Effectiveness of Partition and Graph Theoretic Clustering Algorithms for Multiple Source Partial Discharge Pattern Classification Using Probabilistic Neural Network and Its Adaptive Version: A Critique Based on Experimental Studies

Table 9

Classification capability of HGPNN for multiple source PD patterns.

Preprocessing; scheme	Phase window	No. of tuples	Training patterns	Classification capability (%)
Measures based on maximum	Φ-𝑞max-𝑛 (30°)	36	175	97
Measures based on maximum value	Φ-𝑞max-𝑛 (10°)	36	174	96.67
Measures based on minimum	Φ-𝑞min-𝑛 (10°)	36	188	93.6
Measures based on mean	AM-GM-HM-RM (10°)	36	186	90.5