ranked authors is selected and analyzed. Reasons for these effects are discussed
- …
