Data-driven fault identification method and device based on wind turbine fault characteristics

By constructing a controlled current source model and simulation analysis, combined with the CNN-GRU model, the complex current characteristics of inverse power supply are solved, accurate identification of fault types and locations is achieved, and the grid relay protection performance is improved.

CN118940638BActive Publication Date: 2025-03-25NORTH CHINA ELECTRIC POWER UNIV
2 Cites 0 Cited by

Patent Information

Application Number
CN202411096291.9
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-08-12
Publication Date
2025-03-25
Estimated Expiration
2044-08-12

AI Technical Summary

Technical Problem

After the inverter power supply is connected to the grid, the fault current characteristics are complex, and traditional relay protection methods are difficult to accurately identify the fault, which leads to the threat of the safety and stability of the power grid.

Method used

A controlled current source model based on a permanent magnet direct drive wind turbine is constructed, combined with a low voltage crossing strategy and a negative sequence current suppression strategy, and the electrical quantity change law in the steady-state situation of faults is analyzed through simulation models, and a CNN-GRU fault identification model is built to achieve accurate identification of fault types and locations.

Benefits of technology

It improves the accuracy and positioning accuracy of inverse power supply fault identification, enhances the grid relay protection performance, and ensures the safe and stable operation of the new power system.

✦ Generated by Eureka AI based on patent content.
Patent Text Reader

Abstract

The present invention discloses a data-driven fault identification method and device based on the fault characteristics of wind turbines. The fault identification method takes a permanent magnet direct-drive wind turbine (PMSG) in an inverter power supply as a research object, based on a control strategy and considering the fault characteristics of the permanent magnet direct-drive wind turbine, a simulation model of a multi-unit collection and transmission line is constructed by a simplified modeling method, and the variation law of the output line electrical quantity under the steady-state condition of a power grid fault is analyzed based on the simulation model. Based on this variation law, a CNN-GRU data-driven power grid fault identification network model suitable for multi-unit collection and transmission line fault electrical quantity information is constructed, and the accuracy of line fault diagnosis and positioning is further improved through deep learning. The data-driven fault identification method based on the fault characteristics of wind turbines provided by the present invention simplifies modeling processing, has high fault identification accuracy and accurate positioning.
Need to check novelty before this filing date? Find Prior Art