Ragaa Abd El-Hakim

International Roughness Index Prediction for Rigid Pavements: An Artificial Neural Network Application

nternational Roughness Index (IRI) is an important parameter that indicates the ride quality and pavement condition. In this study, an Artificial Neural Network (ANN) model was developed to predict the IRI for Jointed Plain Concrete Pavement (JPCP) sections. The inputs for this model are: initial IRI value, pavement age, transverse cracking, percent joints spalled, flexible and rigid patching areas, total joint faulting, freezing index, and percent subgrade passing No. 200 U.S. sieve. This data was obtained from the Long Term Pavement Performance (LTPP) Program. It is the same data and inputs used for the development of the Mechanistic-Empirical pavement Design Guide (MEPDG) IRI model for JPCP. The data includes a total of 184 IRI measurements. The results of this study shows that using the same input variables, the ANN model yielded a higher prediction accuracy (coeficint of determination: R2 = 0.828, and ratio of standard error of estimate (predicted) to standard deviation of the measured IRI values: Se/Sy =0.414) compared to the MEPDG model (R2 = 0.584, Se/Sy =0.643). In addition, the bias in the predicted IRI values using the ANN model was significantly lower compared to the MEPDG regression model.

Quantifying the Mechanistic and Economic Impacts of Using Asphalt Rubber Mixtures

As far as hot mix asphalt pavement goes, tension at the bottom layer of the HMA layer creates the most issues for pavement engineers. Adding rubber to asphalt mix has the ability to extend the life of a pavement and provide an end use to old tires that would otherwise end up in a landfill. It is already known that the initial construction cost of an asphalt rubber mix will be higher than that of a conventional mix, but the purpose of this paper is to see if the reduced layer thickness and improved fatigue life will offset the initial cost. After completing a mechanistic analysis using the FHWA software package named 3D Move, the pavement thickness required to last for 50,000,000 cycles (estimated endurance limit) is much less for the asphalt rubber mixes as opposed to the reference hot mix asphalt. The cost to construct one lane mile of the reference mix pavement designed for 70 mph traffic was

International Roughness Index prediction model for flexible pavements

171,530.88 while the asphalt rubber mix at 70 mph came out to be

Structural number prediction for flexible pavements using the long term pavement performance data

157,059.70. This is a

Application of Artificial Neural Networks for Hot Mix Asphalt Dynamic Modulus (E*) Prediction

14,471.18 difference. Additionally, the cost to construct one lane mile of the reference mix pavement designed for 10 mph traffic was

Factors Affecting Accidents Risks among Truck Drivers In Egypt

231,932.76, while the asphalt rubber mix at 10 mph came out to be

Simplified Closed-Form Procedure for Network-Level Determination of Pavement Layer Moduli from Falling Weight Deflectometer Data

200,162.55. This is a

Comparing Artificial Neural Networks with Regression Models for Hot-Mix Asphalt Dynamic Modulus Prediction

31,770.21 price difference. Overall, analysis showed that AR modified asphalt mixtures exhibited significantly lower cost of pavement per 1000 cycles of fatigue life per mile compared to conventional HMA mixture.

Mechanistic and Economic Impacts of Using Asphalt Rubber Mixtures at Various Vehicle Speeds

Abstract International Roughness Index (IRI) is a pavement performance indicator which reflects not only the pavement condition but also the ride quality and comfort level of road users. The aim of this paper is to develop an accurate IRI prediction model for flexible pavements using both multiple linear regression analysis and artificial neural networks (ANNs). The models were developed based on the Long-Term Pavement Performance Database. The data were collected for both original and overlaid flexible pavements from the general pavement studies (GPS-1, GPS-2 and GPS-6) and the specific pavement studies (SPS-1, SPS-3 and SPS-5). The final database consisted of 506 sections with 2439 observations. The proposed models (regression and ANNs) predict IRI as a function of pavement age, initial IRI (IRI just after pavement construction), transverse cracks, alligator cracks and standard deviation of the rut depth. The regression model yielded a coefficient of determination (R 2) value of 0.57 while the ANNs model resulted in a much higher R 2 value of 0.75.

Validation and Improvement of Pavement ME Flexible Pavement Roughness Prediction Model Using Extended LTPP Database

ABSTRACT Structural Number (SN) is a numerical value used as pavement structural capacity indicator. This paper reviews the most recognised historical SN prediction models. These models are COST, Schnoor and Horak, Kavussi et al., Rohde, and Kim et al. These models predict the structural number of existing flexible pavement systems (SNeff) based primarily on the Falling Weight Deflectometer (FWD) data. One major drawback of these models, is that they ignore the effect of temperature on the backcalculated modulus of the Asphalt Concrete (AC) layer and hence the predicted SNeff values. The accuracy of the investigated SNeff prediction models after applying temperature correction to the AC layer modulus (EAC) and the FWD peak deflection (Do) to a reference temperature of 21°C was examined. FWD data and backcalculated moduli of pavement layers were collected from the Long Term Pavement Performance (LTPP) database. Fourteen pavement test sections covering the four climatic regions in the U.S. with 1293 FWD test points were used to evaluate and improve the accuracy of the investigated models compared to the AASHTO 1993 method. The most prominent models were calibrated and/or simplified. The proposed calibrated/simplified models produced more accurate and less biased SNeff predictions as compared to the original models. The proposed modified models were validated using another set of LTPP data and they yielded comparable predictions.