A Context-Based Approach to Fuzzy Type-2 Membership Functions Parametrising in Control Applications
摘要
The article considers the problem of constructing the type of fuzzy membership functions of type 2. The problems are both the complexity of collecting expert information to describe the control function in various systems and the need to update the information extracted from the data sets. The proposed new two-stage approach allows for both the initial setup of the type of fuzzy membership functions and the refinement of the parameters of the membership functions and the “if-then” rule base at the second step of the optimization stage.