Neuro-fuzzy and soft computing: a computational approach to learning and machine intelligence
Neuro-fuzzy and soft computing: a computational approach to learning and machine intelligence
Determination of neural-network topology for partial discharge pulse pattern recognition
IEEE Transactions on Neural Networks
| Hi-index | 0.00 |
A novel method for partial discharge (PD) pattern classification is proposed based on adaptive neurofuzzy inference system (ANFIS). It is used for classification of partial discharges signals occurring in internal voids. Three different void shapes are considered in this work, namely flat void, square void and narrow void. The initial input feature vector, used for the classification is based on 15 statistical parameters. These parameters characterize fully the PD signals. The structure of the ANFIS classifier is thoroughly described. Afterwards, discriminant analysis is implemented to reduce the dimension of the feature vector. Therefore, the complexity of the ANFIS structure is reduced and classifier performance improved. Also, assessments of the classifiers are presented.