Hybrid Self-organizing Fuzzy and Radial Basis-function Neural-network Controller for Active Suspension Systems

This study developed a hybrid self-organizing fuzzy and radial basis-function neural-network controller (HSFRBNC) for active suspension systems. The HSFRBNC uses a radial basis function neural-network to adjust the learning rate and the weighting distribution of a self-organizing fuzzy controller (SOFC) in real time, as an alternative to obtain these parameters through trial and error. Therefore, using the HSFRBNC to control active suspension systems not only overcomes the difficulties of finding appropriate membership functions and fuzzy rules in the design of a fuzzy logic controller (FLC) but also solves the problem of determining suitable SOFC parameters. To evaluate the HSFRBNC applicability, the HSFRBNC was used to control an active suspension system and its control performance was determined. Experimental results indicated that the control performance of the HSFRBNC outperforms that of the SOFC, the FLC and the passive control in manipulating the active suspension system.