Multivariable analysis methods applied to variables optimisation in manufacturing processes

Generally, a large number of variables and parameters are involved in a manufacturing process; they are divided into INPUT (IP) and OUTPUT (OV). Usually, IPs are controlled by the manufacturing designer. In contrast, OVs frequently depend on a large number of factors, including IP, they are hardly controllable and they involve very difficult study. The present work is the result of a study on the application of methods of multivariable analysis to manufacturing processes. These methods have been selected on the basis of the use of an experimental design based on an orthogonal array, and the applicability of Grey Relational Analysis (GRA) as a tool for analysing the influence of different parameters on OVs has been studied. Processes in which it is desired to know how their variables are modified with multiple factors in a wide range of values are proposed, and applied to the design of experimental tests, making a joint modelling of variables.