The use of deep neural networks for developing generic pavement rutting predictive models

Haddad, Angela J.; Chehab, Ghassan R.; Saad, George Abi

doi:10.1080/10298436.2021.1942466

Cited by 30 publications

(10 citation statements)

References 44 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…On the other hand, periodic maintenance refers to tasks often performed at regular but spaced-out periods in the same section. Resealing and overlaying are routine maintenance procedures for paved roads with flexible pavement [12]. Construction of rigid pavements and subsequent maintenance tasks are distinct from those for flexible pavements.…”

Section: Literature Reviewmentioning

confidence: 99%

Empirical Models Investigation of Pavement Management for Advancing the Road's Planning Using Predictive Maintenance

Aldabbas¹

2023

cea

View full text Add to dashboard Cite

Section: Literature Reviewmentioning

confidence: 99%

Empirical Models Investigation of Pavement Management for Advancing the Road's Planning Using Predictive Maintenance

Aldabbas¹

2023

cea

View full text Add to dashboard Cite

“…Haddad et al [57] developed a rutting depth prediction model taking into account the lack of data and resources available in developing countries and local road agencies. Data were extracted from the LTPP database, including a set of climate, traffic, asphalt, base, and subgrade properties.…”

Section: Flexible Pavement Maintenancementioning

confidence: 99%

Artificial Neural Networks for Flexible Pavement

et al. 2023

View full text Add to dashboard Cite

Transportation agencies are primarily responsible for building new roads and maintaining current roads. The main focuses of these agencies are to prioritize maintenance and make significant rehabilitation decisions to handle serious problems facing road authorities. Considerable efforts and an abundance of studies have been performed to determine the nature, mechanisms, test methods, and measurement of pavements for preservation and improvements of roadways. The presented study reports a state-of-the-art review on recent advances in the application of artificial intelligence in various steps of flexible pavement, including pavement construction, performance, cost, and maintenance. Herein, the challenges of gathering large amounts of data, parameter optimization, portability, and low-cost data annotating are discussed. According to the findings, it is suggested that greater attention should be paid to integrating multidisciplinary roadway engineering techniques to address existing challenges and opportunities in the future.

show abstract

“…In contrast, mechanistic models involve the computation of permanent deformation accumulation, integrating specific material behaviors like the viscoplastic model [27] and the elastic-viscoplastic model [28]. These models operate within diverse loading conditions such as pulse loads [27], moving loads [29], and equivalent loads [30], utilizing methods like finite element [31] and discrete element approaches [32]. However, simulating actual loading and varying climate conditions presents challenges due to the complexity of tirepavement contact areas and stress distribution.…”

Section: Introductionmentioning

confidence: 99%

“…In 2004, the Mechanistic-Empirical Pavement Design Guide (MEPDG) was introduced, presenting a mechanistic-empirical (M-E) approach to rutting prediction [31]. The M-E method involves establishing a regression equation linking rutting depth to factors including pavement structural responses, climate conditions, traffic loadings, material properties, and wheel tracking test outcomes.…”

Section: Introductionmentioning

confidence: 99%

Creating Rutting Prediction Models through Machine Learning Techniques Utilizing the Long-Term Pavement Performance Database

Alnaqbi,

Zeiada,

Al-Khateeb

et al. 2023

Sustainability

View full text Add to dashboard Cite

Over time, roads undergo deterioration caused by various factors such as traffic loads, climate conditions, and material properties. Considering the substantial global investments in road construction, it is crucial to periodically assess and implement maintenance and rehabilitation (M and R) plans to ensure the network’s acceptable level of service. An integral component of the M and R plan involves utilizing performance prediction models, especially for rutting distress, a significant issue in asphalt pavement. This study aimed to develop rutting prediction models using data from the Long-Term Pavement Performance (LTPP) database, employing several machine learning techniques such as regression tree (RT), support vector machine (SVM), ensembles, Gaussian process regression (GPR), and Artificial Neural Network (ANN). These techniques are well-known for effectively handling extensive and complex datasets. To achieve the highest modeling accuracy, the parameters of each model were meticulously fine-tuned. Upon evaluation, the results revealed that the GPR models outperformed other techniques in various metrics, including Root Mean Square Error (RMSE), R-squared, Mean Absolute Error (MAE), and Mean Square Error (MSE). The best GPR model achieved an RMSE of 1.96, R-squared of 0.70, MAE of 1.32, and MSE of 109.33, indicating its superior predictive capabilities compared with the other machine learning methods tested in this study. Comparison Analysis was made for 10 randomly selected sections on our novel machine learning model that outperforms existing models, with an R2 of 0.989 compared with 0.303 and 0.3095 for other models. This demonstrates the potential of advanced machine learning in accurate rut depth prediction across diverse climates, aiding pavement management decisions.

show abstract

The use of deep neural networks for developing generic pavement rutting predictive models

Cited by 30 publications

References 44 publications

Empirical Models Investigation of Pavement Management for Advancing the Road's Planning Using Predictive Maintenance

Empirical Models Investigation of Pavement Management for Advancing the Road's Planning Using Predictive Maintenance

Artificial Neural Networks for Flexible Pavement

Creating Rutting Prediction Models through Machine Learning Techniques Utilizing the Long-Term Pavement Performance Database

Contact Info

Product

Resources

About