首页>
外国专利>
RANDOM FOREST ALGORITHM-BASED PHOTOVOLTAIC ARRAY FAULT DIAGNOSIS METHOD
RANDOM FOREST ALGORITHM-BASED PHOTOVOLTAIC ARRAY FAULT DIAGNOSIS METHOD
展开▼
机译:基于随机森林算法的光伏阵列故障诊断方法
展开▼
页面导航
摘要
著录项
相似文献
摘要
The present invention relates to the technical field of photovoltaics. Disclosed is a random forest algorithm-based photovoltaic array fault diagnosis method. The method comprises: acquiring circuit parameter groups corresponding to branches and a main trunk when a photovoltaic array is in typical operation states; constructing a fault feature vector according to the acquired circuit parameter groups to construct a data sample set; constructing a photovoltaic array fault diagnosis model on the basis of a random forest algorithm by using the data sample set; performing diagnosis on a photovoltaic array to be diagnosed using the model to obtain voting results corresponding to the typical operation states; and obtaining a fault diagnosis result of the photovoltaic array to be diagnosed according to the voting results. The method constructs a photovoltaic array fault diagnosis model by using a random forest algorithm on the basis of a data drive idea, is adapted to actual characteristics of a photovoltaic array, overcomes the defect that a conventional neural network algorithm requires a large data volume, a long training time, and the like, and can easily and quickly complete a diagnosis task.
展开▼