Detection and classification of partial discharge using a feature decomposition-based modular neural network

IEEE Transactions on Instrumentation and Measurement

Volumn 50, Issue 5, 2001, Pages 1349-1354

  Hong, Tao ^b,c   Fang, M T C ^a,d  

^a IEEE

^b Nestor Inc   (United States)

^c ACI Worldwide   (United States)

^d UNIVERSITY OF LIVERPOOL   (United Kingdom)

Author keywords

Back propagation network; Feature decomposition; Multiple neural networks (MNNs); Network generalization; Partial discharge classification; Pattern recognition

Indexed keywords

BACKPROPAGATION; FEATURE EXTRACTION; NEURAL NETWORKS; PARTIAL DISCHARGES; STATISTICAL METHODS;

FEATURE DECOMPOSITION; MODULAR NEURAL NETWORK;

ELECTRIC VARIABLES MEASUREMENT;

EID: 0035483913     PISSN: 00189456     EISSN: None     Source Type: Journal    
DOI: 10.1109/19.963209     Document Type: Article

References (24)

1. Partial discharge: Overview and signal generation
2. Partial discharge measurement and interpretation
3. Partial discharge measurements for insulation quality
4. Digital techniques for partial discharge measurements
5. Investigation of partial discharges in SF6 using computer based data acquisition system
6. Computer-aided recognition of discharge sources
7. Classification of partial discharge
8. The importance of statistical characteristics of partial discharge data
9. Neural networks as a tool for recognition of partial discharges
10. Discrimination of partial discharge patterns using a neural network
11. Pattern recognition of partial discharge in XLPE cables using a neural network
12. Partial discharge pattern classification using multilayer neural networks
13. Pruning algorithms: A survey
14. Nonlinear black-box modeling in system identification: A unified overview
15. Function approximation - A fast-convergence neural approach based on spectral analysis
16. Improving model accuracy using optimal linear-combinations of trained neural networks
17. The ensemble approach to neural-network learning and generalization
18. Bagging predictors
19. Adaptive mixtures of local experts
20. Efficient classification for multiclass problems using modular neural networks
21. Back propagation neural nets with one and two hidden layers
22. ANFIS: Adaptive-network-based fuzzy inference systems
23. Using additive noise in BP training
24. Stopped training and other remedies for over-fitting