Neuro-Fuzzy Adaptive Direct Torque and Flux Control of a Grid-Connected DFIG-WECS With Improved Dynamic Performance

This article presents an adaptive neuro-fuzzy interface system (ANFIS) based direct torque and flux (TF) control technique for manipulation of grid connected doubly fed induction generators (DFIG) in wind energy conversion systems (WECS). The proposed direct TF control technique generates PWM switching signals for the rotor side converter by comparing the actual torque and stator flux with their respective references so as to improve dynamic performance for the WECS. A hybrid training algorithm is proposed to adapt the ANFIS parameters to handle the WECS nonlinearities and wind speed uncertainties. The stability of the developed ANFIS is analyzed by modeling the WECS to a standard second order system. Initially, the effectiveness of the proposed ANFIS technique is examined by simulation under different operating conditions of the DFIG-WECS using MATLAB/Simulink. Then, a laboratory prototype of DFIG-WECS has been developed to investigate the real-time performance of the proposed direct TF control technique. Test results show that the proposed ANFIS direct TF control technique can provide more efficient performance compared to the related traditional techniques such as fuzzy and PI based schemes.