Abstract:
Pavement maintenance and rehabilitation are critical components of a Pavement Management System (PMS), ensuring roads remain in serviceable condition, addressing distresses in a timely and cost-effective manner. Depending on the severity of the surface deterioration, rehabilitation is prioritized over maintenance, increasing the pavement’s lifespan. The International Roughness Index (IRI) is a critical metric for evaluating pavement surface roughness and assists in determining the need for proper treatments. Therefore, an efficient IRI model capturing the influence of climate on treatment types is the prerequisite to making any decision on proper treatment types. Utilizing the United States flexible pavement sections data from the Long-Term Pavement Performance (LTPP) program, the research examined the effectiveness of different rehabilitation treatments across various climate conditions through the IRI models. Fuzzy c-means clustering technique was used, categorizing climate conditions into three clusters. Moreover, feature importance and multicollinearity analysis helped evaluate influential IRI model variables. This study employed multiple linear regression (MLR) and artificial neural networks (ANNs) to predict IRI. The results revealed that both models performed well under different climatic conditions with reasonable accuracy (R-squared > 80% and MSE < 0.2). The results showed that milling existing pavement and overlay with hot mix recycled asphalt concrete consistently outperformed the control asphalt concrete overlay in all climatic conditions, while recycled asphalt concrete overlay was more effective than asphalt concrete overlay in moderate to hot climates. Warm mix asphalt concrete overlay performed better than asphalt concrete overlay in cold to moderate climate conditions but less effective in hot regions
Contributors: Khan S, Barzegaran J, Hossain K, Swarna S.