Statistical Analysis for Design Improvement of Wheels  
Author Zhi-Sheng Ye


Co-Author(s) Jian-Guo Li; Min Xie


Abstract The mechanical properties of wheels vary among the wheel population. The variation comes from two sources, i.e., within-model variation and between-model variation. It is qualitatively known that different wheel models have different shapes, which affect the mechanical properties of the wheels. The between-model variation is thus captured by the shapes of different wheel models and the within-model variation is captured by a random noise. Principal component regression is used to estimate the parameters and the results are interpreted using engineering knowledge.


Keywords Wheel design, multicollinearity, principal component regression
    Article #:  19131
Proceedings of the 19th ISSAT International Conference on Reliability and Quality in Design
August 5-7, 2013 - Honolulu, Hawaii, U.S.A.