Partial discharge (PD) monitoring is one of the most used tools for diagnosing the condition of electrical equipment and machines that operate normally at high voltage levels. Ideally, PD identification can be easily done if there is a single source acting over the electrical asset during the measurement. However, in industrial environments, it is common to find the presence of multiple sources acting simultaneously, which hinders the identification process, due to sources of greater amplitude hiding the presence of other types of sources of lesser amplitude that could eventually be much more harmful to the insulation system. In this sense, the separation of PD through the use of clustering techniques allows individual source recognition once they have been clearly separated. This paper describes the main clustering techniques that have been used over time to separate PD sources and electrical noise. The results obtained by the different authors in the utilization of each technique demonstrates good performance in terms of separation.INDEX TERMS Partial discharges, separation techniques, noise sources, progress, review.

One of the main tools for monitoring the condition of high voltage equipment is the measurement of partial discharges (PD). The electromagnetic (EM) radiation originated from this degradation phenomenon can be captured by various types of ultra‐high frequency (UHF) antennas carefully designed and optimised for specific frequency bands. However, the presence of environmental noise may limit the use of this technique. Different types of monopole antennas normally used in UHF PD measurement have been evaluated in order to validate the performance of a novel separation technique of EM sources. Accordingly, a new separation technique based on the energy ratio of the captured signals was developed, considering noise interferences. The results revealed that the new technique allows an adequate separation, even when three sources act simultaneously.