Integrated Experimental Methods and Machine Learning for Tire Wear Prediction

dc.contributor.authorSu, Chuangen
dc.contributor.committeechairTaheri, Saieden
dc.contributor.committeememberAhmadian, Mehdien
dc.contributor.committeememberSandu, Corinaen
dc.contributor.committeememberTarazaga, Pablo Albertoen
dc.contributor.committeememberWang, Linbingen
dc.contributor.departmentMechanical Engineeringen
dc.date.accessioned2020-09-09T06:00:23Zen
dc.date.available2020-09-09T06:00:23Zen
dc.date.issued2019-03-18en
dc.description.abstractA 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.en
dc.description.abstractgeneralTire wear is closely related to the life time of tire, and excessive wear of tire can results in serious accidents. Since 1950s, research have been done to predict tire wear using experiments and empirical relations. These approaches are expensive, time consuming, and highly restricted to certain conditions. The objectives of this research is to develop a statistic based rubber sample wear model, and find the correlation between rubber sample wear and tire wear. To develop the statistic based rubber sample wear model, a test machine, named Dynamic Friction Tester (DFT) was designed and built to collect rubber sample wear data. The final rubber sample wear model is trained by wear data under 600 different test conditions. A set of mathematical equations were proposed to correlate rubber sample wear and tire wear. These equations were validated by actual tire wear data collected from lab and public roads. In combination of the statistic based rubber sample wear model and mathematical relation between rubber sample wear and tire wear, this research contributes a flexible, economical, and fast method to predict tire wear.en
dc.description.degreeDoctor of Philosophyen
dc.format.mediumETDen
dc.identifier.othervt_gsexam:19135en
dc.identifier.urihttp://hdl.handle.net/10919/99929en
dc.publisherVirginia Techen
dc.rightsIn Copyrighten
dc.rights.urihttp://rightsstatements.org/vocab/InC/1.0/en
dc.subjecttire wearen
dc.subjectrubber abrasionen
dc.subjectmachine designen
dc.subjectwear testingen
dc.subjectMachine learningen
dc.titleIntegrated Experimental Methods and Machine Learning for Tire Wear Predictionen
dc.typeDissertationen
thesis.degree.disciplineMechanical Engineeringen
thesis.degree.grantorVirginia Polytechnic Institute and State Universityen
thesis.degree.leveldoctoralen
thesis.degree.nameDoctor of Philosophyen

Files

Original bundle
Now showing 1 - 1 of 1
Loading...
Thumbnail Image
Name:
Su_C_D_2019.pdf
Size:
4.44 MB
Format:
Adobe Portable Document Format