Development of Tree-Based Algorithm for Prediction of Field Performance of Asphalt Concrete Overlays

Gaspard³

2022

Self Cite

Extreme weather events, including inundation, are the major causes of weather-related disruption to the transportation sector. Considerable research has been conducted in recent years to evaluate the impacts of inundation on pavement functional and structural conditions. Yet, limited studies quantified how inundation may affect the long-term pavement performance and pavement life-cycle costs. As such, the main objective of this study was to quantify the impact of the 2016 inundation event in Louisiana, U.S., on the long-term pavement performance (in relation to reduction in the pavement service life [PSL]) and on pavement life-cycle costs. To achieve this objective, a total of 10 inundated pavement sections were evaluated. Pavement conditions, fatigue, and rutting indices for these sections were analyzed over a monitoring period of up to 15 years (11 years before and 4 years after inundation). Results indicated that the 2016 inundation event reduced the PSL of the inundated sections to an extent that depended on their pre-flooding pavement condition, traffic level, and asphalt concrete thickness. This reduction was attributed to the accelerated fatigue, rutting damage, or both, that resulted from prolonged water submergence and heavy traffic loading during debris hauling that took place after the inundation event. A logistic regression model with adequate accuracy was developed to predict whether an inundated pavement would experience reduction in its PSL based on the project conditions. The study findings were incorporated into a simple tool to assist transportation agencies make effective decisions for the maintenance and rehabilitation of inundated pavements.

Section: Results and Analysismentioning

confidence: 99%

Impact of the Great Flood of 2016 on the Asphaltic Concrete Road Infrastructure in Louisiana

Elseifi

Gaspard³

2022

Self Cite

“…These parameters include the following ( 28 To tune these hyper-parameters, two combined techniques were employed: (1) grid search and (2) five-fold cross validations. Grid search is an exhaustive search through all possible combinations of values for the hyper-parameters within a defined space to identify the optimal combination (28). For both models developed in this study, the different parameter spaces were defined as De [2,4,6,8,10], Te [2,10,20,30,50,100,200, 300, 400, 500, 600, 700, 800, 1000], and Le [0.001, 0.005, 0.01, 0.05, 0.1, 0.5].…”

Section: Model Trainingmentioning

confidence: 99%

“…This was repeated five times by changing the validation subset. For each trial, the R 2 was obtained, and the average R 2 value was finally obtained for the five trials to evaluate the model performance (28).…”

Section: Model Trainingmentioning

confidence: 99%

Predicting the Retroreflectivity Degradation of Waterborne Paint Pavement Markings using Advanced Machine Learning Techniques

Hassan

et al. 2021

Waterborne paint is the most common marking material used throughout the United States. Because of budget constraints, most transportation agencies repaint their markings based on a fixed schedule, which is questionable in relation to efficiency and economy. To overcome this problem, state agencies could evaluate the marking performance by utilizing measured retroreflectivity of waterborne paints applied in the National Transportation Product Evaluation Program (NTPEP) or by using retroreflectivity degradation models developed in previous studies. Generally, both options lack accuracy because of the high dimensionality and multi-collinearity of retroreflectivity data. Therefore, the objective of this study was to employ an advanced machine learning algorithm to develop performance prediction models for waterborne paints considering the variables that are believed to affect their performance. To achieve this objective, a total of 17,952 skip and wheel retroreflectivity measurements were collected from 10 test decks included in the NTPEP. Based on these data, two CatBoost models were developed with an acceptable level of accuracy which can predict the skip and wheel retroreflectivity of waterborne paints for up to 3 years using only the initial measured retroreflectivity and the anticipated project conditions over the intended prediction horizon, such as line color, traffic, air temperature, and so forth. These models could be used by transportation agencies throughout the United States to 1) compare between different products and select the best product for a specific project, and 2) determine the expected service life of a specific product based on a specified threshold retroreflectivity to plan for future restriping activities.

“…A study was conducted to evaluate the field performance of structural AC overlays in Louisiana, which is an important factor in the present study as almost all of the maintenance treatments in Louisiana are placed over AC overlays ( 22 ). The results of this study were used to determine the PSL of 144 AC overlay projects as a function of the overlay thickness as shown in Table 1.…”

Section: Data Collectionmentioning

confidence: 99%

Development of a Decision-Making Tool to Select Optimum Preventive Maintenance Treatments in a Hot and Humid Climate

Elseifi

Zhang

et al. 2020

Self Cite

Preventive maintenance treatments are widely used throughout the United States to extend pavement service life (PSL), and therefore, defer costly rehabilitation activities. However, optimizing the use of these treatments faces several key challenges. First, the benefits resulting from these treatments are not well-defined. Second, there is considerable debate over the optimal timing of these treatments. Third, concerns exist that these treatments may be responsible for moisture damage if the surrounding moisture conditions are not adequately considered before installation. Although significant research has been conducted to address these challenges, few efforts have been directed toward technology transfer and implementation of the research findings. Therefore, the objective of this study was to combine the results of a comprehensive research study addressing these challenges into an enhanced decision-making tool that can be used to select the best maintenance treatment to be applied to an existing asphalt concrete (AC) overlay based on the project conditions. For a given project, this tool will predict the most cost-effective maintenance treatment (crack sealing, chip seal, microsurfacing, or do nothing) to address existing surface distresses without causing moisture damage. The tool will also provide the optimal timing of installation of the recommended treatment. To ensure that the developed tool is practical and simple to use, it was developed using macros in Microsoft Excel. The developed tool is implementation-ready and should be utilized by the relevant Department of Transportation to maximize the benefits from pavement maintenance activities.