• Research Reports
• Geographic Roadway Inventory Tool (GRIT)
• Event Proceedings
• Staff Presentations
• Other Resources (Surface Selection Tool, Grain Industry Data, etc.)

Research Reports
Report Details

Abstract

The rapid increase in traffic volume and heavy vehicle loads is causing accelerated deterioration of pavement infrastructure worldwide. This research investigates the impact of overweight and dynamic axle loads on pavement performance, employing advanced weigh-in-motion (WIM) systems and machine learning models to enhance predictive accuracy. By integrating data from WIM systems with support vector regression (SVR) and random survival forest models, this study provides a comprehensive analysis of pavement deterioration trends, accounting for high-dimensional variables such as axle load spectra and environmental conditions. The findings reveal that overweight vehicles significantly reduce pavement life, particularly affecting fatigue cracking, rutting, and longitudinal cracking. The application of random survival forest models demonstrates superior predictive performance compared to traditional methods, enabling the development of survival probability curves that inform maintenance strategies. Furthermore, hybrid systems combining in-pavement sensors with roadside cameras and artificial neural networks offer promising solutions for correcting dynamic variables and improving measurement accuracy. This research provides a robust framework for assessing the impacts of traffic loads on pavement performance, offering practical solutions for enhancing infrastructure resilience and sustainability. The insights gained contribute to the optimization of pavement design, maintenance, and rehabilitation strategies, ensuring the longevity and safety of roadways in the face of increasing transportation demands.

How to Cite

Lu, Pan, Denver Tolliver, Xinyi Yang, Jingnan Zhao, Ying Huang, and Hao Wang. Sensitivity and Accuracy Assessment of Vehicle Weigh-In-Motion System Measurement Errors Using In-Pavement Strain-Based Sensors, MPC-24-548. North Dakota State University - Upper Great Plains Transportation Institute, Fargo: Mountain-Plains Consortium, 2024.