Downloads: 120
M.Tech M.E PhD Thesis | Electrical Engineering | Volume 7 Issue 6, June 2018 | Pages: 1818 - 1822 | India
Analysis of DGA Methods for the Incipient Fault Diagnosis in Power Transformer Using ANN
Abstract: Power transformers are the heart of electric power distribution and transmission systems. Power transformers are always under the impact of electrical, mechanical, thermal and environmental stresses. DGA is one of the reliable and proven techniques to detect incipient fault in transformer. But the main drawback of the ratio methods is that they fail to cover all ranges of data. The proposed ANN algorithm applied to DGA has been tested by many real fault samples, and its results are compared with conventional DGA methods i. e. Doernenburg Ratios Method, Rogers Ratio method and IEC ratio methods. ANN approach is automatically capable of handling highly nonlinear input output relationships, acquiring experiences which are unknown to human experts from training data and also to generalize solutions for a new set of data.
Keywords: Artificial Neural Network ANN, Dissolved Gas Analysis DGA, Doernenburg Ratios Method, IEC ratio method, Rogers ratio method
How to Cite?: Rajat S. Zade, Prof. Sagar Kudkelwar, "Analysis of DGA Methods for the Incipient Fault Diagnosis in Power Transformer Using ANN", Volume 7 Issue 6, June 2018, International Journal of Science and Research (IJSR), Pages: 1818-1822, https://www.ijsr.net/getabstract.php?paperid=ART20183678, DOI: https://dx.doi.org/10.21275/ART20183678