Coupling pairwise support vector machines for fault classification
Autor: | H. Hyotyniemi, S. Poyhonen, Antero Arkkio, Pedro Jover |
---|---|
Rok vydání: | 2005 |
Předmět: |
Majority rule
Structured support vector machine business.industry Computer science Applied Mathematics Spectral density Pattern recognition Perceptron Fault detection and isolation Computer Science Applications Support vector machine ComputingMethodologies_PATTERNRECOGNITION Control and Systems Engineering Pairwise comparison Artificial intelligence Electrical and Electronic Engineering business Induction motor |
Zdroj: | Control Engineering Practice. 13:759-769 |
ISSN: | 0967-0661 |
Popis: | Different coupling strategies to reconstruct a multi-class classifier from pairwise support vector machine (SVM)-based classifiers are compared with application to fault diagnostics of a cage induction motor. Power spectrum density estimates of circulating currents in parallel branches of the motor are calculated with Welch's method, and SVMs are trained to distinguish a healthy spectrum from faulty spectra and faulty spectra from each other. Majority voting, a mixture matrix and a multi-layer perceptron network are compared in reconstructing the global classification decision. The comparison is done with simulations and the best method is validated with experimental data. |
Databáze: | OpenAIRE |
Externí odkaz: |