Ability to organize data spatially while conserving the topological relation between data features makes the Self Organizing Map (SOM) a very useful tool for analysis and visualization of high dimensional data such as a power transformer's Dissolved Gas Analysis (DGA). Past SOM application required large historical data for its training and has limited fault detection sensitivity. In this paper, the effects of input features and data normalization are studied to enhance SOM's clustering. SOM is trained using DGA results extracted from actual faulted transformers. Combination of input features and data normalization methods are tested on SOM before the best SOM is identified. Validation is conducted using several datasets i.e. the IEC Technical Committee 10 database. Compared with past SOM applications, the proposed SOM required lesser training data, improved SOM's sensitivity in incipient fault detection and has good diagnosis accuracy. The proposed SOM is also compared with other AI-based DGA interpretation method i.e. Support Vector Machine (SVM) for benchmarking.INDEX TERMS Dissolved gas analysis, fault detection, power transformer, self-organizing map, data pre-processing.

No abstract

No abstract

This paper presents a comprehensive investigation of the Self Organizing Map (SOM) classification process of good and defective power distribution transformers. Three main features were extracted from the numerical calculation method of the Sweep Frequency Response Analysis (SFRA) signals acquired from the transformers. These features are the input vectors for the SOM classification. Analysis of the results has shown the capability of the features and the SOM classification method to differentiate between good and defective transformers.

No abstract