Multivariable self-organizing fuzzy logic control (SOFLC) using a switching mode linguistic compensator

Due to the interactions between the control channels, it is not an easy task to express the control strategies in the form of related multi-situations to multi-actions control fuzzy rules. Decoupled control is one answer to this problem. It separates the control task into two types: one is the dominating controller applied to fulfill the tracking task of a particular single-situation to a single-action loop, and the other is the compensator used to decouple the channels themselves. This paper adopts the self-organizing fuzzy logic control (SOFLC) strategy, which has the ability of self-generating and modifying the control rules depending on the on-line system control information, as the main controller for each channel. The compensating controller is triggered according to the nature of the effect of the interaction from the corresponding channel. The strategy of identifying the interaction effect follows the system performance evaluation method applied in SOFLC as well. A series of simulations were carried out on a two-input and two-output biomedical process, with the conclusion that the proposed decoupling control mechanism has the ability to deal with varying system dynamics, noise and inaccurate estimation of compensator gains very effectively.