Asphalt pavement friction coefficient prediction method based on genetic-algorithm-improved neural network (GAI-NN) model

• Published in: Canadian journal of civil engineering Vol. 49; no. 1; pp. 109 - 120
• Main Authors: Sun, Zhaoyun, Hao, Xueli, Li, Wei, Huyan, Ju, Sun, Hongchao
• Format: Journal Article
• Language: English
• Published: 1840 Woodward Drive, Suite 1, Ottawa, ON K2C 0P7 NRC Research Press 01.01.2022; Canadian Science Publishing NRC Research Press
• Subjects: 3D point-cloud data; Algorithms; Analysis; Asphalt; Asphalt pavements; Cloud computing; Coefficient of friction; Cube texture; données en nuage de points tridimensionnelles (3D); Friction; friction coefficient prediction; genetic neural network; ingénierie des chaussées; Interpolation; Mathematical models; Mechanical properties; Methods; Missing data; Neural networks; Parameter modification; Parameters; pavement engineering; Pavements, Asphalt; prédiction du coefficient de frottement; réseau neuronal génétique; résistance au dérapage; Skid resistance; Smart sensors; Surface layers; Texture; Three dimensional models; China
• ISSN: 0315-1468; 1208-6029; 1208-6029
• DOI: 10.1139/cjce-2020-0051

To overcome the limitations of pavement skid resistance prediction using the friction coefficient, a genetic-algorithm-improved neural network (GAI-NN) was developed in this study. First, three-dimensional (3D) point-cloud data of an asphalt pavement surface were obtained using a smart sensor (Gocator 3110). The friction coefficient of the pavement was then obtained using a pendulum friction tester. The 3D point-cloud dataset was then analyzed to recover the missing data and perform denoising. In particular, these data were filled using cubic spline interpolation. Parameters for texture characterization were defined, and methods for computing the parameters were developed. Finally, the GAI-NN model was developed by modifying the weights and thresholds. The test results indicated that using pavement surface texture 3D data, the GAI-NN was capable of predicting the pavement friction coefficient with sufficient accuracy, with an error of 12.1%.