Photovoltaic array fault diagnosis method based on K-SVD training sparse dictionary

Abstract

The invention relates to a photovoltaic array fault diagnosis method based on a K-SVD training sparse dictionary. Multiple groups of photovoltaic array normal, short circuit and open circuit current sample signals are acquired to construct training sample matrixes; each sample signal is subjected to normalization processing; a K-SVD algorithm is called to determine the row number N and the columnnumber M of the training sample matrix, the vocabulary K and the sparsity L of the sparse dictionary and the number of iterations n; a normal sample matrix, a short circuit sample matrix and an open circuit sample matrix are used to train a normal sparse dictionary, a short circuit sparse dictionary and an open circuit sparse dictionary; an OMP algorithm is called, the three sparse dictionaries are used to reconstruct detected sample signals respectively, and correlation coefficients between the three reconstructed signals and the detected sample signals are calculated; and according to the sizes of the correlation coefficients between the detected sample signals and the reconstructed signals of the sparse dictionaries, diagnosis and classification on photovoltaic array faults can be realized. Research experience and research ideas can be provided for photovoltaic fault diagnosis.

Description

technical field [0001] The invention relates to a photovoltaic array fault diagnosis technology, in particular to a photovoltaic array fault diagnosis method based on K-SVD training sparse dictionary. Background technique [0002] Because of its clean, non-polluting and inexhaustible characteristics, solar energy has become a strategic means to solve global energy shortages and environmental pollution. Photovoltaic power generation is the main way to utilize solar energy. With the support of national policies, the photovoltaic power generation industry has risen rapidly, bringing huge economic and environmental benefits. In photovoltaic power generation systems, photovoltaic power generation arrays, as the core components of solar energy collection, usually work in complex and changeable outdoor environments, and are easily affected by harsh factors such as wind, frost, rain and snow, resulting in failures such as short circuits, open circuits, shadows, etc. Faults will red...

AI Technical Summary

Problems solved by technology

[0005] At present, there is no research on applying K-SVD training sparse dictionary to fault diagnosis and classification of photovoltaic power generation arrays in published literature and patents

Images