Identification of rules using subtractive clustering with application to fuzzy controllers

The common way of developing fuzzy controller is by determining the rule base and some appropriate fuzzy sets over the controller's input and output ranges. A simple and efficient approach, namely, fuzzy subtractive clustering is used here. This approach is used to minimize the number of rules of fuzzy logic controllers. The rule extraction method based on estimating clusters in the numerical data; each cluster obtained corresponds to a fuzzy rule that relates a region in the input space to an output region. The rule base is defined on error and change in error of the controlled variable using the most natural and unbiased membership functions. The simulation analysis on a wide range of processes is carried out. The clustering based fuzzy logic controllers is compared with those of conventional fuzzy logic controllers. The fuzzy subtractive clustering approach is shown to reduce 49 rules to 8 rules maintaining almost the same level of performance.