Performance Prediction of Asphalt Pavement Based on the Combined Model

CICTP 2020 ◽  
2020 ◽  
Author(s):  
Wenwen Feng ◽  
Guanglai Jin ◽  
Haiting Liu ◽  
Zhixiang Zhang
Keyword(s):  
Performance Prediction ◽  
Asphalt Pavement ◽  
Combined Model

scholarly journals A Hybrid Model for Prediction in Asphalt Pavement Performance Based on Support Vector Machine and Grey Relation Analysis

2020 ◽  
Vol 2020 ◽  
pp. 1-14
Author(s):  
Xuancang Wang ◽  
Jing Zhao ◽  
Qiqi Li ◽  
Naren Fang ◽  
Peicheng Wang ◽  
...  
Keyword(s):  
Support Vector Machine ◽  
Prediction Model ◽  
Performance Prediction ◽  
Asphalt Pavement ◽  
Pavement Performance ◽  
Support Vector ◽  
Grey Relation Analysis ◽  
Relation Analysis ◽  
Pavement Performance Prediction ◽  
Grey Relation

Pavement performance prediction is a crucial issue in big data maintenance. This paper develops a hybrid grey relation analysis (GRA) and support vector machine regression (SVR) technique to predict pavement performance. The prediction model can solve the shortcomings of the traditional model including a single consideration factor, a short prediction period, and easy overfitting. GAR is employed in selecting the main factors affecting the performance of asphalt pavement. The SVR is performed to predict the performance. Finally, the data collected from the weather station installed on Guangyun Expressway were adopted to verify the validity of the GRA-SVR model. Meanwhile, the contrast with the grey model (GM (1, 1)), genetic algorithm optimization BP[[parms resize(1),pos(50,50),size(200,200),bgcol(156)]]081%, −0.823%, 1.270%, and −4.569%, respectively. The study concluded that the nonlinear and multivariate prediction model established by GRA-SVR has higher precision and operability, which can be used in long-period pavement performance prediction.

Combined Model Framework for Asphalt Pavement Condition Determination After Flooding

2017 ◽  
Vol 2639 (1) ◽  
pp. 64-72 ◽  
Author(s):  
Rajib B. Mallick ◽  
Mingjiang Tao ◽  
Jo Sias Daniel ◽  
Jennifer M. Jacobs ◽  
A. Veeraragavan
Keyword(s):  
Layer Thickness ◽  
Hot Mix Asphalt ◽  
Asphalt Pavement ◽  
Interactive Simulation ◽  
Model Framework ◽  
Combined Model ◽  
Pavement Condition ◽  
The Public ◽  
Short Period ◽  
The Web

Flooding of pavements often causes damage that is invisible on the surface. A way to predict the condition of a pavement after flooding will be useful for agencies to make rational decisions about the need for closing a road to traffic or opening it up for cleaning and recovery work. In this study, the problem of flooded pavement assessment was formulated as a combination of hydraulic and structural analyses. A model was developed; it consisted of results from unsaturated hydraulic and layered elastic structural analyses. An interactive simulation was developed from the model and was made available on the web to users in the public domain. Simulations with the model showed significant impacts when subgrade layer moduli were below 50 MPa and layer thickness was less than 200 mm for the hot-mix asphalt (HMA) and less than 600 mm for the base. Axle loads exceeding 80 kN exacerbated damages and hazardous conditions. The time to reach conditions that will not lead to damage or failure within a short period of time depends on both the pavement conditions and the load magnitude. On the basis of thickness of surface HMA layer and soil subgrade moduli, restrictions of traffic could be placed on flooded pavements.

Suitability of Asphalt Pavement Analyzer for Predicting Pavement Rutting

2000 ◽  
Vol 1723 (1) ◽  
pp. 107-115 ◽  
Author(s):  
Bouzid Choubane ◽  
Gale C. Page ◽  
James A. Musselman
Keyword(s):  
Performance Prediction ◽  
Field Data ◽  
Asphalt Pavement ◽  
Evaluation Process ◽  
Field Measurements ◽  
Asphalt Mixtures ◽  
Test Results ◽  
Asphalt Mixes ◽  
Tracking Device ◽  
Wheel Tracking

Findings are summarized from an investigation performed to evaluate the suitability of a wheel-tracking device known as the asphalt pavement analyzer (APA) for assessing the rutting potential of asphalt mixes. The evaluation process consisted of correlating the APA’s predicted rutting with known field measurements. The correlation between beam and gyratory samples and the testing variability were also investigated. In addition, the APA test results were compared with those obtained using the Georgia loaded-wheel tester. The findings of this investigation indicated that the APA may be an effective tool to rank asphalt mixtures in terms of their respective rut performance. However, for each mixture type, the APA testing variability was significant between tests and between the three testing locations within each test. Differences in rut measurements of up to 4.7 and 6.3 mm were recorded for beam and gyratory samples, respectively. Therefore, using the APA as a clear pass-or-fail criterion for performance prediction purposes of asphalt mixtures may not be appropriate at this time. It should be noted that these findings are based on data collected on three mixes. Therefore, it is suggested that the APA testing variability (testing and testing locations within the device) be further assessed with a wider range of mixtures. The intent of such an assessment should not only be to correlate the APA results with field data but also to develop potential pass-or-fail limits and procedures.

Evaluation and Performance Prediction for Asphalt Pavement Preventive Conservation Measures

2011 ◽  
Vol 99-100 ◽  
pp. 308-313
Author(s):  
Yan Hai Yang ◽  
Huai Zhi Zhang ◽  
Bo Wang
Keyword(s):  
Performance Prediction ◽  
Prediction Models ◽  
Asphalt Pavement ◽  
Traffic Volume ◽  
Monitoring Data ◽  
Preventive Conservation ◽  
Conservation Measures ◽  
And Performance ◽  
Regressing Analysis

Based on the monitoring data of pavement performances and traffic volume from the China key projects, the expressways from Shenyang to Shanhaiguan and from Panjin to Haicheng, the effects of asphalt pavement preventive conservation measures utilized in the two expressways and the remaining equivalent standard loads are evaluated. Three models are adopted to predict the pavement performances for the two expressways in six years by the regressing analysis and the reasonable performance prediction models are accomplished through modifying the initial models by the actual monitoring data.

Fatigue Performance Prediction of Asphalt Pavements with FlexPAVETM, the S-VECD Model, and DR Failure Criterion

2018 ◽  
Vol 2672 (40) ◽  
pp. 217-227 ◽  
Author(s):  
Yizhuang David Wang ◽  
Behrooz Keshavarzi ◽  
Y. Richard Kim
Keyword(s):  
Performance Prediction ◽  
Failure Criterion ◽  
Asphalt Pavement ◽  
Moving Load ◽  
Field Measurements ◽  
The United States ◽  
Climatic Conditions ◽  
Fatigue Performance ◽  
Pavement Performance ◽  
Finite Element Program

Reliable predictions of asphalt materials and pavement performance are important elements in mixture design, mechanistic-empirical pavement design, and performance-related specifications. This paper presents FlexPAVE™, a pavement performance prediction program. FlexPAVE™ is a three-dimensional finite element program that is capable of moving load analysis under realistic climatic conditions. It utilizes the simplified viscoelastic continuum damage (S-VECD) model to predict asphalt pavement fatigue life. This S-VECD model currently incorporates the so-called GR failure criterion to define the failure of asphalt mixtures. In this study, a new failure criterion for the S-VECD model, designated as the DR criterion, has been developed to remedy some of the shortcomings of the GR failure criterion. This DR criterion has been implemented successfully in FlexPAVETM. In this paper, FlexPAVETM is used to simulate the fatigue performance of field test sections. These test sections include various pavement structures, such as perpetual pavements and accelerated load facility test pavements in the United States, South Korea, and China, as well as various materials, such as warm-mix asphalt, reclaimed asphalt pavement, and mixtures with modified binders. The DR-based FlexPAVETM predictions have yielded good agreement with the field measurements and show more reasonable trends compared to predictions obtained using the GR failure criterion.

Sign in / Sign up

Export Citation Format

Share Document