An adaptive Neuro-Fuzzy (NF) PI controller for HVDC system

Abstract

Although Fuzzy Logic (FL) controllers for HVDC systems have been previously explored, the optimization of these controllers is still part of active research. In this paper, a 4-layer Neuro-Fuzzy (NF) controller to tune the Fuzzy Rule Base is presented. FL-based PI controllers require gains values as further gains are updated around these values. The proposed controller adds intelligence to the controller as it has the capability of finding out the PI gains with changing system conditions. Gaussian and Triangular membership functions (MFs), corresponding to Radial Basis Functions (RBF) and Cerebellar Model Articulation Controller (CMAC) neural network architecture respectively, have been used to see which one offers a better performance. Results from simulations illustrate the potential of the proposed control scheme as the NF controller successfully adapts to different system conditions and is able to minimize the total current error. Furthermore, a performance comparison with a conventional PI controller is also made.