Screening of Process Parameters for Color Fast Finishing Process Using Fractional Factorial Design: A Textile Case Study

Abstract

Screening experiments are the most powerful of design of experiment techniques for uncovering the power factors in a manufacturing process. Often, there are many possible factors, some of which may be critical and others, which may have little or no effect on a response. It may be desirable, as a goal by itself, to reduce the number of factors to a relatively small set (2-5) so that attention can be focused on controlling those factors with appropriate specifications, conducting the main experiment and control charts, and so forth. In this screening design, with eight factors, the experiments were conducted according to the layout of 2IV8-4 fractional factorial design and five response functions values were obtained with two replicates. The factors that had less effect upon the responses were eliminated from the main experiment. The linear model for estimating the responses (shade variation to the standard, color fastness to washing, center to selvedge variation, color fastness to light, and fabric residual shrinkage) was constructed using software Design Expert 8.0. After examining the surface plots and contour plot, it was revealed that the direction of optimum range for responses can be obtained by increasing the significant factors' value. The response functions, surface plots, and contour plots provided a convenient way to find a path of the steepest ascent for the main experiment.