Development of a Tire/Pavement Contact-Stress Model Based on an Artificial Neural Network

Abstract

Abstract This paper presents comprehensive tire/pavement contact-stress models based on the Artificial Neural Networks developed by the authors at the Pennsylvania Transportation Institute and Applied Research Laboratory of the Pennsylvania State University. These models represent the first mathematical representation of measured, vertical contact stress at wide ranges of vertical loads and inflation pressures for two types of tires. The Developed ANN model has the capabilities to generate complex stress distribution patterns under a tire at any given load and inflation pressure for a specific tire type used for the ANN training. The information given here is considered to be an important contribution to the ongoing efforts to improve tire/pavement contact stress modeling and analysis. The neural network representation of a tire contact stress distribution is denoted as “Neuro-Patch Model”. The neural network models have been trained using precisely measured, three-dimensional contact-stress distribution patterns obtained from low speed rolling tire tests conducted by the University of California at Berkeley. This data has been supplied by the Federal Highway Administration (FHWA). In this study two types of tires, namely a 11R22.5 Radial-Ply and a 10.00 × 20 Bias-Ply truck tire, were modeled at different inflation pressures ranging from 520 kPa to 920 kPa and vertical loads ranging from 26 kN to 56 kN.