Fault diagnostics of an electrical machine with multiple support vector classifiers
| Autor: | Marian Negrea, Heikki N. Koivo, Antero Arkkio, S. Poyhonen, H. Hyotyniemi |
|---|---|
| Rok vydání: | 2003 |
| Předmět: |
Electric machine
Electric motor Engineering business.product_category Structured support vector machine Artificial neural network business.industry Stator Pattern recognition computer.software_genre Fault (power engineering) law.invention Relevance vector machine Support vector machine ComputingMethodologies_PATTERNRECOGNITION law Data mining Artificial intelligence business computer |
| Zdroj: | Proceedings of the IEEE Internatinal Symposium on Intelligent Control. |
| Popis: | Support vector machine (SVM) based classification is applied to fault diagnostics of an electrical machine. Numerical magnetic field analysis is used to provide virtual measurement data from healthy and faulty operations of an electric machine. Power spectra estimates of a stator line current of the motor are calculated with Welch's method, and SVMs are applied to distinguish the healthy spectrum from faulty spectra. Multiple SVMs are combined with a majority voting approach to reconstruct the final classification decision. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|