A photovoltaic array hot spot detection method based on PSO optimized PCNN

• Main Authors: MAO MINGXUAN, WAN YIHAO, ZHOU LIN, LI HAIXIAO, LIU QIANG, ZHANG QIANJIN, ZHOU SIYU, WU HAO, XIE BAO, XI XINZE, GUO KE, HAO GAOFENG
• Format: Patent
• Language: Chinese; English
• Published: 11.12.2018
• Subjects: CALCULATING; COMPUTING; COUNTING; IMAGE DATA PROCESSING OR GENERATION, IN GENERAL; PHYSICS

The invention discloses a photovoltaic array hot spot detection method based on a PSO optimized PCNN, belonging to the photovoltaic power generation field. Firstly, the R component in RGB color spaceis used to process the image, and then the region of photovoltaic array is extracted by shape feature recognition. Secondly, the image is transformed from RGB to HSV color space, and the hot spot region of S component image in HSV space is segmented by PCNN algorithm. For a PCNN algorithm, the maximum entropy criterion is used to determine the number of iterations, and particle swarm optimization(PSO) is used to optimize its parameters, which simplifies the operation process and improves the effect of segmentation. 本发明公开了种基于PSO优化PCNN的光伏阵列热斑检测方法，属于光伏发电领域。首先使用RGB颜色空间下的R分量进行处理，并利用形状特性识别提取光伏阵列区域，然后进行RGB到HSV颜色空间的转换，使用PCNN算法对HSV空间的S分量图像进行热斑区域分割。对于PCNN算法，本文采用最大熵准则确定迭代次数，以及利用粒子群算法(PSO)优化其参数，简化了操作过程，并提高分割的效果。