Intelligent Compaction Technology Research Articles

Detection of uniformity and spatial correlation of subgrade compaction quality based on intelligent compaction technology

Intelligent compaction uniformity and spatial correlation detection of subgrade is an important part of intelligent compaction technology. In this paper, a subgrade compaction uniformity detection method is established based on the univariate statistical normal distribution 3σ criterion, and further a subgrade compaction quality spatial correlation detection method is established by the multivariate statistical spatial semi-variance function, and finally the established subgrade compaction uniformity and spatial correlation methods are verified by field tests. The subgrade compaction uniformity and spatial correlation are detected based on field tests. The results obtained in this paper show that the 3σ criterion based on normal distribution can be used for the detection of intelligent compaction uniformity of subgrade, and the field test results are verified by this method, and all the intelligent compaction uniformity of subgrade meets the requirements; considering the construction efficiency and the influence between rollers, it is recommended that the rolling speed should be in the interval range of 2–3 m/s, and the construction spacing of rollers is maintained at 10 m and above.

An overview of the angular geomorphic lock – an anti-rutting model for sustainable road infrastructure

Sustainable road infrastructure is largely dependent on the resilience of the road foundation to withstand dynamic stresses. From Empirical to Mechanistic Empirical Pavement Design Guidelines (MEPDG), the use of unbound granular materials (UGMs) has been specified for road foundation bases for flexible roads. Rutting is a common road failure from these designs. MEPDG includes climate change factors that essentially invalidate the empirical approach. However, both design approaches still rely on the anisotropic particle interlock of UGM upon compaction, notwithstanding traditional or intelligent compaction technology. The anisotropic character of compacted UGM only exhibits vertical stiffness with the highest shear stress located in the mid layer. This makes the interface between the surface of the compacted subgrade and the bottom of the compacted subbase incompatible. Consequently, the stiffness of the UGM is satisfactory for static loads, but when these become dynamic, the inter-granular transmission of these stresses creates a new challenge, non-linearity of stress and the ensuing propensity for stress rotation. A model subbase of a road foundation was modified acknowledging the natural angle of repose of UGM. The ribbed saw tooth structure with an inherent composite anisotropic character seemed to offer significant stiffness. A three-point shear stress localisation (3-PSSL) was experimentally created with three stress levels identified within the subbase and a fourth stress level in the base. This geomorphic lock is possible by the use of an angular geo-lock compactor (AGL). Added stiffness in the road foundation should avert rutting, thereby increasing resilience and sustainability of road infrastructure, and ultimately stimulating socio-economic development. World Intellectual Property Organisation (WIPO) has documented this ongoing research as patent No. WO 2021/048590 A1 awaiting entry into The National Phase. This is Work in Progress, where particle intra-lock may invalidate particle interlock.

Investigation of Particle Rotation Characteristics and Compaction Quality Control of Asphalt Pavement Using the Discrete Element Method.

The compaction of asphalt pavement is a crucial step to ensure its service life. Although intelligent compaction technology can monitor compaction quality in real time, its application to individual asphalt surface courses still faces limitations. Therefore, it is necessary to study the compaction mechanism of asphalt pavements from the particle level to optimize intelligent compaction technology. This study constructed an asphalt pavement compaction model using the Discrete Element Method (DEM). First, the changes in pavement smoothness during the compaction process were analyzed. Second, the changes in the angular velocity of the mixture and the triaxial angular velocity (TAV) of the mortar, aggregates, and mixture during vibratory compaction were examined. Finally, the correlations between the TAV amplitude and the coordination number (CN) amplitude with the compaction degree of the mixture were investigated. This study found that vibratory compaction can significantly reduce asymmetric wave deformation, improving pavement smoothness. The mixture primarily rotates in the vertical plane during the first six passes of vibratory compaction and within the horizontal plane during the seventh pass. Additionally, TAV reveals the three-dimensional dynamic rotation characteristics of the particles, and the linear relationship between its amplitude and the pavement compaction degree aids in controlling the compaction quality of asphalt pavements. Finally, the linear relationship between CN amplitude and pavement compaction degree can predict the stability of the aggregate structure. This study significantly enhances quality control in pavement compaction and advances intelligent compaction technology development.

Research on the Coupled Dynamic Response of Vibratory Roller-Unsaturated Subgrade under Different Compaction and Moisture Content States

The dynamic response between the vibratory roller and subgrade under vibratory compaction is essential to improve the compaction quality and optimize the construction technology. Considering the nonlinear hysteresis characteristics of the subgrade in vibratory compaction, a two-degree-of-freedom viscoelastic-plastic, vibratory roller-unsaturated subgrade coupling model, is established to evaluate the effect of compaction stage and moisture content on the vibratory roller-unsaturated subgrade coupling dynamic response. The dynamic resilient modulus semi-empirical model is established based on the dynamic resilient modulus experiment by considering the matrix suction of the unsaturated subgrade and it is the basis of the vibratory roller-unsaturated subgrade coupling model to consider the moisture content influence of compaction. In addition, a plasticity index was proposed to divide the selection of coupling models to consider the influence of compaction stages. The results show that the semi-empirical model takes into account the effect of moisture content by soil–water characteristic curve and it performs well in responding to the experiment results and other experimental data in the published literature. Based on this, the vibratory roller-unsaturated subgrade coupling dynamic response varied for different compaction stages and the moisture content of the unsaturated subgrade. The compaction quality gradually improved as the increase of compaction passes and the decrease of the moisture content. However, the compaction quality of the unsaturated subgrade is weakened by over compaction and excessive moisture content and should balance the compaction operation and quality assurance of the unsaturated subgrade. The results of the research will indicate the compaction mechanism of unsaturated subgrade and provide a theoretical basis for the development of intelligent compaction technology.

Research on global optimization mechanism of intelligent compaction parameters of soil subgrade based on difference method

The global optimization mechanism plays a crucial role in enhancing construction efficiency and ensuring construction quality of soil subgrade such as building foundation or roadbed, within the context of intelligent compaction technology. There are three parts in the global optimization mechanism, which are determining the optimal work parameters, judging the compaction quality, and the feedback adjustment method. To establish a global optimization mechanism for intelligent compaction of subgrade soil, this paper developed a numerical simulation model for subgrade intelligent compaction, defined the necessary numerical simulation conditions for the global optimization mechanism of intelligent compaction. In this way, it provides a source of data for the establishment of global optimization mechanisms. Furthermore, the optimal working parameters are determined by the method of multivariate nonlinear fitting and calculating its extreme value. Meanwhile, an intelligent compaction quality judgment mechanism is established. Additionally, a feedback adjustment method for intelligent compaction was developed using the difference method to form a comprehensive global optimization mechanism. Finally, the intelligent compaction's global optimization mechanism has been validated through field experiments. The results of this study demonstrate that the boundary between low speed and medium speed rolling is 1.7 m/s. The optimal number of rolling passes is four and the ideal rolling speed ranges from 1.2 to 1.3 m/s when initial compaction degree reaches between 80 % and 90 %. The compaction degree, CMV (Compaction Meter Value) and AICV (Acceleration Intelligent Compaction Value) all exhibit a decreasing trend of subgrade compaction quality with increasing rolling speed, and the rate of decrease gradually accelerates.

Intelligent Compaction Measurement Value in Variability Control of Subgrade Compaction Quality

Intelligent compaction (IC) is an innovative and modified technology used for quality control in subgrade digital construction. However, current intelligent compaction measurement values (ICMVs) cannot provide accurate measurement of the filling layer when the strength of the underlying layer is relatively high. Experimental field tests conducted in the cut to fill subgrade were performed to collect and analyze the variability of ICMV called the vibration modulus (Evib). Furthermore, a new ICMV called the modulus of vibration compaction (Evc) that could remove the interference of the underlying layer and reveal the actual compaction state of filling layer is presented based on the theoretical analysis and numerical simulation method. It was also extracted to study the variability of the filling layer’s compaction state. The results of the above research indicate the influence of the underlying layer’s stiffness on overall compaction quality is remarkable. It was found that it is more likely to achieve the variability control of the compaction state of the filling layer by a new ICMV called Evc. The measured data, improved approaches, and associated conclusions that are presented provide valuable information for researchers and employees considering the use of IC technology.

Research on intelligent compaction stiffness index and its application based on three-degree-of-freedom elastic–plastic dynamical model

CMV (Compaction Meter Value) and stiffness coefficient ks are the two most commonly used indexes in the intelligent compaction technology for subgrade soil. However, the applicability of CMV is affected by the operation mode and the working parameters of the vibrating roller. The calculation model of stiffness coefficient ks does not consider the plastic characteristics of the soil and the data usage rate of its calculation method is low. As a result, the current ICMVs (intelligent compaction measurement values) are only applicable to the compaction quality characterization in the later stage of compaction, and the accuracy and applicability of the compaction quality characterization in the whole process of construction are low, which limits the application of intelligent compaction technology. In view of the above problems, this paper aims to establish a comprehensive stiffness coefficient index which is not affected by the operation mode of the roller, comprehensively reflects the elastic–plastic mechanical properties and has strong resistance to accidental factors, in order to provide an accurate basis for the characterization of subgrade soil compaction quality. Firstly, a numerical simulation model of subgrade soil vibrating compaction with real-time change of soil Mohr-Coulomb model parameters with triaxial strain response is established, which provides accurate data support for ICMV calculation. Secondly, the calculation model and application method of CMV and ks are analyzed. Aiming at the shortcomings of the two indexes, the comprehensive stiffness coefficient kcs reflecting the elastic–plastic characteristics of soil and its complete calculation method are established. Finally, based on the simulation data, the accuracy of kcs is verified, and the variation law of the kcs calculation model parameters and the evolution mechanism of soil elastic–plastic properties are clarified. Based on the field tests data, the accuracy of kcs is verified. The results show that the deciding coefficients between kcs and compaction degree obtained by numerical simulation and field test are R2 = 0.83 and R2 = 0.72, respectively, which are higher than that between ks and compaction degree (R2 = 0.72, R2 = 0.52) and that between CMV and compaction degree (R2 = 0.04, R2 = 0.23). The accuracy of kcs to characterize compaction quality is higher, and it can maintain high stability during field application. During the compaction process, the elastic–plastic mechanical properties of subgrade soil evolve continuously, and each parameter of kcs calculation model increases with the rolling pass.

Research on vibratory & oscillatory coexistence nonlinear dynamics based on drum-subgrade coupling model

In order to provide theoretical basis for subgrade continuous compaction monitoring technology and intelligent compaction technology, it is urgent to study the nonlinear coupling dynamics of drum and subgrade in the process of vibratory and oscillatory compaction. In this study, a nonlinear coupling dynamic model of 6-degree-of-freedom vibratory drum-subgrade is proposed, which considers the elastoplastic characteristics of the subgrade during compaction. According to the geometric and physical relationship between the drum and the subgrade in the contact area, the longitudinal dynamic contact force coefficient is derived, which establishes the coupling relationship between the drum-subgrade vertical vibration and longitudinal oscillation. Combined with the evolution law of material properties of subgrade in actual compaction operation, the nonlinear dynamic behavior of coupling system in the whole compaction period is analyzed. The results show that the chaotic compaction state in the vertical direction of the drum may occur during the full compaction cycle, which is related to the excitation parameters of the drum. Furthermore, the excitation parameters are more sensitive to the longitudinal one-cycle vibration response of the system than the vertical vibration response. Through the response characteristics of the drum and the subgrade and the bifurcation diagram of the drum, it is proved that the proposed model can effectively simulate the longitudinal-vertical nonlinear coupling characteristics of the drum and subgrade, and can provide a premise for theoretical exploration for the vibratory & oscillation compaction mode.

Development and validation of a degree of saturation prediction model using time domain reflectometry for compaction control

Compaction quality is directly related with the shear strength of soils. Inadequately compacted soils have lower shear strength that decrease the load bearing capacity and increase the differential settlement of the pavement, which may endanger safety and durability of the highways. Although intelligent compaction technology has enhanced the quality control of the compaction, conventional evaluation methods adopting sampling from random locations to determine relative compaction are extensively used in most of the earthwork projects. However, relative compaction may lead misjudgment, since the compaction energy level and the soil type in-place cannot match exactly with the given specifications of an earthwork project. Recent studies have shown that soil degree of saturation (Sr) can be utilized as an alternative control parameter for compaction quality. Sr in-place is usually determined with sand cone method. The method is time consuming as well as prone to error due to potential water seepage and deformation of soft soils. With its ability to provide remote and continuous monitoring in real time, Time Domain Reflectometry (TDR) has the potential to serve as a viable alternative method for determination Sr in-place. This research presents models developed using different calibration methods for the prediction of Sr with TDR measured dielectric permittivity. The accuracy of the models was evaluated with cross-validation. The results show that TDR is able to predict the Sr with less than ±5% deviation for 93% of the specimens in the validation set within the saturation ratio range of 0.01–0.93 cm3 cm−3 with an appropriate model.

A new approach to maximising the benefits of current intelligent compaction technology for asphalt materials

This paper investigates the correlations between asphalt density, intelligent compaction measurement values (ICMVs) and asphalt moduli obtained from different laboratory experiments at various temperatures of the asphalt mix AC14 with C320 bitumen. It was found that the influence of the density of asphalt on its modulus is primarily governed by the temperature of the asphalt mix. To examine the influence of asphalt temperature on ICMV-density correlations, a vibrating hammer instrumented with an accelerometer was employed to compact cylindrical asphalt specimens at different temperatures. The correlations between ICMVs and asphalt density at different temperatures showed that ICMVs are insensitive to the change in asphalt density at typical compaction temperatures. A practical method to maximise the benefits of the current intelligent compaction (IC) technology for quality control (QC)/quality assurance (QA) of asphalt pavements is proposed in this study. The proposed approach involves overlaying the ICMV map produced during the pre-mapping of the existing layer and the surface temperature map produced during the final roller pass of the newly-laid asphalt layer compaction to identify the most vulnerable regions for random spot density tests. The effectiveness of this approach was demonstrated for an asphalt overlay testbed compacted using an instrumented vibratory roller.

Study of Regression Algorithms and Influent Factors between Intelligent Compaction Measurement Values and In-Situ Measurement Values

Intelligent compaction (IC) technology have been used for quality control and quality assurance (QC/QA) in subgrade construction. The effective regression correlations between Intelligent Compaction Measurement Values (ICMV) and In-situ Measurement Values (ISMV, including compaction degree and subgrade modulus ELWD) are the essential prerequisite of using IC technology for QC/QA. This paper presents the results from an experimental research study that was conducted from a practical subgrade project of China to explore the regression relationships between ICMV and ISMV. Three types of ICMV, including CMV, CCV and Evib, were collected along with the corresponding positions of the rollers. Two types of ISMV, containing compaction degree and ELWD, were measured by ring sampler method and light weight deflectometer (LWD) at specified test points, respectively. Based on these data, the influences of roller parameters and subgrade properties on the regression relationships of ICMV and ISMV were investigated. In addition, linear regression and 5 nonlinear regression algorithms were compared. The results suggest that ICMV reflect the stiffness of subgrade more than reflecting the density. In the regression of ICMV and ISMV, subgrade properties are more important than roller parameters while both of them should not be neglected. The influences of underlying stiffness and roller amplitude are linear while that of roller speed and moisture content are nonlinear. Nonlinear algorithms, especially the random forest, have the better performance compared to linear algorithm. Moreover, the combination of random forest and linear algorithm can further improve the accuracy of ISMV prediction.

The pioneer of intelligent construction—An overview of the development of intelligent compaction

As the pioneer in the intelligent construction technologies (ICT) of transportation infrastructure, intelligent compaction (IC) has been applied in the infrastructure construction of various countries. It is currently the technology that best reflects the intelligence of engineering construction. This article overviews the latest developments and trends in IC. Firstly, the basic meaning of ICT is defined based on the essential characteristics of intelligent construction of transportation infrastructure, “perception, analysis, decision-making, execution” (PADE). The concept of intelligent compaction technology classification is also introduced. The PADE requirements that intelligent compaction should meet are proposed. Secondly, according to the sequence of “perception, analysis, decision-making, execution,” the workflow and key technologies of intelligent compaction are analyzed, and the mechanism of using the response of the roller to solve the modulus is given and verified. On this basis, The IC feasibility test methods, including compaction degree, compaction stability, and compaction uniformity, are briefly described. The implementation scheme of feedback control is given. Then, the use of artificial neural networks (ANN), hybrid expert systems, and reinforcement learning in intelligent compaction are briefly introduced. Finally, several extended applications of intelligent compaction are expounded, including the development ideas of intelligent road rollers and the role of intelligent compaction in virtual construction, the layer-specific mechanical parameters of fillers, etc.

Double-layered granular soil modulus extraction for intelligent compaction using extended support vector machine learning considering soil-structure interaction

Intelligent Compaction (IC) has been acquiring a growing interest in real-time quality control of compacted soil layers because of its high efficiency and full-area coverage. The current intelligent compaction technology allows the determination of the uniformity level of compaction over large areas according to the dynamic response of the roller. However, accurate real-time determination of the soil modulus during compaction based on roller acceleration has been challenging due to the multi-layered composite nature of the soil and the nonlinearities of the governing dynamic equations of motion and soil response. This study adopts a double-layered soil profile, and a three-dimensional finite element model, accounting for soil-drum interaction, is utilised for the analysis. The isotropic hardening elastoplastic hysteretic model was implemented to simulate the soil behaviour subjected to cyclic loading ranging from small to large strain amplitudes and account for stiffness degradation. The comprehensive dataset composed of the roller acceleration response and ground characteristics is then used to correlate the predicted soil modulus via an advanced machine learning approach. The adopted machine learning method incorporating Gaussian Kernel and Generalised Gegenbauer Kernel functions can reasonably predict the double-layered soil modulus during roller compaction. Additional analyses were conducted to observe the proper training size and number of iterations to achieve real-time quality control to be used by site engineers. Furthermore, the influences of the relative modulus ratio, drum length and top layer modulus on the soil surface dynamic displacement are discussed.

Real-time determination of sandy soil stiffness during vibratory compaction incorporating machine learning method for intelligent compaction

An emerging real-time ground compaction and quality control, known as intelligent compaction (IC), has been applied for efficiently optimising the full-area compaction. Although IC technology can provide real-time assessment of uniformity of the compacted area, accurate determination of the soil stiffness required for quality control and design remains challenging. In this paper, a novel and advanced numerical model simulating the interaction of vibratory drum and soil beneath is developed. The model is capable of evaluating the nonlinear behaviour of underlying soil subjected to dynamic loading by capturing the variations of damping with the cyclic shear strains and degradation of soil modulus. The interaction of the drum and the soil is simulated via the finite element method to develop a comprehensive dataset capturing the dynamic responses of the drum and the soil. Indeed, more than a thousand three-dimensional (3D) numerical models covering various soil characteristics, roller weights, vibration amplitudes and frequencies were adopted. The developed dataset is then used to train the inverse solver using an innovative machine learning approach, i.e. the extended support vector regression, to simulate the stiffness of the compacted soil by adopting drum acceleration records. Furthermore, the impacts of the amplitude and frequency of the vibration on the level of underlying soil compaction are discussed. The proposed machine learning approach is promising for real-time extraction of actual soil stiffness during compaction. Results of the study can be employed by practising engineers to interpret roller drum acceleration data to estimate the level of compaction and ground stiffness during compaction.

Compaction quality assessment of cement stabilized gravel using intelligent compaction technology—A case study

As a new compaction quality management system of road construction, the intelligent compaction (IC) technology has shown a great potential for quality control and acceptance (QC/QA) in the compaction of cement stabilized gravel (CSG) subbase. However, before it achieves a high level of technology readiness, there are some challenges to be solved. One of the critical problems is that there is no reliable correlation between IC measurement values (ICMVs) and field test measurements, which is thus focused on. The influence of moisture content on the relationships between ICMVs and density were studied. Two types of ICMVs, roller-integrated stiffness (Kb) and compaction meter value (CMV), were collected and their correlations with material compactness were established respectively. In addition, it discusses the changing pattern of compaction degree and its uniformity with roller passes. The results show that, moisture content has a significant effect on the correlation between ICMVs and compaction degree of CSG. Compared with CMV, Kb has a higher regression coefficient with the in-situ measurements. Also, it is proven that the compaction degree and uniformity of CSG do not necessarily increase with the development in the number of rolling passes. Finally, this study makes a comprehensive evaluation of the compaction quality of the test section based on the relationships between ICMVs and in-situ test results.

Assessment of Intelligent Compaction Quality Evaluation Index and Uniformity

Compaction Measurement Value (CMV) is the most widely used quality evaluation index for intelligent compaction. However, with the growth of compaction degree, CMV becomes less accurate due to increased reaction force from densified geomaterials. To solve this problem, this paper proposes a more accurate intelligent compaction quality evaluation index, acceleration intelligent compaction value (AICV). Based on field measurement data analysis, AICV turned out to be effective to elevate quality evaluation accuracy. Additionally, the singularities were detected by 3σ normal distribution in order to assess the uniformity of subgrade compaction quality. Based on the semivariogram analysis method of spatial statistics, CMV and AICV were analyzed for spatial correlation, and the influence range of intelligent compaction technology employed for subgrade was evaluated. The results from this study provide a basis for further research on precision control and uniformity analysis of intelligent compaction technology.

Intelligent compaction quality evaluation based on multi-domain analysis and artificial neural network

Intelligent compaction technology monitors the compaction quality of pavement materials in real-time by observing the sensor signals installed on the roller. At present, the existing intelligent compaction detection methods cannot always accurately evaluate the comprehensive compaction quality of soil from shallow layer to deep layer. In addition, the time domain features of the signal and the frequency domain features of the power spectrum have never been considered as an observation values to evaluate the soil compaction quality. In this paper, we combine these signal features with an artificial neural network to accurately evaluate the overall soil compaction quality. First, to achieve the minimum amount of data required by an artificial neural network, each original signal is split into one hundred pieces. Then the time-domain features and frequency-domain features of the signal fragment in the power spectrum is calculated and the correlation between these characteristics and the comprehensive compaction quality is analyzed. Finally, the eight features with the best correlation are used as the input of an artificial neural network to build a nonlinear model. The test results show that the nonlinear model can accurately classify the overall compaction quality of soil into three categories: under compaction, the best compaction, and over compaction.

A state-of-the-art review of compaction control test methods and intelligent compaction technology for asphalt pavements

This paper investigates the current state of knowledge of the existing compaction testing methods for asphalt and identifies the limitations of these methods in using them during asphalt pavement compaction. Conventional spot tests that are carried out at limited spots for quality control (QC) and quality assurance (QA) of asphalt compaction often fail to ensure the uniformity of compaction. The differential approach using microwave sensors attached to the rollers can qualitatively indicate the optimum density during asphalt compaction; however, it requires spot density measurements to quantify the asphalt density achieved. intelligent compaction (IC) can be used to ensure the uniformity of asphalt compaction and to get real-time feedback. The current IC specifications for soil compaction are not suitable for asphalt compaction due to the viscoelastic nature of asphalt and the variation of asphalt mat temperature during compaction in the field. In addition, the state-of-the-art intelligent compaction measurement value (ICMVs) recorded during asphalt compaction does not correlate well with the asphalt density while it shows a reasonable correlation with asphalt stiffness. The effects of asphalt mat temperature and underlying support on ICMVs measured by IC rollers are identified as the potential causes of the poor correlation between ICMVs and spot density measurements. It is proposed that the relationship between asphalt modulus used in pavement designs and the ICMVs corrected for the effects of asphalt mat temperature and underlying support needs to be investigated in order to establish performance-based specifications for QA/QC of asphalt compaction. The emerging research on using GPR for asphalt density estimation is examined and the factors that affect the GPR measurements during asphalt pavement compaction are identified .

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.

Artificial Neural Network-Based Method for Real-Time Estimation of Compaction Quality of Hot Asphalt Mixes

With the advancement of intelligent compaction technology, real-time quality control has been widely investigated on the subgrade, while it is insufficient on asphalt pavement. This paper aims to estimate the real-time compaction quality of hot mix asphalt (HMA) using an artificial neural network (ANN) classifier. A field experiment of HMA compaction was designed. The vibration patterns of the drum were identified by using the ANN classifier and classified based on the compaction levels. The vibration signals were collected and the degree of compaction was measured in the field experiment. The collected signals were processed and the features of vibration patterns were extracted. The processed signals were tagged with their corresponding compaction level to form the sample dataset to train the ANN models. Four ANN models with different hidden layer setups were considered to investigate the effect of hidden layer structure on performance. To test the performance of the ANN classifier, the predictions made by ANN were compared with the measuring results from a non-nuclear density gauge (NNDG). The testing results show that the ANN classifier has good performance and huge potential for estimating the compaction quality of HMA in real-time.