Development of an artificial neural network model to predict subgrade resilient modulus from continuous deflection testing

Elbagalati, Omar; Elseifi, Mostafa A.; Gaspard, Kevin; Zhang, Zhongjie

doi:10.1139/cjce-2017-0132

Cited by 23 publications

(8 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The first 70% of the data was utilized for training the model, while the remaining 30% of the data was divided into model testing and validation data sets. As shown in Figure 5, as an effort to avoid overfitting and maintain network generalization, the D r a f t training was stopped when the validation data set error had stopped decreasing (Elbagalati et al 2017).…”

Section: Model Training Methodology and Evaluationmentioning

confidence: 99%

Integrated predictive artificial neural network fatigue endurance limit model for asphalt concrete pavements

Isied

Souliman

2019

Can. J. Civ. Eng.

View full text Add to dashboard Cite

Asphalt endurance limit is a strain value if experienced by asphalt pavement layer, no accumulated damage will occur and is directly related to asphalt healing. Therefore, if the pavement experiences this value of strain, or lower, no fatigue damage would accumulate within that pavement section. Beam fatigue test data conducted under the NCHRP Project 9-44A were extracted and utilized to create an artificial neural network predictive model (ANN) to determine the endurance limit strain values for conventional asphalt concrete pavements. The developed ANN model architecture as well as how to utilize it to predict the endurance limit were demonstrated and discussed in detail. Also, a stand-alone equation that is capable in the prediction of the endurance limit strain value, separate from the ANN model environment, was derived utilizing the eclectic extraction approach. The model training and validation data included 934 beam fatigue laboratory data points, as extracted from NCHRP Project 9-44A report. The developed model was able to determine the endurance limit strain value as a function of the stiffness ratio, number of cycles to failure, initial stiffness and rest period, and had a reasonable coefficient of determination (R2) value, which indicates the reliability of both the developed ANN model and the stand-alone equation. Furthermore, a correlation between the endurance limit strain values, as predicted utilizing the generated regression model under the NCHRP project 944-A, and the endurance limit strain values predicted utilizing the stand-alone ANN derived equation was found with a high R2 value.

show abstract

Section: Model Training Methodology and Evaluationmentioning

confidence: 99%

Integrated predictive artificial neural network fatigue endurance limit model for asphalt concrete pavements

Isied

Souliman

2019

Can. J. Civ. Eng.

View full text Add to dashboard Cite

show abstract

“…In order to examine the efficacious stabilization of extremely weak subgrade soils at high water contents, the resilient modulus of stabilized subgrade was determined; therefore, ANN and GEP models were formulated by considering 125 samples data and it was concluded that accurate result for M r was achieved by using GEP (R 2 of 0.95) [17]. In yet another study regarding prediction of M r , the computation of a rolling-wheel deflectometer and a falling weight deflectometer was yielded from a testing program for training an ANN-based model, which was independently validated using data from a testing program, such that it depicted an acceptable accuracy in both the development and validation phases (R 2 of 0.73 and 0.72, respectively) [66]. Moreover, Jalal et al [57] suggested that the genetic programming approaches (i.e., GEP and MEP) techniques accurately forecast the compaction characteristics (maximum dry density and optimum moisture content) of swelling clays, such that the GEP model showed a relatively better performance.…”

Section: Introductionmentioning

confidence: 99%

Prediction Models for Evaluating Resilient Modulus of Stabilized Aggregate Bases in Wet and Dry Alternating Environments: ANN and GEP Approaches

et al. 2022

View full text Add to dashboard Cite

Stabilized aggregate bases are vital for the long-term service life of pavements. Their stiffness is comparatively higher; therefore, the inclusion of stabilized materials in the construction of bases prevents the cracking of the asphalt layer. The effect of wet–dry cycles (WDCs) on the resilient modulus (Mr) of subgrade materials stabilized with CaO and cementitious materials, modelled using artificial neural network (ANN) and gene expression programming (GEP) has been studied here. For this purpose, a number of wet–dry cycles (WDC), calcium oxide to SAF (silica, alumina, and ferric oxide compounds in the cementitious materials) ratio (CSAFRs), ratio of maximum dry density to the optimum moisture content (DMR), confining pressure (σ3), and deviator stress (σ4) were considered input variables, and Mr was treated as the target variable. Different ANN and GEP prediction models were developed, validated, and tested using 30% of the experimental data. Additionally, they were evaluated using statistical indices, such as the slope of the regression line between experimental and predicted results and the relative error analysis. The slope of the regression line for the ANN and GEP models was observed as (0.96, 0.99, and 0.94) and (0.72, 0.72, and 0.76) for the training, validation, and test data, respectively. The parametric analysis of the ANN and GEP models showed that Mr increased with the DMR, σ3, and σ4. An increase in the number of WDCs reduced the Mr value. The sensitivity analysis showed the sequences of importance as: DMR > CSAFR > WDC > σ4 > σ3, (ANN model) and DMR > WDC > CSAFR > σ4 > σ3 (GEP model). Both the ANN and GEP models reflected close agreement between experimental and predicted results; however, the ANN model depicted superior accuracy in predicting the Mr value.

show abstract

“…For flexible pavements, the random cracking index (RNDM) encompasses all random cracks, which include thermal, reflective, longitudinal, block, and cement-treated reflective cracks. The equations used to calculate the alligator cracking index (ALCR), the random cracking index (RNDM), the roughness index (ROUGH), and the rutting index (RUTT) are as follows ( 6 ):…”

Section: Introductionmentioning

confidence: 99%

“…Cost-efficiency of RWD testing was evaluated in light of the added economic benefits ( 5 ). Methodologies for backcalculation of subgrade moduli based on RWD measurements and layer moduli based on TSD measurements were developed ( 6 , 7 ). In addition, a framework was developed to incorporate RWD measurements in the Louisiana pavement management system (PMS) at the network level and in asphalt concrete (AC) overlay design at the project level ( 8 , 9 ).…”

mentioning

confidence: 99%

Relationship between Surface-Measured Indices and In-Service Pavement Structural Conditions Predicted from Traffic Speed Deflection Devices

Zihan

Elseifi

Gaspard

et al. 2019

Transportation Research Record: Journal of the Transportation R

Self Cite

View full text Add to dashboard Cite

The rolling wheel deflectometer (RWD) and traffic speed deflectometer (TSD) are continuous deflection measuring devices used for structural evaluation of in-service pavements. Although recent studies have demonstrated the benefits of these devices, state agencies are inclined to believe that surface indices are generally sufficient to describe in-service pavement conditions (functional and structural conditions) and to make cost-effective maintenance and rehabilitation decisions. The main objective of this study was to assess whether the use of surface indices only or the declining rates of these indices to identify structurally damaged sections is feasible instead of relying on RWD and TSD estimated pavement structural indices. Results of the analysis showed that structural deficiency, rates of deterioration, and surface indices were correlated to a certain extent. These results were expected, as pavements that are structurally deteriorated will exhibit surface deficiencies over time. Yet, surface indices cannot be used as a reliable predictor of structural capacity. For RWD, the most accurate surface index, which was the alligator cracking surface index, erroneously identified 35% of structurally sound sections as structurally deficient and 51.5% of structurally deficient sections as structurally sound. Similar results were obtained for the TSD; in this case, the most accurate surface index, which was the random cracking index, erroneously identified 16.7% of structurally sound sections as structurally deficient and 51.0% of structurally deficient sections as structurally sound. The cost implication associated with misinterpreted sections from functional indices was investigated. The incorporation of structural indices is expected to provide significant savings to state agencies.

show abstract

Development of an artificial neural network model to predict subgrade resilient modulus from continuous deflection testing

Cited by 23 publications

References 26 publications

Integrated predictive artificial neural network fatigue endurance limit model for asphalt concrete pavements

Integrated predictive artificial neural network fatigue endurance limit model for asphalt concrete pavements

Prediction Models for Evaluating Resilient Modulus of Stabilized Aggregate Bases in Wet and Dry Alternating Environments: ANN and GEP Approaches

Relationship between Surface-Measured Indices and In-Service Pavement Structural Conditions Predicted from Traffic Speed Deflection Devices

Contact Info

Product

Resources

About