Radial basis function neural network-based maximum power point tracking for photovoltaic brushless DC motor connected water pumping system

In this project, a solar water pumping system topology using a Radial Basis Function Neural Network is proposed (RBFNN) to track the Maximum Power Point (MPP) in a Photovoltaic (PV) array fed Brushless DC (BLDC) motor drive effectively. The integration of Artificial Intelligence (AI) control techniques for efficient energy extraction will provide the solar energy systems with increased efficiency. 

The RBFNN Maximum Power Point Tracking (MPPT) predicts the duty ratio of a Single-Ended Primary Inductor Converter (SEPIC) to reach the MPP. The performance of the system under study is compared to trivial MPPT techniques with varying irradiance, temperature and partial shading condition (PSC). 

The performance in terms of voltage ripple, current ripple, average power loss, MPP settling time, efficiency, torque ripple and stator current total harmonic distortion (THD) is evaluated to show the effectiveness of the proposed MPPT method. The proposed system is modeled in Matlab/Simulink.

Keywords: Maximum power point tracking, Radial basis function neural network, Photovoltaic array, Partial shading condition, Single-ended primary inductor converter, Brushless DC motor.