Abstract of Thesis presented at COPPE/UFRJ as a partial fulfillment of the requirements for the degree of Master of Science (M.Sc.)

Principal Component Analysis for Parameter Tuning of Plastic Injection Machines

Vicente Fernandes Tino

April/2005

Advisors:

Eugenius Kaszkurewicz Amit Bhaya

Department:

Eletrical Engineering

      This work presents a method for parameter tuning of plastic injection machines with the objective of scrap reduction. The process parameters are adjusted using Principal Component Analysis (PCA) on data sampled from the real time monitoring process. For a given injection machine, mold and raw material, the parameters measured during the adjustment period are stored and, with the use of PCA, it is possible to define clusters of parameters and to generate a record of the best parameter adjustments. Future adjustments made on the basis of this acquired knowledge reduce losses of time and raw material. Automatic adjustment based on this method is discussed.