Electronic International Standard Serial Number (EISSN)
1096-1216
abstract
Tires are the only components of vehicles in contact with the road surface. The tire¿road interaction yields many dynamic parameters that have an impact on the final behavior of the vehicle, such as the forces in the tire¿road interaction, the length of the contact patch, the velocity in the contact patch, and the effective radius of the tire. Previous studies have shown the feasibility of estimating these parameters through the strain curves measured with a tire instrumented with strain gauges, denoted as Strain-based Intelligent Tire. These parameters are required to characterize the loss of grip in the tire¿road interaction. Nonetheless, the time and computer resources required for estimating the level of adherence is not compatible with the need of current active control systems, and the instant data retrieval about the tire¿road surface. The objective of this paper is to present a novel methodology in order to develop an Automatic Full Slip Detection System implemented on the Strain-based Intelligent Tire, while the specific developments for real time will be studied in the further steps of this research. This system operates with two conditions or states in the tire, namely, full sliding situation or non-full sliding situation. The inputs required to provide the tire condition are the strain curves measured when the tire is rolling. Therefore, the algorithms implemented in order to estimate the limit of adherence are presented. To delimit the states, the technique Support Vector Machines (SVM) is used to generate a separation hyperplane between these states. Support Vector Machines (SVM) is one of the most widely used supervised learning algorithms in the area of image recognition and, until now, had not been implemented in the automatic recognition of tire full slip detection.