Diagnose of faults in power transformers using electronic nose

The failures of power transformers may cause the loss of a significant amount of life and property. Therefore, some mechanisms should be developed to predict transformer failures before they may occur. In this study, a new device has been designed to detect transformer failures that may occur over time before they reach a serious level. Thus, it will be possible to exchange the necessary parts and equipment on the transformer that has incipient faults, or to change the transformer before it is too late.Certain gases are released in transformer insulating oil in changing working conditions over time. The type and amount of gases in the transformer oil provide information about the status of the transformer. In the study, an electronic nose has been implemented to determine the gases that are released from transformer oil. Various catalytic chemical gas sensors are used in the electronic nose system. The gas samples, that simulate the gas mixtures that of malfunctioned transformers, have been applied to the implemented system and the type of fault has been determined by the sensor responses via information extraction. The chemical sensors that are used in the electronic nose can detect only gases that release in the case of transformer insulating paper deformations and partial discharge events. Thus, damages to the transformer cellulosic paper or pressboard-based solid insulation and partial discharges in the transformer oil or paper are tried to determine by the implemented electronic nose system.As a result of the experiments, the levels of the gases evolved during the transformer fault can be detected with the designed system and the levels of the gases can be continuously monitored for the observation of transformer aging. The designed system cost much less than the existing monitor systems. In the near future, electronic nose systems could widely be used to determine incipient faults in power transformers.