The fault diagnosis method of photovoltaic module based on probabilistic neural network

2nd International Symposium on Resource Exploration and Environmental Science

生态环境科学

Wu, Yongxin^1 ; Wang, Hu^1 ; Guo, Tingting^2

China Datang Corporation Science and Technology Research Institute, Beijing, China^1

Department of Physics, College of Sciences, Tianjin University of Science and Technology, Tianjin, China^2

关键词: Dust deposition;    Equivalent circuit model;    Fault diagnosis method;    Fault diagnosis model;    Output characteristics;    Partial shading;    Photovoltaic modules;    Probabilistic neural networks;   

Others  :  https://iopscience.iop.org/article/10.1088/1755-1315/170/4/042009/pdf
DOI  :  10.1088/1755-1315/170/4/042009

学科分类：环境科学（综合）

来源: IOP

【 摘 要 】

This paper describes a fault diagnosis method of photovoltaic (PV) module, which bases on equivalent circuit module and probabilistic neural network (PNN). The output characteristics of the PV module under normal, dust deposition, abnormal aging and partial shading conditions are simulated by using the equivalent circuit model. The simulated data are used as characteristic parameters to fault type diagnosis. The performance of the fault diagnosis model is evaluated, and the results indicate that the method can detect the fault types correctly.