Bibliographic Details
| Title: |
Fault diagnosis of intelligent substation relay protection system based on transformer architecture and migration training model. |
| Authors: |
Mei, Yao, Ni, Saisai, Zhang, Haibo |
| Source: |
Energy Informatics; 11/19/2024, Vol. 7 Issue 1, p1-18, 18p |
| Subject Terms: |
Pattern recognition systems, Fault diagnosis, Transformer models, Technology transfer, Sustainable development |
| Abstract: |
In the context of global energy transformation, the construction of smart grids is becoming a novel vogue in the evolution of power systems. As the core node of the smart grid, the efficient operation of the intelligent substation relay protection system is essential to the safety and stability of the power system. However, with the expansion of power grid-scale and complexity, traditional relay protection systems need help with fault diagnosis accuracy and response speed. This study proposes a fault diagnosis scheme of an intelligent substation relay protection system based on Transformer architecture and migration training model, aiming at improving the intelligent level of fault diagnosis. By introducing the Transformer architecture, the model can efficiently process high-dimensional and nonlinear complex data of substations, significantly improving the accuracy of fault pattern recognition from 82% of the original model to 96%, and the response speed is also increased by 30%. At the same time, using transfer learning technology, the adaptability and generalization capabilities of the model in new scenarios have been significantly enhanced, reducing the dependence on a large amount of new data and accelerating the deployment of the model among different substations. The experimental results show that this scheme can quickly and accurately identify various fault types and effectively locate fault points. This study not only promotes the development of intelligent technology for power systems but also lays a solid foundation for the safe and stable operation of smart grids and the sustainable development of the power industry. [ABSTRACT FROM AUTHOR] |
|
Copyright of Energy Informatics is the property of Springer Nature and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.) |
| Database: |
Complementary Index |