Interval type-2 fuzzy set application in fault detection for chemical reactor with TLBO algorithm

In this paper, an innovative fault detection method has been presented for nonlinear systems based on interval type-2 fuzzy model. In the proposed approach, a confidence bound has been obtained for the input-output data in the normal operating conditions of the system. The confidence bound is approximated by using a fuzzy model with interval parameters. Confident bound makes it possible to use arbitrary sets of identification input signals. Finally, a chemical reactor system has been used to demonstrate the benefits of the proposed method in fault detection applications.