Title: Multiple response optimisation based on the ANN theory of complex injection moulding process

Authors: Hai-tao Su; Wei-bin Xie; Hui Zeng

Addresses: Department of Economics and Management, Nanchang University, Nanchang, Jiangxi Province 330031, China ' Department of Economics and Management, Nanchang University, Nanchang, Jiangxi Province 330031, China ' Department of Economics and Management, Nanchang University, Nanchang, Jiangxi Province 330031, China

Abstract: Multiple response optimisation design can effectively improve the quality of the products, and generate huge economic benefits. For multiple response problem in the process of industrial production, owing to the control variables, and because the relationship between the control variable is relatively complex, the traditional multiple response optimisation method will not be able to improve the fitting model. On the basis of the theory of ANN, this paper builds a multiple response optimisation model of the injection moulding process, using Principal Component Analysis (PCA) to deal with multiple correlation between response factor, through the TOPSIS method to obtain the optimal level of factor combination, combined with the enterprise product injection instances, and effectively solve the complicated multiple response optimisation problems in moulding process, with a certain referential significance.

Keywords: ANNs; artificial neural networks; PCA; principal component analysis; TOPSIS; correlation; multiresponse optimisation; complex processes; injection moulding; multiple response optimisation.

DOI: 10.1504/IJCAT.2014.066724

International Journal of Computer Applications in Technology, 2014 Vol.50 No.3/4, pp.186 - 190

Published online: 07 Feb 2015 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article