Fractal theory based pattern recognition of motor partial discharge
| Autor: | Kevin Cowan, Zhuo Ma, Donald M. Hepburn, Chengke Zhou |
|---|---|
| Rok vydání: | 2016 |
| Předmět: |
010302 applied physics
Engineering business.industry Condition monitoring Pattern recognition 01 natural sciences Data acquisition Fractal 0103 physical sciences Partial discharge Pattern recognition (psychology) Waveform Artificial intelligence Polar coordinate system business Representation (mathematics) |
| Zdroj: | 2016 International Conference on Condition Monitoring and Diagnosis (CMD). |
| DOI: | 10.1109/cmd.2016.7757963 |
| Popis: | On-line Partial Discharge (PD) monitoring is being increasingly adopted in an effort to improve the assessment of MV motors. This paper presents a novel method for autonomous analysis and classification of PD patterns recorded in situations in which a phase-reference voltage waveform is not available, as is often the case in on-line PD based insulation condition monitoring systems. The main contributions of the paper are a Polar PD (PPD) representation and a Fractal Theory based autonomous PD recognition method. PPD is applied to convert the traditional phase-resolved PD pattern into a circular form where raw PD data over a power cycle of 20 ms is shown in a polar form so that important information related to PD pattern is retained irrespective of the initial point when data acquisition starts. The fractal theory is then presented in detail to address the task of discrimination of six PD patterns related to motors, as outlined in IEC60034. The classification of known and unknown defects is calculated by centour score. Validation of the proposed method is demonstrated using data from laboratory experiments on three typical PD geometries. The results show that the proposed method performs effectively in recognizing single-source PDs. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|