Adaptive-fuzzy detection and assessment of partial shading in solar panels feeding induction motor drives

摘要

The paper presents a methodology based on adaptive neuro-fuzzy inference systems (ANFIS) for the detection and assessment of partial shading conditions in solar photovoltaic (PV) panels. The impact of partial shading on the operation of the induction motor drive load is also studied. The solar panel is modelled under normal and partial shading conditions for performance comparison. Three ANFIS agents are designed, trained, and tested for full identification of the partial shading condition. One ANFIS agent detects the initiation of partial shading, another agent determines the shading factor, and a third agent infers the number of shaded modules of the panel. Results show excellent performance of ANFIS on the detection and assessment of partial shading. Impact on the induction motor drive operation is found insignificant.