A Data-Driven Method for Comprehensive Pavement-Condition Ranking

Abstract

State highway agencies need pavement-condition data to select candidates for pavement maintenance and rehabilitation. However, it is a challenge for pavement engineers to simultaneously assess a number of attributes that represent different aspects of pavement condition. In conventional practice, empirical comprehensive evaluation methodologies, such as fuzzy set theory and analytical hierarchy process, have been used to aggregate multiple distresses into integrated pavement-performance indices. These methodologies, however, are mostly based on experts’ or engineers’ judgment rather than data-driven approaches. In this paper, a framework of applying a data-driven approach to conduct comprehensive pavement evaluation and ranking is presented. The method of Technique for Order Preference by Similarity to Ideal Solution (TOPSIS) is introduced and applied to rank pavement sections with various evaluation attributes. Principal component analysis (PCA) is employed to combine distresses with high correlations and reduce the data dimension. A case study using data from a pavement management system in Lincoln Parish, Louisiana, is presented to demonstrate the feasibility and effectiveness of the proposed methodology. A total of 18 parameters involving four aspects of pavement condition, surface distress, roughness, safety characteristic, and structural capacity, are analyzed to rank the 35 pavement sections. Discussions and recommendations are presented.