English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Generators are one of the vital elements in power systems. Although the probability of fault in generators is not significant, the occurrence of a small fault may lead to huge and irreparable damages to the power system and the generator itself. This research is done with the aim of detecting partial demagnetization fault in wind turbine permanent magnet generators using data-driven methods. In order to realize correct and accurate fault signals, the fault modeling and simulation approach based on the finite element analysis method is used to simulate the PMSG generator. A 24-slot 4-pole generator is simulated as a case study using the finite element method and FEM software. Subsequently, the fast Fourier transform method is used to extract the signal, and the magnetic fault is simulated using the finite element method in Flux software. Also, the counter-electromotive force signal for 100 fault modes from one to one hundred is gradually extracted with one percent steps. The developed artificial neural network is recognized the corresponding class of each signal correctly. Demagnetization fault modeling in an artificial neural network can correctly classify all fault signals except one signal. As a result, the accuracy of the artificial neural network modeling the demagnetization fault has reached 95%.

Detection of Partial Demagnetization Fault in Wind Turbine Permanent Magnet Generator Using a Data-Driven Method