Cotton yarn engineering using robust regression and criteria of Mallow’s Cp

Abstract

The main purpose of the present study was to predict yarn’s important properties i.e., tensile, unevenness, hairiness, and imperfections of cotton yarn with minimum random errors and maximum accuracy. In this work, cotton fiber properties were measured from rovings carefully untwisted. HVI system and evenness tester of Premier were used to measure the various properties. All yarns (108 samples) were spun at yarn counts of 16, 20, 24, 28, and 32 Ne with optimum twist factor. The robust regression and criteria of Mallow’s Cp were used to evaluate the data. Optimal equations with appropriate variables and relative importance of various variables were also investigated. After the goodness of fit, desirable Cp and very large adjusted R2 values were observed. Furthermore, the analysis of variance tables showed that the obtained equations were significant at usual significance levels.