Integrated Experimental Methods and Machine Learning for Tire Wear Prediction

Abstract

A major challenge in tire research, is tire wear modeling. There are too many factors affecting tire wear, and part of those factors are difficult to be accurately expressed in physics and math.

The objective of this research is to develop a machine learning based rubber sample wear model, and find the correlation between sample wear and tire wear. To develop this model, accurate and diverse wear data is necessary. The Dynamic Friction Tester (DFT) was designed and built for this purpose. This test machine has made it possible to collect accurate rubber sample wear data which has been validated under different conditions. Wear tests under diverse test conditions were conducted, and the test data were used to train machine learned based wear models with different algorithms, such as Neural Networks and Support Vector Machines. With test-proved wear behavior classification as additional input, and feature selection, performance of the trained rubber sample wear model has been further improved.

To correlate rubber sample wear and tire wear, a set of correlation functions were developed and proposed. By validating the correlation functions using tire wear test data collected on roads, this research contributes a fast and economical approach to predict tire wear.