An Adaptive Neuro-Fuzzy Model to Multilevel Inverter for Grid Connected Photovoltaic System

作者：Karuppusamy P^*; Natarajan A M; Vijeyakumar K N

来源：Journal of Circuits, Systems, and Computers, 2015, 24(5): 1550066.

DOI：10.1142/S0218126615500668

• PV
• cascaded multilevel inverter
• grid voltage
• control voltage
• ANFIS
• FPGA

This paper proposed an adaptive neuro-fuzzy model (ANFIS) to multilevel inverter (MLI) for grid connected photovoltaic (PV) system. The purpose of the proposed controller is that it is not requiring any optimal pulse width modulated (PWM) switching-angle generator and proportional-integral controller. The proposed method strictly prohibits the variations present in the output voltage of the cascaded H-bridge MLI. In this method, the ANFIS have the input which is grid voltage, the difference voltage and the output target is control voltage. By using these parameters, the ANFIS makes the rules and has been tuned perfectly. During the testing time, the ANFIS gives the control voltage according to the different inputs. The resultant control voltage equivalent gate pulses are utilized for controlling the insulated gate bi-polar switches (IGBT) of MLI. Then the ANFIS based MLI for grid connected PV system is implemented in the MATLAB/simulink platform and the effectiveness of the proposed control technique is analyzed by comparing with the neural network (NN), fuzzy logic control, etc. The comparison results demonstrate the superiority of the proposed approach and confirm its potential to solve the problem. A prototype of three-phase grid connected cascaded H-bridge inverter has been developed using field-programmable gate array (FPGA) and results are analyzed.

• 出版日期2015-6