PROJECT TITLE :
Machine learning techniques for robust classification of partial discharges in oil–paper insulation systems
Ageing Power Systems infrastructure and considerations concerning climate amendment have increased interest in the following generation of grid infrastructure, referred to as the good grid (SG). This study studies a significantly important SG application: intelligent monitoring of power transformers for the early detection of insulation failure. Specifically, the main target is on the utilization of machine learning algorithms to differentiate between completely different sorts of partial discharges, that are closely correlated with insulation failure. Measurements created using acoustic emission sensors are used to train and take a look at totally different classification algorithms. In an earlier study, high classification accuracies were achieved using coaching and take a look at datasets collected below similar measurement conditions. However, underneath completely different conditions, classification accuracy was greatly reduced. Experiments using the most recent classification techniques were performed, manufacturing important enhancements in classification accuracy. A possible reason for these results could be a type of overfitting, and further experiments were conducted to check this hypothesis.
Did you like this research project?
To get this research project Guidelines, Training and Code... Click Here