Decision tree SVM fault diagnosis method of photovoltaic diode-clamped three-level inverter
US10234495B2 · kind B2 · utility
Assignee
Inventors
Key dates
| Filing date | Dec 30, 2016 |
| Grant date | Mar 19, 2019 |
| Priority date | — |
| Expiry date | Apr 2, 2037 |
Classification
- Technology area (CPC Y)Emerging Cross-Sectional Technologies
- CPC primaryY02E10/50
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
The present invention discloses a decision tree SVM fault diagnosis method of a photovoltaic diode-clamped three-level inverter in view of fault diagnosis problems of the photovoltaic three-level inverter in a photovoltaic microgrid. Taking an inverting state for example, firstly, analyzing running conditions of an inverter main circuit and performing fault classification, then taking the middle, upper and lower bridge leg voltages as measurement signals, extracting feature signals with a wavelet multiscale decomposition method, and thereby generating a decision tree SVM fault classification model with a particle swarm clustering algorithm, to finally achieve multi-mode fault diagnosis of the photovoltaic diode-clamped three-level inverter. Advantages of the present invention are that, this algorithm can obviously distinguish various fault states of the photovoltaic diode-clamped three-level inverter, complete the failure diagnostic task with fewer classification models And the diagnosis precision is high. The anti-interference capability is strong.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.