hexagon logo

Article MULTIPLE LINEAR REGRESSION

An approach to process improvement

11 March 2013: Thomas Pfeilsticker

This essay explains how to create and evaluate a regression study based on process data. The aim is to find an empirical model y=f(x1, x2, x3…) for our process data explaining their impact on the response.

The injection molding process of a thermoplastic produced components causing problems during the assembly due to high shrinkage. In order to find out about any method to reduce the percentage shrinkage, data about the injection temperature, injection speed and holding pressure were collected. The general model equation leads to percentage shrinkage = f (injection temperature, injection speed, holding pressure).

Which one of the three influencing factors has the major impact on the percentage shrinkage of the injection molding process? And how do you have to adjust the influencing factors in order to minimize the percentage shrinkage of the injection molded parts as far as possible?

Read the full article