Condition monitoring of power transformers, which are key components of electrical power systems, is essential to identify incipient faults and avoid catastrophic failures. In this paper machine learning algorithms, i.e. nonlinear autoregressive neural networks and support vector machines, are proposed to model the transformer thermal behavior for the purpose of monitoring. The thermal models are developed based on the historical measurements from nine transformers comprised of two 180-MVA units, four 240-MVA units and three 1000-MVA units. The data consist of load profile, tap position, winding indicator temperature (WTI) measurement, ambient temperature, wind speed and solar radiation. The results are validated against field measurements, and it is clearly demonstrated that the alternative algorithms surpass the IEEE Annex G thermal model. An incipient thermal fault identification algorithm is then proposed and successfully used to identify an issue using measurements taken in the field. This algorithm could be used to alert the operator and plan intervention accordingly.

The aim of this work is to develop a top-oil thermal model based on the thermal-electrical analogy and heat transfer principles that captures the thermal influence of prevailing winds and solar radiation which can be generally applied to large power transformers. The key improvements of the proposed thermal model are calculating the heat transfer coefficient of the radiator on the air side using the Nusselt number of combined forced and natural convection, and including the solar radiation as an addition heat source. The proposed model is validated with the operational measurements of 3 transformers that are comprised of a 120/240-MVA unit and two 90/180-MVA units. The results are also compared with the predictions based on the IEEE-Annex G model. The proposed model is more accurate over windy and summer periods as expected.

No abstract

No abstract

No abstract