Hybrid self-organizing fuzzy and radial basis-function neural-network controller for gas-assisted injection molding combination systems

Abstract

This study proposed a self-organizing fuzzy controller (SOFC) to manipulate a gas-assisted injection molding combination system (GAIMCS) and determined the control performance of the system. However, both the learning rate and the weighting distribution of the SOFC are difficult to select and are fixed after selection. To address this problem, this study developed a hybrid self-organizing fuzzy and radial basis-function neural-network controller (HSFRBNC) for GAIMCSs. The HSFRBNC uses a radial basis-function neural-network to regulate the parameters of the SOFC for achieving appropriate values in real time. It not only overcomes the difficulty of finding appropriate parameters of the SOFC but also reduces the time needed to establish suitable fuzzy control rules for manipulating the GAIMCS. Experimental results showed that the HSFRBNC has better control performance than the SOFC in controlling the GAIMCS.