Application of multi-comparational algorithms to classification of acoustic emission signals generated by partial discharges

This article concerned on the mechanism of functioning of two multi-comparational algorithms, that is: CMCA (Classic Multi-Comparational Algorithm) and OMCA (Optimised Multi-Comparational Algorithm). The range and possibility of application of frequency descriptors that explicitly characterise the acoustic emission (AE) signals from partial discharges (PD) were described. The method for selection of quantity of the standard waveforms for the purpose of the classification process, carried out using the tested algorithms was presented. In addition, there were showed results of the simulation, performed using the proposed algorithms and two databases containing the AE signal waveforms generated by basic forms of PD, which can occur in insulation systems of transformers. The efficiency of CMCA and OMCA algorithms in application for AE signals generated by PD, as well as the reason to complete the developed database by another class of waveforms due to the defect of insulation system that not being catalogued previously was demonstrated in the study.