Photovoltaic Array Fault Diagnosis Method Based on Non-Principal Component Data Features

A photovoltaic array and data feature technology, applied in photovoltaic modules, photovoltaic power generation, photovoltaic system monitoring, etc., can solve problems such as fault diagnosis and classification of photovoltaic power generation arrays that have not yet been seen

CN109039280BInactive Publication Date: 2020-02-18FUJIAN AGRI & FORESTRY UNIV
4 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Publication Date
2020-02-18
Estimated Expiration
Not applicable · inactive patent

Smart Images

  • Figure 1
    Figure 1
  • Figure 2
    Figure 2
  • Figure 3
    Figure 3
Patent Text Reader

Abstract

The invention relates to a photovoltaic array fault diagnosis method based on non-principal component data characteristics, which is characterized in that the method comprises the following steps: 1,collecting relevant parameter samples of the photovoltaic power generation array to obtain a parameter sample combination; 2, normalizing each parameter sample according to the parameter sample combination to obtain a to-be-tested parameter matrix; 3, performing PCA on a standard data matrix to obtain a transformation matrix; 4, multiplying the be-measured parameter matrix by the transformation matrix to obtain the transformed parameter matrix, and selecting two dimensions of non-principal components according to the transformed parameter matrix to obtain a two-parameter non-principal component matrix; 5, mixing the two-parameter non-principal component matrix and known label data, performing clustering analysis, and judging the category of the two-parameter non-principal component matrixdata according to the label data in the category where the matrix data is, thereby completing fault detection and classification. The invention can effectively identify the faults of the photovoltaicarray and classify the working state thereof.
Need to check novelty before this filing date? Find Prior Art

Description

technical field

[0001] The invention relates to the field of photovoltaic power generation fault detection and classification, in particular to a photovoltaic array fault diagnosis method based on non-principal component data features. Background technique

[0002] In order to alleviate the demand for fossil energy and solve the ecological crisis, photovoltaic technology has become the backbone of the new energy field. Benefiting from the improvement of technology level and the reduction of manufacturing cost, coupled with the easy access to and abundant solar energy, the deployment of photovoltaic arrays in the world has steadily increased, and its installed capacity has reached hundreds to thousands of megawatts.

[0003] However, due to its special working environment, photovoltaic systems are often threatened by various external or internal faults, such as component short circuit, open circuit, shadow shading, etc. Photovoltaic system failures can lead to reduced system...

Examples

Embodiment Construction

[0065] The present invention will be further described below in conjunction with the accompanying drawings and embodiments.

[0066] The present invention provides a photovoltaic array fault diagnosis method based on non-principal component data features, the flow chart is as follows figure 1 shown. figure 2 This is the topological diagram of the photovoltaic power generation system in this embodiment. The system consists of m×n photovoltaic modules to form a photovoltaic array, which is connected to the power grid through a grid-connected inverter. Under different atmospheric temperatures and irradiances, different working conditions in the daily operation of photovoltaic power generation arrays are simulated, and data collection of photovoltaic power generation systems is carried out. The concrete operation of embodiment comprises the following steps:

[0067] Step S1: Collect relevant parameter samples of the photovoltaic power generation array to obtain a parameter samp...