Transformer Health Index by Prediction Artificial Neural Networks Diagnostic Techniques

Abstract

This paper presents the artificial neural network diagnostic techniques for predicting the health index in transformer. Collection data is measured and tested from insulation resistance in between phase-ground, phase to phase and also the winding resistance transformer. The data was collected from 10 units of transformers from Company Transformer Manufacturing and Servicing (CTMS) in Malaysia. The data was used to calculate condition transformer index or health index transformer. Condition transformer index can identify whether transformer in good condition or not good condition. The purpose of knowing transformer health index or condition transformer index is to prevent failures functional transformer and ensure transformer in stable condition. Prediction health index or condition transformer index can be determined by artificial neural network. Therefore, it can monitor and observe very closely conditions of the transformer. Data health index transformer is very important because it know the condition transformer and can solve the major problem in transformer or do the maintenance in early stage before the transformer is totally malfunction.