Data mining: a technique used to extract information from tan delta measurements on medium voltage induction motors
Abstract
The study attempted to understand the condition of the insulation system and to classify the data according to its condition. Data mining processes were used to gain insight into the data and the condition of the insulation system. The different stages of data mining are explained. An analysis was done using self-organizing maps, which is an unsupervised neural network technique. Hierarchical and K-mean clustering techniques were used to classify the data. The results of the different techniques were compared to an expert's assessment. A comparison was done between the different techniques used. The patterns in the different features of the data due to ageing were observed. The data was qualitatively assessed and classified into groups according to the deterioration of the insulation system using the classification techniques. Finally the results correlated well with the expert's assessment
URI
http://hdl.handle.net/10394/20273https://ieeexplore.ieee.org/document/4401639
https://doi.org/10.1109/AFRCON.2007.4401639