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.

Construction Quality Control of Unbound Base Course using Light Weight Deflectometer where Reclaimed Asphalt Pavement Aggregate is Used as an Example

Reclaimed asphalt pavement (RAP) is already being recycled as a construction and building material. One of the commonly considered applications is to create an unbound aggregate from this material. However, since the particles of RAP have binder coatings, traditional quality control procedures applied during construction such as use of a nuclear density gauge does not provide accurate results. Therefore there is a need to find another method that can be applied during construction to confirm that the placement in the field meets the design criteria. For this reason, in this study, the suitability of using light weight deflectometer (LWD) has been investigated. The presented methodology outlines how to implement the use of LWD to create a target modulus in the laboratory as part of design criteria and compare with the field measurements. In the field, depending on the thickness of the constructed aggregate layer, the LWD measurements may be influenced by more than just the layer of interest. The presented methodology also provides a solution for such multilayer conditions. Although the study primarily focuses on using RAP as the investigated material, the methodology developed in this study can be applied to any type of unbound aggregate as demonstrated in this study.

Applicability of Modified University of Illinois at Urbana–Champaign Model for Unbound Aggregate Material with Different Water Content

This paper proposes a modified University of Illinois at Urbana–Champaign (UIUC) model to predict permanent deformation behavior of unbound aggregate materials. Most existing models relate permanent deformation to resilient properties, whereas the UIUC model treats shear strength as a critical factor in permanent deformation behavior. Three types of test, monotonic shearing test, cyclic axial loading test, and cyclic axial and shear loading test, were conducted by multi-ring shear apparatus on two kinds of parallel grading aggregate materials, natural crusher-run and recycled crusher-run obtained from demolished concrete structure. Test results demonstrate that shear strength is the core factor in permanent deformation behavior, compared with resilient properties, and principal stress axis rotation (PSAR) greatly increases the permanent deformation. By considering the effect of PSAR on permanent deformation, a new parameter, ( Rs)ave, is added to the conventional UIUC model to modify it. Regression analysis results verify that the modified UIUC model has good applicability for predicting permanent deformation of aggregates with different water contents and stress states, and with and without PSAR. The modified UIUC model builds a relation between test results with and without PSAR. A simple framework is also proposed for predicting permanent deformation in flexible pavement structures based on the modified UIUC model.

Evaluation of Unbound Aggregate Base Layers using Moisture Monitoring Data

The behaviors of unbound aggregate base (UAB) and subgrade layers are considerably affected by seasonal moisture fluctuations which ultimately affect both their load-bearing capacity and the overall performance of the pavement structure. As part of an effort towards designing optimal performing pavements, this study was undertaken to evaluate, characterize, and quantify the effects of moisture and temperature variations on UAB and subgrade materials commonly used in Minnesota. The scope included analyses of subsurface moisture and temperature measurements and characterization of moisture variation in multiple instrumented pavement sections. Key findings indicated that dense-graded aggregate base materials with high quality crushed aggregates and lower fine particles were more resistant to seasonal moisture variations. By contrast, the subbase and subgrade materials exhibited considerable sensitivity to seasonal moisture variations. The subgrade layers, in particular, were found to operate in fully saturated conditions for more than half of their service life. Overall, the study results are a valuable contribution to establishing guidelines for laboratory testing and designing optimal performing pavement structures.