Modeling the Deterioration of Pavement Skid Resistance and Surface Texture After Preventive Maintenance

2025-07-02

AI Summary

The degradation patterns of post-micro-milling pavement skid resistance (SN) and macrotexture (MPD) remain poorly understood, hindering evidence-based preventive maintenance evaluation. Method: Leveraging long-term time-series monitoring data from 31 highway segments across four climatic zones in Texas, this study develops data-driven predictive models that integrate environmental variables and construction parameters to capture their nonlinear, coupled degradation mechanisms. Contribution/Results: A Transformer-based model achieves high-accuracy SN prediction (R² = 0.981), while a random forest model efficiently forecasts MPD evolution (R² = 0.838). Both outperform conventional linear and tree-based models, significantly improving prediction fidelity for post-micro-milling performance deterioration. The framework provides a generalizable, physics-informed modeling paradigm to quantitatively assess long-term micro-milling effectiveness and support optimized, lifecycle-oriented maintenance decision-making.

Technology Category

• Planning, Routing, and Scheduling: Model-Based Reasoning
• Machine Learning: Feature Construction/Reformulation
• Data Mining & Knowledge Management: Scalability, Parallel & Distributed Systems

Application Category

• Web Mining and Content Analysis: Models for Web evolution
• User Modeling, Personalization and Recommendation: Metrics for user behavior and evaluating success
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

This study investigates the deterioration of skid resistance and surface macrotexture following preventive maintenance using micro-milling techniques. Field data were collected from 31 asphalt pavement sections located across four climatic zones in Texas, encompassing a variety of surface types, milling depths, operational speeds, and drum configurations. A standardized data collection protocol was followed, with measurements taken before milling, immediately after treatment, and at 3, 6, 12, and 18 months post-treatment. Skid number and Mean Profile Depth (MPD) were used to evaluate surface friction and texture characteristics. The dataset was reformatted into a time-series structure with 930 observations, incorporating contextual variables such as climatic zone, treatment parameters, and baseline surface condition. A comparative modeling framework was applied to predict the deterioration trends of both skid resistance and macrotexture over time. Eight regression models, including linear, tree-based, and ensemble methods, were evaluated alongside a sequence-to-one transformer model. Results show that the transformer model achieved the highest prediction accuracy for skid resistance (R2=0.981), while Random Forest performing best for macrotexture prediction (R2 = 0.838). The findings indicate that the degradation of surface characteristics after preventive maintenance is nonlinear and influenced by a combination of environmental and operational factors. This study demonstrates the effectiveness of data-driven modeling in supporting transportation agencies with pavement performance forecasting and maintenance planning.

Problem

• Investigates skid resistance deterioration after micro-milling maintenance
• Evaluates predictive models for pavement surface friction and texture
• Analyzes environmental and operational impacts on pavement degradation

Innovation

• Micro-milling techniques for pavement maintenance
• Time-series data analysis with contextual variables
• Transformer model for skid resistance prediction