Prediction Of Resilient Modulus Research Articles

Prediction of resilient modulus with pre-post experimental data of undisturbed subgrade soils using machine learning algorithms

The resilient modulus (MR) of subgrade, which shows relationship between stress and unit deformation of a pavement systems under traffic loads, is a design parameter of the pavement structure. Although a cyclic triaxial test apparatus can be used to directly determine the MR of the subgrade in the laboratory, utilizing prediction models based on easily obtainable soil parameters, is a more efficient method when taking time and cost considerations into account. A comprehensive laboratory testing program is designed to create MR prediction models using machine learning (ML) algorithms. 70 undisturbed soil samples are subjected to MR tests, as well as physical and engineering soil properties tests (water content, field density, specific gravity, gradation, consistency limits, unconfined compressive strength, swell pressure, swell percentage). Soil samples are drilled from a highway that has been in operation for over five years.First, a linear model like MLR is used in the study. Next, nonlinear regression models like RF, GBM, LightGBM, CatBoost, and XGBoost algorithms are used. Research findings showed that nonlinear regression models outperformed linear regression models in predicting the MR (R2 > 0.85), with the XGBoost algorithm yielding the best accuracy (R2 = 0.90). Apart from the primary effects such as confining pressure (σ3) and deviatoric stress (σd), it was found that unconfined compressive strength (qu), natural water content (wn), and swelling percentage (SR) are significant parameters in the prediction of MR among all parameters.

Prediction of Resilient Modulus of Subgrade Loamy Soils Through Wave Propagation Technique

Prediction of Resilient Modulus of Subgrade Loamy Soils Through Wave Propagation Technique

Prediction of resilient modulus and critical dynamic stress of recycled aggregates: Experimental study and machine learning methods

This paper aimed to investigate the feasibility of partially or completely replacing natural aggregates with recycled aggregates from construction and demolition wastes for low-carbon-emission use as coarse-grained embankment fill materials. The laboratory specimens were prepared by blending natural and recycled aggregates at varying proportions, and a series of laboratory repeated load triaxial compression tests were carried out to study the effects of material index properties and dynamic stress states on the resilient modulus and permanent strain characteristics. Based on the experimental results and by considering the main influencing parameters of the resilient modulus and permanent deformation, an artificial neural network (ANN) prediction model with optimal architecture was developed and optimized by the particle swarm optimization (PSO) algorithm, and its performance and accuracy were verified by supplementary analyses. A shakedown state classification method was proposed based on the unsupervised clustering algorithm, and a prediction model of critical dynamic stress was established based on the machine learning (ML) method and the shakedown state classification results. The research results indicate that the stress state has a greater influence on the resilient modulus and permanent deformation characteristics than other factors, and the shear stress ratio has a significant effect on the shakedown state. The resilient modulus and critical dynamic stress of such specimens vary linearly with confining pressure. The improved PSO-ANN prediction model exhibits high prediction accuracy and robustness, superior to several other commonly used ML regression prediction algorithms. The resilient modulus and critical dynamic stress prediction methods based on ML algorithms can provide technical guidance and theoretical basis for the design and in-service maintenance of similar unbound granular materials.

Heavy rainfall and moisture susceptibility of pavement foundation: A case study coupling finite element method and MnROAD moisture monitoring data

The Midwest region, including Minnesota, has been experiencing increased heavy precipitation events due to climate change, and the Minnesota Department of Transportation (MnDOT) is currently investigating the effect of climate change on pavement foundation and other transportation assets. As part of this effort, a study was conducted to investigate the impact of heavy rainfall on pavement foundation performance by focusing on moisture dynamics and resilient modulus changes in the pavement base layer. This study is aimed at understanding the adverse effects of heavy rainfall on moisture fluxes within pavement foundation and corresponding stiffness of the base aggregate layer. A two-step approach was adopted for predicting changes in saturation when estimating corresponding resilient modulus values using the resilient modulus prediction equation employed in AASHTOWare Pavement Mechanistic-Empirical (ME) Design. PLAXIS 3D, a finite-element analysis tool, was utilized to simulate the movement of moisture within the pavement layers under varying heavy rainfall scenarios. By incorporating predicted saturation from PLAXIS 3D simulations into the Pavement ME equation, corresponding resilient modulus values were estimated for the base layer. To ensure its accuracy and reliability, the model was validated using field sensor data from the MnROAD facility. Multiple linear regression models were developed to provide a means for estimating resilient modulus changes due to heavy rainfall. This study highlights the importance of considering moisture effects in pavement design and maintenance in regions prone to heavy rainfall events, and findings can be used by transportation agencies as part of their transportation/geotechnical asset management programs.

Indirect estimation of resilient modulus (Mr) of subgrade soil: Gene expression programming vs multi expression programming

Accurate prediction of resilient modulus (MR) in compacted subgrade soil is crucial for planning secure and environmentally friendly flexible pavement systems. This research assembled a dataset of 2813 data points from twelve compacted soils. The dry density, confining stress, deviator stress, number of freeze-thaw cycles, and moisture content were among the important variables considered for determining the MR. Subsequently, this study employs ensemble machine learning methodologies, specifically gene expression programming (GEP) and multi-expression programming (MEP), to investigate the subject further. The precision and anticipatory proficiency of both the GEP and MEP models are assessed through statistical evaluations, encompassing crucial metrics (R, RMSE, MAE, RSE, RRMSE, and ρ). The GEP and MEP models align well with validation criteria, underscoring their robustness in predicting novel data and showcasing their broad applicability. The GEP model consistently outperformed the MEP model, with higher coefficient of regression (R2) values in both training (0.992 vs. 0.983) and testing (0.981 vs. 0.972) phases, demonstrating its superior predictive accuracy and robustness. In summary, the GEP model consistently outperforms the MEP model in accuracy and prediction, making it the preferred choice for subgrade soil MR prediction. Sensitivity analysis was done, which ranked the parameters by their influence: dry density (26.6 %), confining stress (22.7 %), weighted plasticity index (15.3 %), moisture content (13.5 %), deviator stress (12.5 %), and freeze and thaw cycles (9.4 %). This research aims to enhance the utilization of GEP and MEP in civil engineering for more accurate and efficient MR prediction, ultimately reducing time and costs.

Resilient Modulus Prediction Model of Subbase Materials in Unsaturated State

Resilient Modulus Prediction Model of Subbase Materials in Unsaturated State

Research on Resilient Modulus Prediction Model and Equivalence Analysis for Polymer Reinforced Subgrade Soil under Dry-Wet Cycle.

The subgrade soil of asphalt pavement is significantly susceptible to changes in moisture content, and therefore many projects introduce polymer-based reinforcement to ensure soil performance. This paper aims to incorporate a variable representing the dry-wet cycle into the prediction model of resilient modulus of polymer reinforced soil. The polymer adopted is a self-developed subgrade soil solidification material consisting of sodium dodecyl sulfate and polyvinyl oxide. The current resilient modulus prediction model is improved, notably involving the effects of the dry-wet cycle. Combined with finite element method (FEM) analysis, the actual stress state of pavement and the coupling effect of dry-wet cycle and vehicle load on the resilient modulus are studied. The deterioration in resilient modulus with the variation in seasonal climate and load response is also investigated. Results show that the deviator stress is negatively correlated with the resilient modulus while the bulk stress has a linearly positive relation. The decreasing rate at low deviator stress is larger than that at the high level. Moreover, the dry-wet cycle can reduce the resilient modulus and the reducing amplitude is the largest at the first dry-wet cycle. FEM analysis shows that the middle position of the subgrade slope has the largest initial resilient modulus with decreasing amplitude in the first year of dry-wet cycles, while the upper position shows a smaller change. The variation in resilient modulus is closely related to the changes in cumulative volumetric water content. Considering that different positions of subgrade bear the external vehicle load, the equivalent resilient modulus is more realistic for guiding the subgrade design.

An ensemble tree-based prediction of Marshall mix design parameters and resilient modulus in stabilized base materials

A flexible pavement with an adequate Marshall mix design for the asphalt mixture surface layer(s) and appropriate subbase/base design offers a proper pavement structure for driving safety and comfortability. The conventional approach of calculating the Marshall mix design properties (e.g., stability and flow) and resilient modulus of base materials typically requires laborious, expensive, and time-consuming laboratory sample preparation and testing, such as the Marshall stability test and Resilient modulus test. Therefore, this study conducts research on the application of tree-based ensemble methods specifically, random forest (RFR) and eXtreme gradient boosting regression (XGBR) to predict the properties (mainly including Marshall stability, flow, VMA, VFA, and unit weigh) of asphalt mix following Marshall mix design and resilient modulus (Mr) of stabilized aggregate base material. To develop the prediction models, a comprehensive database was established using existing literature. The performance of the prediction models was evaluated using statistical parameters, performance index (p), and other suggested model performance criteria from external research. Additionally, the Shapley Additive exPlainations (SHAP) interpretation technique was employed to explain the models. The analysis results demonstrate that both RFR and XGBR methods have the excellent fitting capability (R > 0.9). However, XGBR has superior performance in predicting Marshall mix properties and Mr value. Comparison with previous research studies reveals that the proposed models show superior performance than genetic programming-based Marshall mix design models. The RFR model performs approximately similar to ANN, while XGBR outperforms ANN, and particle swarm optimization-extreme learning machine-based models for Mr prediction. Furthermore, the equation developed based on multi expression programming for Mr value prediction exhibits superior performance compared to previous research study gene expression programming model.

Machine learning-based prediction of resilient modulus for blends of tire-derived aggregates and demolition wastes

Although numerous studies have been undertaken to examine the potential of C&D wastes in pavement structures, limited research to date has developed constitutive models for the resilient modulus (Mr) of C&D wastes. In this study, machine learning algorithms: artificial neural network (ANN); Support Vector Regression (SVR); and Random Forest Regression (RFR) were utilised for estimating the Mr of C&D wastes blended with tire-derived aggregate (TDA). A database of repeated load triaxial test results on C&D/TDA blends including stress-state parameters, Mr values and other influential parameters on the Mr such as physical properties of the blends, as well as the California bearing ratio (CBR) test results was utilised for developing the machine learning models. The predictive performance of the developed algorithms was assessed using statistical indices and several validation stages. The results exhibited the robustness of machine learning algorithms used for predicting the Mr of C&D/TDA wastes, with R 2 train, R 2 test, MAPEtrain, MAPEtest between 0.996–0.997, 0.911–0.997, 0.037–0.068, and 0.037–0.067, respectively. The sensitivity analysis results indicated that the optimum moisture content and CBR had the highest impacts on the Mr of C&D/TDA blends.

Prediction of resilient modulus of fine-grained soil for pavement design using KNN, MARS, and random forest techniques

Prediction of resilient modulus of fine-grained soil for pavement design using KNN, MARS, and random forest techniques

Effect of biorejuvenator types on microstructure, mechanistic performance, and resilient modulus prediction model of asphalt concrete containing recycled materials in Indonesia

Biorejuvenators are rejuvenating agents produced from sustainable biological raw materials. In this study, a biorejuvenator was used in recycled materials, such as reclaimed asphalt pavement (RAP), to determine its effect on the asphalt binder film thickness (ABFT) and resilient modulus (Smix) of an asphalt concrete wearing course (ACWC) mixture, which was tested at the optimum binder content (OBC). The ABFT was investigated using scanning electron microscopy and the Smix was determined from the asphalt mixture test using UMATTA at test temperatures of 20–40 °C. The asphalt mixture was prepared with RAP (0–30%), pen 60/70, aggregates, and two types of biorejuvenators, namely coconut shell bioasphalt (BioCS) and BitutechRAP (from trees). Furthermore, an Smix model was developed for each mixture type. The ABFT value obtained from the microstructural test results for each mixture corresponded with the minimum ABFT requirements for the adhesion criteria of the asphalt mixture, microstructurally demonstrating that the biorejuvenators worked well to restore the performance of 30%RAP in the ACWC mixture. Both types of biorejuvenators could activate the bitumen of the RAP (RA binder) because they could still produce Smix. The value of Smix produced from the RAP and BioCS mixture was greater than that produced from the RAP and BitutechRAP mixture. In the resulting Smix model, the influential volumetric parameters for ACWC + RAP + BioCS and ACWC + RAP + BitutechRAP were the voids in mineral aggregate and voids in asphalt, respectively. Based on the results of the microstructural, mechanistic, and Smix models, BioCS, as a local Indonesian biorejuvenator, has significant potential to rejuvenate recycled materials up to 30%.

Mechanical properties and heavy metal leaching behaviors of municipal solid waste incineration bottom ash as road embankment fillings

With the development of economy and urbanization, the natural gravels and sands for new road construction materials encountered severe shortage issues in recent decades. In the meantime, the municipal Solid Waste Incineration bottom ash (MSWIBA) is regarded as a feasible alternative of mined nature aggregates due to its similar mineralogical, physical and chemical characteristics. However, the uncertainties of long-term service performance and potential environmental pollution risk of MSWIBA prevent its widespread applications in road constructions. For these reasons, this paper investigates the resilient modulus and permanent deformation properties by the repeated load triaxial test at different moisture contents, and examines the long-term environment influence using leaching tests on the samples after subjecting to 5 freeze-thaw cycles and samples after one year weathering. Besides, the existing resilient modulus and permanent deformation prediction models of unbounded granular materials are evaluated for their applicability on MSWIBA. The test results indicate that the MSWIBA shows obvious stress-dependence and moisture-dependence in resilient modulus and permanent deformation behaviors. Moreover, the existing resilient modulus and permanent deformation prediction models with stress and moisture dependence are feasible for MSWIBA as well. Additionally, heavy metal leaching concentrations obtained from column test can meet the standard of surface water quality class V in China. This work is expected to benefit the design work and provide the insight of performance of MSWIBA as road embankment material, and promote its further widespread application in road construction.

Laboratory test and prediction model of dynamic resilient modulus of carbonaceous mudstone coarse-grained soil

Carbonaceous mudstone is widely distributed in southwest China. With the rapid development of transportation construction in this region, the use of carbonaceous mudstone for subgrade filling has good economic and environmental benefits. At present, studies on the dynamic characteristics of carbonaceous mudstone coarse-grained soil are few. The shape characteristics of mudstone particles and the compaction characteristics of subgrade fillings with different grades are analyzed then dynamic triaxial tests are conducted to explore the variation of the dynamic resilient modulus MR of carbonaceous mudstone coarse-grained soil under different stresses and physical states. The influence of different gradation, confining pressure σ3, dynamic deviatoric stress σd, moisture content w, and degree of compaction K on MR of carbonaceous mudstone coarse-grained soil was studied. Results indicate that the particle shape index of carbonaceous mudstone is insensitive to particle size. With the increase in the gradation parameter D, the optimal moisture content wopt of the sample increases, whereas the maximum dry density ρdmax initially increases, and then decreases. MR is positively correlated with σ3 and K, but negatively correlated with σd and w. The decrease of MR caused by w decreases gradually with the increase of D. When w≤ 1.1 *wopt, the increase in D reduces MR, but when w= 1.2 *wopt, the trend changes to a positive correlation between MR and D. Carbonaceous mudstone subgrade filling can be used for the highway with light or medium traffic load grade. The recommended gradation parameter D ranges from 2.43 to 2.63. A resilient modulus prediction model considering the influence of gradation, stress state, moisture content, and physical state is proposed and its rationality is verified. The research results can provide reference for the design of carbonaceous mudstone coarse-grained soil subgrade.

Prediction of Resilient Modulus of Subgrade Soils from Stress State and Index Properties Using Machine Learning

Prediction of Resilient Modulus of Subgrade Soils from Stress State and Index Properties Using Machine Learning

Prediction of resilient modulus of ballast under cyclic loading using machine learning techniques

The resilient modulus (MR) of ballast is one of the key output parameters in any rail design project because it controls the elastic magnitude of track deformation under cyclic loading. This study investigates the response of MR under cyclic conditions as a function of four key parameters, i.e., the loading magnitude, the number of loading cycles, the loading frequency, and the confining pressure. To do so, two non-linear predictive models, namely, the artificial neural network (ANN), and the adaptive neuro-fuzzy inference system (ANFIS), are used to predict the MR values under different loading conditions. To evaluate and predict MR, an experimental database with 196 data samples is considered in this study. A series of sensitivity analyses is carried out to investigate the most effective parameters in each non-linear model and also predict the highest performance model. Although the results from the primary validation phase are satisfactory for the ANN and ANFIS models, ANFIS proves better (i.e., the coefficient of determination = 0.709) at estimating the MR during the secondary validation phase, using an independent dataset. Hence, it can be used as a powerful and practical model for predicting the magnitude of MR. On the basis of the ANFIS model, this study also offers some design considerations in terms of MR of ballast under a practical range of cyclic loading parameters.

Prediction Model of Dynamic Resilient Modulus of Unsaturated Modified Subgrade under Multi-Factor Combination

The objective of this research is to solve the problem of the lack of prediction methods and basis for the long-term road performance of oil shale residue-modified soil in seasonally frozen regions. This paper summarizes and expands the resilient modulus prediction methods in the related literature. Based on the measured soil–water characteristic curve (SWCC) of the compacted modified soil and the trend characteristics of dynamic resilient modulus under freeze–thaw cycles, a semi-empirical prediction model is proposed. This model was used to quantitatively forecast the resilient modulus of unsaturated modified subgrade soil after the freeze–thaw cycle in a seasonal permafrost region. The applicability and accuracy of the method were verified by dynamic resilient modulus tests of the oil shale residue-modified soil under various freeze–thaw cycles and moisture content. The results show that the model has a high degree of fit to the experimental data and is more suitable for predicting the dynamic resilient modulus of modified soil under the change of moisture and the freeze–thaw cycle compared to the existing models.

Resilient Modulus Behavior and Prediction Models of Unbound Permeable Aggregate Base Materials Derived from Tunneling Rock Wastes.

Tunneling rock wastes (TRWs), which are often open- or gap-graded in nature, have been increasingly recycled and reused for sustainable construction of unbound permeable aggregate base (UPAB) courses with high porosity and desired drainability. However, there is still a lack of sufficient understanding of long-term mechanical stability of such TRW materials subjected to repeated applications of moving wheel loads. This paper aimed to characterize and predict resilient modulus (Mr) behavior of the TRW materials used in unbound permeable aggregate base applications. To achieve this goal, five different UPAB gradations were designed based on the gravel-to-sand ratio (G/S) concept. In order to study their Mr behavior, the laboratory repeated load triaxial tests were conducted under different combinations of confining pressure and deviator stress as controlled by the levels of the shear stress ratio (SSR). The prediction accuracy of fourteen classical Mr prediction models was comparatively analyzed, from which the improved Mr prediction model incorporating gradation and stress variables was proposed for TRW-derived UPAB materials and further validated by external database accordingly. The results show that under the same G/S value and confining pressure level, the higher the SSR is, the greater the final Mr values are, and the more significant the effect of G/S on Mr is. Under the same SSR level, the increase of confining pressure alleviates the effect of G/S on Mr. There appears to exist an optimal G/S value of around 1.6–1.8 that yields the best Mr behavior of the TRW-derived UPAB materials studied. The improved Mr prediction model was verified extensively to be universally applicable. It can potentially contribute to balancing long-term mechanical stability and drainability of TRW-derived UPAB materials through gradation optimization. The findings could provide a theoretical basis and technical reference for cost-effective and sustainable applications of UPAB materials derived from TRWs.

Selection of suitable backcalculation technique and prediction of laboratory resilient modulus from NDT devices

ABSTRACT This study aims to analyse the backcalculated cohesive subgrade moduli using various backcalculation approaches. A series of in situ and laboratory investigations have been carried out on 190 test locations from 30 pavement sections of cohesive soils using Falling Weight Deflectometer (FWD), Light Weight Deflectometer (LWD), and Repeated Load Triaxial to determine backcalculated resilient moduli (MR_back), composite resilient moduli (MR_comp), and laboratory resilient modulus (MR_lab). The comparative analysis was performed for MR_back by LWD (MR_back_LWD), MR_comp by LWD on subgrade (MR_comp_LWD), and MR_back by FWD (MR_back_FWD) with MR_lab values to assess the level of agreement. MR_back_FWD and MR_back_LWD values of different soils by using Artificial Neural Network and Support Vector Machine techniques have shown the mean percentage variation (1.16–59.63%), correlation in terms of R2 value (0.628–0.824), and RMSE value (0.51–20.49%) with MR_lab values. In contrast, MR_comp_LWD values have shown good agreement with MR_lab values among MR_back_LWD and MR_comp_LWD. This study also suggested adjustment factors (0.308–0.974) for predicting MR_lab values from MR_back_FWD and MR_back_LWD for cohesive soils. Thus, this study recommends an appropriate backcalculation technique and suggests adjustment factors to the cohesive type of soils for realistic prediction of resilient characteristics of subgrade.

Statistical analysis and prediction of spatial resilient modulus of coarse-grained soils for pavement subbase and base layers using MLR, ANN and Ensemble techniques

Prediction methods for the estimation of the resilient modulus({M}_{R}) of unbound granular materials continues to be fraught with challenges associated with the in situ dependency of the existing methods, which makes them unreliable when considering the spatial variability of soil properties. Moreover, the artificial intelligence methods, which prove to be superior for {M}_{R} prediction, indicate that more recent and hybrid machine learning methods are more apt. Consequently, a comparative analysis was executed in the present study using advanced statistical approaches and a simple routine method for the prediction of the {M}_{R} of coarse-grained soils used as unbound granular materials in highway pavements. This study considered also the spatial variability of the routine soil properties based on the long-term pavement performance database. The result of the descriptive analysis conducted using principal component analysis revealed that the variation in {M}_{R} is due to three principal factors, which include the effect of moisture on the fines content, effect of coarse particles on the compaction characteristics and the effect of the soil stress state. Subsequently, prediction of the {M}_{R} using multiple linear regression was unreliable based on residual analysis and multi-collinearity problems. Thus, predictive modeling of {M}_{R} was then executed using artificial neural network (ANN) and ensemble techniques (random forest and gradient boosting machine), which resulted in very high R2 values above 0.9, considered apt for MEPD. The ANN model was found to provide a superior prediction performance than the ensemble techniques.

Prediction of CBR and resilient modulus of crushed waste rocks using machine learning models

Prediction of CBR and resilient modulus of crushed waste rocks using machine learning models