PV Module Fault Diagnosis Based on I–V Curve Deformation Characteristics and Computer Vision

Early diagnosis of PV module faults is crucial to reducing maintenance costs. The I–V curve can be intuitively used for diagnosis, but traditionally, only certain feature points on the curve are extracted, neglecting the entire curve's deformation characteristics. This paper analyzes the I–V curves deformation characteristics based on three-diode model (TDM), and presents a novel diagnosis method utilizing I–V curve and computer vision. The voltage, current, and power corresponding to each point on the I–V curve is mapped to the three channels in RGB format to form a color image. In this way, the complete deformation features of the I–V curve can be captured and converted into color features on the image. The improved Multi-Axis Vision Transformer (I-MaxViT) is proposed for fault diagnosis on the color image by introducing the scaled cosine attention mechanism and log-spaced continuous position deviation into MaxViT block, which reduces the model's computational complexity. Experimental results demonstrate that the proposed innovative diagnostic method achieves the highest diagnostic accuracy, reaching 94%, when compared to the other six diagnostic algorithms, and shows better universality.