A Method for Diagnosing the State of Insulation Paper in Traction Transformer Based on FDS Test and CS-DQ Algorithm
Article
Article Title | A Method for Diagnosing the State of Insulation Paper in Traction Transformer Based on FDS Test and CS-DQ Algorithm |
---|---|
ERA Journal ID | 210577 |
Article Category | Article |
Authors | Zhou, Lijun (Author), Wang, Dongyang (Author), Cui, Yi (Author), Zhang, Liqing (Author), Wang, Lujia (Author) and Guo, Lei (Author) |
Journal Title | IEEE Transactions on Transportation Electrification |
Journal Citation | 7 (1), pp. 91-103 |
Number of Pages | 13 |
Year | 2021 |
Publisher | IEEE (Institute of Electrical and Electronics Engineers) |
Place of Publication | United States |
ISSN | 2332-7782 |
Digital Object Identifier (DOI) | https://doi.org/10.1109/TTE.2020.3018268 |
Web Address (URL) | https://ieeexplore.ieee.org/document/9171853 |
Abstract | Traction transformer is vital equipment in high-speed railway. Insulation status decides its safety and reliability, and the frequency-domain dielectric spectrum (FDS) test is one of the most effective methods reflecting the changing of insulation status. For field applications, the following problems should be addressed: 1) how to obtain the result of paper insulation from the combined result of the oil-paper insulation system and 2) how to discriminate the defects of insulation paper between aging and damp. In this article, the first problem was transferred to a nonlinear equation set, and a cuckoo search algorithm optimized by the differential evolution algorithm and the quadratic interpolation (QI) method (CS-DQ algorithm) was proposed to solve it. Then, the insulation states were discriminated by establishing a multiclass least-squares support vector machine (LS-SVM) model, in which the CS-DQ algorithm was also used. Finally, a diagnostic approach for the insulation paper in the traction transformer was proposed. The results in the laboratory show that the pure result of insulation paper can be obtained, and the insulation states can be discriminated effectively by using the proposed approach. Meanwhile, the proposed CS-DQ algorithm has a better performance than the conventional CS algorithm. The results of field testing also verify the proposed approach. |
Keywords | Cuckoo search (CS) algorithm optimized by the differential evolution (DE) algorithm and the quadratic interpolation (QI) method (CS-DQ algorithm); frequency-domain dielectric spectrum (FDS) test; high-speed railway; insulation diagnosis; multiclass least-squares support vector machine (LS-SVM) model; traction transformer |
ANZSRC Field of Research 2020 | 400803. Electrical energy generation (incl. renewables, excl. photovoltaics) |
Public Notes | Files associated with this item cannot be displayed due to copyright restrictions. |
Byline Affiliations | Southwest Jiaotong University, China |
University of Queensland | |
University of Macau, China | |
China University of Mining and Technology, China | |
Institution of Origin | University of Southern Queensland |
https://research.usq.edu.au/item/q7w06/a-method-for-diagnosing-the-state-of-insulation-paper-in-traction-transformer-based-on-fds-test-and-cs-dq-algorithm
40
total views2
total downloads1
views this month0
downloads this month