Prediction interval-based ANFIS controller for nonlinear processes

Prediction interval (PI) has been appeared as a
promising tool to quantify the uncertainties and disturbances
associated with point forecasts. Despite of its numerous applications
in prediction problems, the use of PIs in control
application is still limited. In this paper, a PI-based ANFIS
controller is proposed and designed for nonlinear systems. In
the proposed algorithm, a PI-based neural network model (PINN)
is developed to construct the PIs, and this model is used
as an online estimator of PIs for the controller. The PIs along
with other traditional inputs are used to train the inverse ANFIS
model. The developed PI-based ANFIS model is then used as
a nonlinear PI-based controller (PIC). The performance of the
proposed PIC is examined for a nonlinear numerical plant.
Simulation results revealed that the proposed PIC performance
is superior over the traditional ANFIS-based controller.