polymerjournals Chemistry, materials, technology
Polymers and Polymer Composites

MULTI-RESPONSE OPTIMIZATION OF PC/ABS BLENDS USING PRINCIPAL COMPONENT ANALYSIS

August 1, 2004 By: Chin-Ping Fung; Po-Chung Kang Research article

Title: MULTI-RESPONSE OPTIMIZATION OF PC/ABS BLENDS USING PRINCIPAL COMPONENT ANALYSIS
Page Range: p.679-688
Author(s): Chin-Ping Fung; Po-Chung Kang
File size: 114K
Download the pdf (subscribers only)
Buy the pdf (non-subscribers)
Journal: Polymers and Polymer Composites
Issue Year: ppc
Volume: 12
Issue No: No. 8

Abstract
This paper, using principal component analysis (PCA) based on the Taguchi method, presents the optimum levels of injection moulding parameters in relation to the mechanical properties of polycarbonate/ABS blends. The experiment design used an orthogonal array for the four controllable manufacturing process factors, namely, filling time, melt temperature, mould temperature, and packing pressure, each at three levels, to find the optimum process factor/level combination. The single-response optimisation of the mechanical properties was conducted using the Taguchi method. For a multi-response case, PCA was employed to transform the correlated principal properties to a set of uncorrelated principal components. The optimum process factor/level combination based on the first principal component was determined first. Then the appropriate number of principal components extracted, and the impact of that number on the optimum process condition was investigated by extracting more than one principal component and integrating them into a comprehensive index. Finally, an analysis of variance was used to find the most influential injection moulding parameter for single and multiple response problems. Results are discussed. 20 refs.

Related reading

More journal reading and science coverage connected to this topic.