Self-organizing maps applied to monitoring and diagnosis of ZnO surge arresters

In this work a monitoring and diagnostic technique for ZnO surge arresters is proposed. This technique is based on a special kind of Artificial Neural Network (ANN) known as Self-Organizing Maps (SOM), which is a network, trained using unsupervised learning. The proposed technique performs the thermal profile analysis of ZnO surge arresters when submitted to their operating voltage. From this analysis, the SOM network can determine the status of the surge arrester. So, this technique may be a very useful tool to power system utilities in their predictive monitoring activities, as well as to the manufactures, assisting the project of more robust surge arresters.