Research on Transformer Fault Diagnosis Method Based on Artificial Immune Network and Fuzzy C-Means Clustering Algorithm

Abstract

The transformer is one of the indispensable equipment in transformer substation, it is of great significance for fault diagnosis. In order to accurately judge the transformer fault types, an algorithm is proposed based on artificial immune network combined with fuzzy c-means clustering to study on transformer fault samples. Focus on the introduction of data processing of transformer faults based on artificial immune network, the identification of transformer faults based on fuzzy c-means clustering, and the simulation process. The experimental results show that the proposed algorithm can classify power transformer fault types effectively, and the algorithm has a good application prospect in the transformer fault diagnosis.

Diagnosis of Transformer Faults Using Feature Extraction and Automatic Division Based Fuzzy Clustering

“…After the abnormal data were eliminated, the sample data were identified using fuzzy clustering method. Fuzzy clustering has favorable performance in diagnosing faults and can perform better when combining with other methods, for example, fuzzy cmeans in combination with support vector machine [15], fuzzy c-means in combination with artificial immune network [16] and fuzzy c-means in combination with probabilistic neural network [17]. In this study, a kernel function based dot density weighted fuzzy clustering algorithm was put forward.…”

Archives of Electrical Engineering

“…Besides, transformers of different voltage levels are difficult to make reasonable adjustments when applying the ratio, so most of these traditional diagnosis methods only make a vague judgment on the type of fault, and may even cause misjudgment of the fault type. Due to the diagnosis results of the traditional diagnosis methods are not ideal, the transformer diagnosis methods based on artificial intelligence algorithms such as neural networks [3][4][5][6][7][8][9][10][11], genetic algorithms [12], fuzzy theory [13] and expert systems [14] have developed rapidly.…”