Photovoltaic array fault diagnosis method based on non-intrusive state detection

Abstract

The invention belongs to the technical field of photovoltaic power generation, and particularly relates to a photovoltaic array fault diagnosis method based on non-intrusive state detection. On the basis of performing principal component analysis on original data, time sequence voltage and current data are subjected to pole symmetry mode decomposition, and mirror image continuation is adopted to repair breakpoint missing of an eigenmode function after mode decomposition. Hilbert-Huang transformation is carried out on the decomposed eigenmode function, Hilbert marginal spectrum energy is formed, actual waveforms of time sequence voltage and current are amplified, the influence of noise is reduced, and effective extraction of eigenvectors is achieved. A combined classifier formed by an Adaboost algorithm is utilized, a fuzzy clustering-mahalanobis distance model is adopted to calculate the vector similarity of a sample group, the weight coefficient of the combined classifier is effectively updated, and the perceptual ability of the classifier to errors is enhanced, so that effective mining of fault data is realized, and online fault diagnosis of a photovoltaic array system is realized.

Description

technical field [0001] The invention belongs to the technical field of photovoltaic power generation, and in particular relates to a photovoltaic array fault diagnosis method based on non-invasive state detection. Background technique [0002] With the continuous improvement of support for renewable energy, more and more large-scale photovoltaic equipment has been put into use. As an important part of photovoltaic power generation system, photovoltaic array is particularly important for its electrical parameter monitoring and fault type diagnosis. Since photovoltaic power generation equipment is generally located in deserts, mines, and roofs, and the working environment is relatively harsh, the operating state and insulation level of photovoltaic array components are greatly affected by the external environment, which makes photovoltaic arrays prone to short circuits, open circuits, and insulation aging. Failures are not uncommon. It can be seen that it is of great practic...

AI Technical Summary

Problems solved by technology

The disadvantage of this method is that when the photovoltaic array is at the maximum power tracking point (MPPT), the data error between the simulation model and the actual system increases, which will cause serious judgment errors in the fault diagnosis model

The I-V curve analysis method is a common method for fault diagnosis of photovoltaic arrays, and it is widely used in engineering practice. However, when using this method, the inverter needs to be taken out of operation, which will cause unnecessary human errors.

Images