Deep Neural Network Models for the Prediction of the Aggregate Base Course Compaction Parameters

Laboratory tests for the estimation of the compaction parameters, namely the maximum dry density (MDD) and optimum moisture content (OMC) are time-consuming and costly. Thus, this paper employs the artificial neural network technique for the prediction of the OMC and MDD for the aggregate base course from relatively easier index properties tests. The grain size distribution, plastic limit, and liquid limits are used as the inputs for the development of the ANNs. In this study, multiple ANNs (240 ANNs) are tested to choose the optimum ANN that produces the best predictions. This paper focuses on studying the impact of three different activation functions: number of hidden layers, number of neurons per hidden layer on the predictions, and heatmaps are generated to compare the performance of every ANN with different settings. Results show that the optimum ANN hyperparameters change depending on the predicted parameter. Additionally, the hyperbolic tangent activation is the most efficient activation function as it outperforms the other two activation functions. Additionally, the simplest ANN architectures results in the best predictions, as the performance of the ANNs deteriorates with the increase in the number of hidden layers or the number of neurons per hidden layers.

Pavement Optimisation With Aggregate Base Or Asphalt Layers Stabilised With Hexagonal Geogrids

The use of hexagonal geogrids in pavement structures results in the increase of the life of designed structure. This offers the possibility to reduce the thickness of layers without reduction of pavement life, or to increase the traffic capacity of a pavement without the need to increase its thickness. This way of using geogrids in pavements design was introduced to the pavement industry by one producer of hexagonal geogrids as a Pavement Optimisation (PO) concept. It can be transformed into both economic and environmental benefits, and obviously results in savings of natural resources and reduction of carbon footprint of a project. PO with geogrids can be used both in the newly designed pavement structures, and in the asphalt overlays of the existing old pavements. Asphalt overlays enhancement with a geogrid either increases the fatigue life of overlays or allows the reduction of overlays thickness to achieve the same pavement life. In new pavements, stabilisation of aggregate base with geogrids increases the stiffness of aggregate, which increases the performance of a whole pavement. This paper presents several tests results, which confirm beneficial effects of using hexagonal geogrids in asphalt overlays and aggregate base layers, from laboratory to full scale accelerated pavement tests. Also, modifications of Mechanistic-Empirical pavement design method, which allow to implement the geogrid benefits into the design process, are discussed. Finally, case studies of pavements – newly designed and reconstructed – optimised with hexagonal geogrids are presented.

A Machine-Learning Approach for Extracting Modulus of Compacted Unbound Aggregate Base and Subgrade Materials Using Intelligent Compaction Technology

This study presents a rigorous approach for the extraction of the modulus of soil and unbound aggregate base materials for quality management using intelligent compaction (IC) technology. The proposed approach makes use of machine-learning methods in tandem with IC technology and modulus-based spot testing as a local calibration process to estimate the mechanical properties of compacted geomaterials. A calibrated three-dimensional finite element (FE) model that simulates the proof-mapping process of compacted geomaterials was used to develop a comprehensive database of responses of a wide range of single and two-layered geosystems. The database was then used to develop different inverse solvers using artificial neural networks for the estimation of the modulus from the characteristics of the roller and information about the geomaterials. Several instrumented test sites were used for the evaluation and validation of the inverse solvers. The proposed approach was found promising for the extraction of the modulus of compacted geomaterials using IC. The accuracy of the inverse solvers is enhanced if a local calibration process is incorporated as part of a quality management program that includes the use of in situ measurements using modulus-based test devices and laboratory resilient modulus testing. Moreover, compaction uniformity plays a key role in the retrieval of the modulus of geomaterials with certainty. The proposed approach fuses artificial intelligence with mechanistic solutions to position IC as a technology that is well suited for the quality management of compacted materials.

Layer Composition of Continuously Reinforced Concrete Pavement Optimized Using a Regression Analysis Method

A procedure for determining the optimized composition of layer properties for a continuously reinforced concrete pavement (CRCP) system was constructed using field tests, finite element (FE) analysis, and regression analysis methods. The field support characteristics of a rigid pavement system were investigated using a falling weight deflectometer (FWD), dynamic cone penetrometer (DCP), and a static plate load test. The subgrade layer exhibited a more uniform condition than the aggregate base, and the modulus of the subgrade reaction of the aggregate base and subgrade combination (effective k-value) was improved by about 1.5 times by introducing a 2 inch (50.8 mm) asphalt stabilized base (ASB) layer. Thereafter, FE support models describing the actual field conditions were studied. The effects of the thickness of the stabilized base layer, the elastic modulus of the stabilized base material, and the effective k-value on the composite k-value of the support system were identified using a regression analysis method, and the results showed that the variables had a similar effect when determining the composite k-value. Afterward, a procedure for selecting the layer properties for producing a suitable composite k-value was constructed, and we identified that the maximum stress in the concrete slab was induced at different levels, even with identical composite k-values. Lastly, regression relationships were derived to estimate the maximum stress in the concrete slab by considering both the support layer properties and the concrete slab. Subsequently, an algorithm for selecting an optimized layer composition of the CRCP structure was construction considering the economical aspect.

Studies on the Volumetric Stability and Mechanical Properties of Cement-Fly-Ash-Stabilized Steel Slag

The stability of steel-slag road materials remains a critical issue in their utilization as an aggregate base course. In this pursuit, the present study was envisaged to investigate the effects of fly ash on the mechanical properties and expansion behavior of cement-fly-ash-stabilized steel slag. Strength tests and expansion tests of the cement-fly-ash-stabilized steel slag with varying additions of fly ash were carried out. The results indicate that the cement-fly-ash-stabilized steel slag exhibited good mechanical properties. The expansion rate and the number of bulges of the stabilized material reduced with an increase in the addition. When the addition of fly ash was 30–60%, the stabilized material was not damaged due to expansion. Furthermore, the results of X-CT, XRD and SEM-EDS show that fly ash reacted with the expansive component of the steel slag. In addition, the macro structure of the stabilized material was found to be changed by an increase in the concentration of the fly ash, in order to improve the volumetric stability. Our study shows that the cement-fly-ash-stabilized steel slag exhibits good mechanical properties and volumetric stability with reasonable additions of fly ash.

Evaluation of thin flexible pavements under simulated aircraft traffic

A full-scale airfield pavement test section was constructed and trafficked by the U.S. Army Engineer Research and Development Center (ERDC) to evaluate the performance of relatively thin airfield pavement structures. The test section consisted of 16 test items that included three asphalt pavement thicknesses and two different aggregate base courses. The test items were subjected to simulated aircraft traffic to evaluate their response and performance to realistic aircraft loads and to evaluate the effect of reductions in tire pressure on thin asphalt pavement. Rutting behavior, pavement cracking, instrumentation response, and falling weight deflectometer response were monitored at selected traffic intervals. The results of this study were used to extend existing Department of Defense pavement design and evaluation techniques to include the evaluation of airfield pavement sections that do not meet the current criteria for aggregate base quality and minimum asphalt concrete surface thickness. These performance data were used to develop new aggregate base failure design curves using existing stress-based design methodology.