Are you an EPFL student looking for a semester project?
Work with us on data science and visualisation projects, and deploy your project as an app on top of Graph Search.
Publication
Are you an EPFL student looking for a semester project?
Work with us on data science and visualisation projects, and deploy your project as an app on top of Graph Search.
Recent advances in the application of nontraditional methods and procedures for offline diagnosis and online monitoring of new and service-aged power transformers are discussed. Advanced offline methods are based on the main operational stresses (electrical, mechanical, thermal) and on typical failure modes: measurement of polarisation and depolarisation currents, electrical detection of partial discharges and measurement of the transfer function. A pilot installation of an online monitoring system on a strategically important transformer is described. The measured data of the built-in sensors (e.g. load, temperatures, gas and moisture in oil, overvoltages) are analyzed using a model-based software approach with an adaptive threshold to define faulty conditions
Marcos Rubinstein, Hamidreza Karami
, , ,