Inicio  /  Applied Sciences  /  Vol: 14 Par: 8 (2024)  /  Artículo
ARTÍCULO
TITULO

Predicting Rutting Development Using Machine Learning Methods Based on RIOCHTrack Data

Chunru Cheng    
Linbing Wang    
Xingye Zhou and Xudong Wang    

Resumen

As the main cause of asphalt pavement distress, rutting severely affects pavement safety. Establishing an accurate rutting prediction model is crucial for asphalt pavement maintenance, pavement structure design, and pavement repair. This study explores five machine learning methods, namely Support Vector Regression (SVR), Artificial Neural Network (ANN), Gradient Boosting Decision Tree (GBDT), Random Forest (RF), and Extra Trees, to predict the development of rutting depth using data from RIOHTRack. The model?s performance is measured by comparing the performance evaluation indicators of different models, such as the coefficient of determination, root mean square error, mean absolute error, and mean absolute percentage error. The results demonstrate that integrated learning techniques such as RF, GBDT, and Extra Trees works best with R2 = 0.9761, 0.9833, and 0.9747. Moreover, the GBFT model can capture the trend of the measured rutting progression curve better than the mechanistic-empirical (M-E) model. The analysis of feature importance reveals that, in addition to external factors such as temperature and axle load, the aggregate of the asphalt concrete layer and air void crucially affect rutting. The higher the base strength, the smaller the rutting depth. The proposed model is highly straightforward and serves as an accessible analysis tool for engineers in practice.

 Artículos similares

       
 
Pedro Limón-Covarrubias, Leonardo Ambrosio Ochoa-Ambriz, David Avalos-Cueva, José Roberto Galaviz-González, María de la Luz Pérez-Rea and Manuel Alberto Gallardo-Sánchez    
The Mexican asphalt paving industry is increasingly interested in using reclaimed asphalt pavement (RAP) to produce hot mix asphalt (HMA) due to its economic and environmental advantages. However, an ill-defined methodology for integrating RAP into the H... ver más
Revista: Infrastructures

 
Kaifeng Wang, Ziyu Lu, Yingxue Zou, Yunsheng Zhu and Junhui Yu    
For improving the night recognition of road markings and enhancing the driving safety of asphalt pavements, single-factor optimization is used to investigate the effects of the component materials, including luminescent power, pigment, filler, and anti-s... ver más
Revista: Coatings

 
Ana Luiza Rodrigues, Caio Falcão and R. Christopher Williams    
Crosslinking agents, notably sulfur, are used in asphalt binder modification to facilitate chemical bonding between polymer chains and the asphalt binder. Despite some prior research indicating the benefits of sulfur crosslinking in enhancing polymer-mod... ver más
Revista: Infrastructures

 
Jorge Pais, Paulo Pereira and Liseane Thives    
Connected and Autonomous Vehicles (CAV) will change how road engineers design road pavements because they can position themselves within a traffic lane, keeping their position in the lane more precisely than human-driven vehicles. These vehicles will hav... ver más
Revista: Infrastructures

 
Hatim M. Akraym, Ratnasamy Muniandy, Fauzan Mohd Jakarni and Salihudin Hassim    
Over four decades, researchers have extensively focused on bonding flexible pavement layers. Scholars have concentrated on the partial or complete lack of interlayer bonding between asphalt layers, which is the primary cause of premature pavement failure... ver más
Revista: Infrastructures