•  
  •  
 

Turkish Journal of Agriculture and Forestry

Author ORCID Identifier

XUEWEI CHAO 0000-0001-7559-0293

LIXIN ZHANG 0000-0001-8367-6935

YANG LI 0000-0002-4268-4004

CHAO HUANG 0009-0009-8856-8955

JING LI 0009-0002-5028-4438

DOI

10.55730/1300-011X.3192

Abstract

The rapid development of the agricultural photovoltaic integration model holds significant importance in improving land utilization and green energy economic benefits. However, due to the harsh working environment and prolonged exposure to natural conditions, photovoltaic (PV) components are prone to hot spot faults, leading to severe consequences. In this article, we propose a fine-grained PV hot spot fault detection framework based on the fusion of infrared and visible light images, addressing various factors that contribute to hot spot faults. Firstly, multiple sets of infrared and visible light image pairs under different hot spot fault conditions are collected. We employ generative adversarial networks (GANs) to augment the collected infrared-visible light image pairs, effectively expanding the dataset. Subsequently, data augmentation techniques are applied to further increase the data volume. To eliminate information redundancy caused by data augmentation, we introduce a novel information quality evaluation method called Cosine Distance Pseudo-Label Cross-Entropy (CDPC). This method enables the selection of high-quality infrared-visible light image pairs for model training and fine-grained fault detection. Experimental results demonstrate the stability and effectiveness of the proposed detection method based on information fusion, with an average testing accuracy of 93.7% for fine-grained fault recognition. Moreover, the efficiency of data training is significantly improved. Taking 35% of the whole training data as an example, the recognition accuracy trained with high-quality data is nearly 12 percentage higher than that trained with low-quality data. Furthermore, under the premise of the same accuracy, the used dataset can be compressed by 30%, effectively reducing the model training time and carbon emission.

Keywords

Data expansion, information fusion, quality evaluation, photovoltaic failure, fault detection

First Page

430

Last Page

442

Creative Commons License

Creative Commons Attribution 4.0 International License
This work is licensed under a Creative Commons Attribution 4.0 International License.

Download

Share

COinS