Big data-based fuzzy prediction and evaluation of performance of cold recycled asphalt pavement

Abstract

Cold recycling of asphalt pavement is important in realizing sustainable development of highway transportation. Understanding change laws of cold recycled asphalt pavement (RAP) performance is important in the correct evaluation of pavement quality and scientific formulation of maintenance strategies. Various performance indexes were analytically demonstrated to predict and evaluate change laws of the cold RAP performance. The proposed cold recycled pavement evaluation indexes were divided into three fuzzy grades of evaluation indexes and subindexes. Integral algorithms from four indexes, namely, pavement surface condition index, riding quality index, rutting depth index, and pavement structure strength index (PSSI), were combined on the basis of the traditional gray prediction model GM (1,1). Index weights were determined according to improved analytic hierarchy process, and a performance index database system based on historical data was established for the cold RAP. Finally, an evaluation system was set up on the basis of the prediction model GM (1,1), and prediction and evaluation results were analyzed with existing data. Results showed the excellent performance of the proposed method with the maximum weight of PSSI and a cold recycled pavement evaluation index score of 77.45. Goodness of fit between the prediction curve and original data is favorable with minimal relative errors. The curve analysis of evaluation indexes demonstrated the satisfactory performance of the pavement with the overall slow declining trend of pavement performance indexes. The research results of this study can provide a reference for evaluating performance variation trends of road network-level cold RAPs.