Full Text
(45 K)

Applying PCA to Examine the Influence of Fiber Properties on Roving and Yarn Quality Characteristics

Wen-Bin Yu, Clarence D. Rogers


The multi-collinearity between fiber characteristics results in unstable regression coefficients when fiber properties were used to predict/explain yarn quality in a regression analysis. Principal component analysis (PCA) and principal component regression (PCR), which were used in the previous study and generated explainable results, are techniques that can solve the interrelationship exists between fiber characteristics. In this study, PCA and PCR were used to investigate fiber-roving and fiber-yarn relationship and develop reliable models from production data. The results suggest that there might be an important factor, which has not been included in the HVI measures, that affects roving evenness.

Reprinted from Proceedings of the 1996 Beltwide Cotton Conferences pp. 1331 - 1334
©National Cotton Council, Memphis TN

[Main TOC] | [TOC] | [TOC by Section] | [Search] | [Help]
Previous Page [Previous] [Next] Next Page
Document last modified Sunday, Dec 6 1998