In this paper, a procedure for estimation of effective modulus of a multilayered hot mix asphalt (HMA) pavement using intelligent compaction (IC) is investigated. The study is conducted during the construction of an interstate highway (I-35) in Norman, OK. A complete coverage of the level of compaction of each of the asphalt pavement layers was recorded using the intelligent asphalt compaction analyzer (IACA). The collected IACA data allow determination of the level of compaction (density) at any selected location, for each layer, and provided a set of global positioning system (GPS) coordinates. Calibration procedures have previously been tested and validated by the authors to estimate the density of different types of pavements from IACA data. In this paper, a different calibration procedure is used to measure the dynamic modulus instead of the density of a pavement using IACA. Considering the IACA estimated density, the dynamic modulus of each of the selected locations for an individual pavement layer was measured from laboratory developed master curves. Thereafter, an effective modulus of the three-layer pavement system was calculated for all of the selected locations using Odemark's method. The proposed technique was verified by conducting falling-weight deflectometer (FWD) tests at these selected locations. Analyses of the results show that the proposed intelligent compaction technique may be promising in estimating the effective modulus of the pavement layers in a non-destructive manner. In addition, the Witczak model was used to estimate moduli of each of the pavement layers. The comparison of the Witczak model with FWD revealed that the model over-predicted the modulus significantly.

While having been successfully used for soil compaction for many years, intelligent compaction (IC) technology is still relatively new for asphalt pavement construction. The potential of using intelligent compaction meter value (ICMV) for evaluating the compaction of asphalt pavements has been hindered by the fact that ICMV can be affected by many factors, which include not only roller operation parameters, but also the temperature of asphalt layer and the underlying support. Therefore, further research is necessary to improve the application of IC for the asphalt compaction. In this study, the feasibility of IC for asphalt compaction was evaluated from many aspects. Based on that, a laboratory IC technology for evaluating asphalt mixture compaction in the laboratory was also developed. In this study, one field project for soil compaction was constructed using IC technology, and a strong and stable linear relationship between ICMV and deflection could be identified when the water content of soil was consistent. After that, more field projects for asphalt compaction were constructed using the IC asphalt roller. The density of asphalt, as the most critical parameter for asphalt layers, along with other parameters, were measured and correlated with the ICMVs. Various factors such as asphalt temperature and the underlying support were considered in this study to improve the correlation between the density and ICMV. Based upon the results of correlation analyses, three IC parameters were recommended for evaluating the compaction quality of resurfacing project. In addition, the geostatistical analyses were performed to evaluate the spatial uniformity of compaction, and the cost-benefit analysis was included to demonstrate the economic benefits of IC technology. Based on the test results of field projects, the IC indices were further utilized to quantify the lab vibratory compaction for paving materials. The compaction processes in the laboratory was monitored by accelerometers. Using Discrete-Time Fourier Transform, the recorded data during compaction were analyzed to evaluate the compactability of paving materials and to further correlate to the field compaction.

Effective compaction is crucial for the performance and durability of asphalt pavement. Traditional field compaction, relying heavily on engineers' experience and test strips, sometimes could be problematic to achieve a unified pavement with a desirable density, especially with new materials. To address these challenges, Intelligent Compaction (IC) has been developed to equip the vibratory rollers with GPS, accelerometers, onboard computers, and infrared thermometers to facilitate the quality control of pavement compaction. This technology allows for real-time monitoring and visualization of pavement responses and temperatures, significantly improving compaction uniformity. However, accurately predicting pavement density remains challenging due to the multilayered pavement structure and the complex interactions between the roller drum and the viscoelastic asphalt mixture. To understand the compaction mechanism and improve the compaction quality of the asphalt pavement, a Microelectromechanical System (MEMS) sensor, SmartKli was employed to study the asphalt mixture compaction at the mesoscale. It was found that the compaction characteristics at the macroscale are closely related to the behavior of coarse aggregates at the mesoscale level. The particle rotation plays a critical role in the densification of the asphalt specimens. Utilizing the Discrete Element Model (DEM), the impact of mix design and particle property on kinematic behaviors was examined. The mixture gradation and particle size also greatly affect the aggregates' behavior during compaction. Based on the developed compaction mechanism, a new method for evaluating asphalt mixture workability was proposed, incorporating workability parameters, compaction curves, and statistical analysis of compaction data. By verifying with different asphalt types including Hot Mix Asphalt (HMA), Warm Mix Asphalt (WMA), and Recycled Plastic Modified Asphalt (RPMA), this method could effectively assess the influence of various factors like asphalt content, compaction temperature, and additives on mixture workability, aiding in optimizing mix design and construction conditions. Moreover, an innovative compaction monitoring system was developed to accurately predict the compaction conditions of the asphalt pavement. This system uses a wireless particle size sensor for data acquisition and a machine learning model for density prediction. Linking laboratory gyratory and field roller compaction data through particle kinematic behaviors, the system achieved high precision in density prediction with a prediction error of less than 0.7%. The results demonstrate that integrating AI and sensing data is effective for predicting asphalt mixture compaction. This system could significantly enhance the compaction quality of asphalt pavement and contribute to the comprehensive quality control and assurance of pavement construction.

Intelligent compaction (IC) is a construction method relatively new to the USA that uses modern vibratory rollers equipped IC components and technologies. Though used for decades in the rest of the world, the IC technology is less mature for its application in the asphalt compaction than its counter part for the soils and subbase compaction. Under the on-going FHWA/TPF IC studies, tremendous amount of knowledge has been gained on HMA IC. Components of asphalt IC include: double-drum IC rollers, roller measurement system, global position system (GPS) radio/receiver/base station, infrared temperature sensors, and integrated reporting system. Therefore, an asphalt IC roller can "adapt its behavior in response to varying situations and requirements" -being "intelligent"! There are many benefits using asphalt IC rollers. To name a few: proof rolling (mapping) to identify soft spots, achieve consistent roller patterns, monitor asphalt surface temperature (to keep up with the paver) and levels of compaction for 100% coverage area, and many more.

Intelligent Compaction (IC) technology is an innovation of roller technology that can be used to improve quality control (QC) of the asphalt pavement compaction process. It is increasingly used by the asphalt paving industry in the US. Currently, IC is being adopted by many federal and state highway agencies. Asphalt IC technology uses accelerometer - based methods to collect IC measurement values (ICMV) that relate to the stiffness of the compacted materials. Across the US, in - place asphalt density measurement is still the de facto method for acceptance as the in - place densities relate to long - term performance of asphalt pavements. Past limited research has not been successful in finding a strong correlation between ICMV and measured in - place density. To accelerate the implementation of IC technology, it is essential to further study the relationship between IC measured data and core density to assess the use of IC measurements beyond QC. This project includes extensive field studies and data analysis and modeling in order to investigate the relationship between ICMV and other IC measurements (such as pass counts, temperatures, vibration frequencies/amplitudes, direction, speed, etc.) and asphalt in - place densities. The pass - by - pass ICMV correlate well with nu clear density gauge measurements during breakdown compaction. As the final ICMV does not correlate well with core densities, the final ICMV data is not recommended to replace cores for acceptance. A n IC - based nonlinear panel data model was also developed to reasonably predict asphalt in - place density as an enhanced QC tool . Recommendation are also provided regarding future research and implementation to maximize the potential benefits of IC.

The in-situ dynamic modulus properties of asphalt mixture play a significant role in assessing pavement mechanical responses under traffic loading, determining the pavement performance and condition, and making optimized maintenance decisions. Several methods, such as the falling weight deflectometer (FWD), have been utilized as a non-destructive test to back-calculate the in-situ pavement modulus and conditions; however, the FWD test can only be performed periodically and has the disadvantage of disturbing traffic due to lane-closure needs. With the recent advancement in data science and sensing technologies, the application of micro-electromechanical system (MEMS) sensors and machine learning techniques in pavement nondestructive tests has attracted more research attention. This research aims to develop an in-situ evaluation system that can automatically collect, process, and interpret data to determine the in-situ dynamic modulus of the asphalt mixture under traffic loads using embedded wireless sensors and machine learning techniques. The proposed system is a self-adaptive process and can predict in-situ dynamic modulus based only on mechanical responses and environmental conditions. Ultimately, the well-trained predictive model can be integrated into the pavement management system for the automated and cost-effective assessment of pavement conditions, facilitating informed decision-making. The research program encompasses three types of dynamic modulus experiments: laboratory uniaxial dynamic modulus tests, the one-third scale model mobile load simulator (MMLS3) tests, and in-situ dynamic modulus tests. Particle-size wireless sensors, SmartKli sensors, were implemented in the laboratory specimens and the pavements to collect data from sine wave loads and moving loads. Finite element models (FEM) were also developed and calibrated to generate pavement mechanical response data for more pavement types. The collected data and the FEM simulations were integrated into a database for a proposed adaptive data processing procedure. In addition, because the data collected by embedded sensors in infrastructure health monitoring are inevitably contaminated with noise, and the data features have a distinct discrepancy in different types of tests, a secondary objective of this research is to propose a data processing method capable of removing noises, recognizing data feature discrepancies, and extracting hidden features. An adaptive data processing procedure was developed by combining an empirical mode decomposition (EMD) method and an intrinsic mode function (IMF) selection processing to enhance the reliability of the pavement dynamic modulus prediction. Different EMD techniques were applied to decompose signals from wireless sensors embedded in the pavements. The maximum normalized cross-correlation (MNCC) and signal noise ratio (SNR) were selected as indices in the K-means classification to select the effective IMFs. The results indicated that ensemble EMD (EEMD) and multivariant EMD (MEMD) methods can extract more information from the mechanical responses and extend data dimensions. The EEMD method gives the lowest mean relative error (MRE). Therefore, the EEMD method was recommended for infrastructure data processing. The K-means method can adaptively select the effective IMFs based on the MNCC and SNR. Finally, three dynamic modulus predictive models were developed for different situations. An artificial neural network (ANN) model was developed based on the laboratory test data. This model verified that the ANN model can predict in-situ dynamic modulus. The second dynamic modulus predictive model was developed using the ensemble ANN model to improve the stability of the ANN model, which was trained and tested by the data collected from the MMLS3 test. The third model was developed to predict the dynamic modulus of various asphalt mixtures by fusing a transfer learning approach and Transformer architecture. Besides, the training database was extended with the FEM simulations. The results indicated that the ensemble ANN model is feasible and robust in predicting the dynamic modulus of the asphalt mixture in the MMLS3 test. The transfer learning model is reasonable and robust in predicting the in-situ dynamic modulus of the asphalt pavement.