Application of Meta-Heuristic Approaches in the Spectral Power Clustering Technique (SPCT) to Improve the Separation of Partial Discharge and Electrical Noise Sources

Abstract

In order to achieve an adequate diagnosis of the insulation system in any electrical asset it is necessary to carry out a proper separation process after measuring partial discharges (PD), since during the data acquisition it is very likely that simultaneous PD sources and electrical noise have been measured. Clearly, such separation will simplify the subsequent identification process, because the analysis will be done individually for each of the sources and not over the total of the signals. In this sense, the Spectral Power Clustering Technique (SPCT) has proven to be an effective technique when separating multiple sources acting simultaneously in a monitoring process. The effectiveness of this separation technique is fundamentally based on the proper selection of frequency bands or separation intervals, where the spectral power of the pulses is different for each source. In the case of selecting the wrong bands, the clusters will overlap, hiding the presence of the total number of sources. This research evaluates the performance of different meta-heuristic algorithms when applied to the SPCT for selecting separation intervals. The results obtained from the measurements made in different test objects will allow determining the most appropriate technique for separating PD sources and electrical noise acting simultaneously over an insulation system. INDEX TERMS Partial discharge, electrical noise sources, meta-heuristic approach, spectral power clustering technique, clustering.

Separation Techniques of Partial Discharges and Electrical Noise Sources: A Review of Recent Progress

“…Subsequent works evaluated the application of different optimization techniques such as: particle swarm optimization [63,65], genetic algorithms [66], hill climbing [63,64] and differential evolution [64]. The results confirmed better separation than that obtained manually and with the automatic selection algorithm.…”

“…Finally, with the values of PRL and PRH, a two-dimensional separation map called PR (Power Ratio) map is established and the clusters associated with each source are formed. As indicated in [61][62][63][64] k-means was used to search for groups on PR maps. The results obtained with this technique show that up to four different sources of PD and electrical noise can be separated, even if they are simultaneously acting [62].…”

A new technique for separation of partial discharge sources and electromagnetic noise in radiofrequency measurements using energy ratios of different antennas

“…In this case, the 5-cm monopole is optimised to 1.5 GHz, the 10-cm monopole to 0.75 GHz and the 15-cm monopole to 0.5 GHz. More information about these antennas and the measurement circuit used can be found in References [5,7,8,10]. As observed in Figure 1, the signal acquisition in the test objects was carried out through two different antennas (A 1 and A 2 ).…”

“…Most of the works in literature have mainly focused on the separation of sources for the very high frequency (VHF) range from inductive and/or capacitive sensors [9][10][11]. Due to the complex spectral and temporal characteristics of the signals captured by the antennas, the application of these VHF techniques cannot be considered a good alternative when it comes to performing a correct separation in UHF measurements [7].…”