Title :
Feature form extraction and optimization of induction machine faults using PSO technique
Author :
Medoued, Ammar ; Lebaroud, Abdesselam ; Laifa, Abdelaziz ; Sayad, D.
Author_Institution :
Dept. de Genie Electr., Univ. du 20 Aout, Skikda, Algeria
Abstract :
This paper presents a diagnosis method for induction machine faults investigation. The method is based on feature extraction and optimization. The feature form extraction is based on the time-frequency representation (TFR), which is designed for maximizing the separability between classes. A distinct TFR is designed for each fault class. The PSO algorithm is used for the feature form optimization. The classifier is designed with an artificial neural network. This method is validated on a 5.5-kW induction motor test bench.
Keywords :
electric machine analysis computing; fault diagnosis; induction motors; neural nets; particle swarm optimisation; time-frequency analysis; ANN; PSO technique; TFR; artificial neural network; fault class; fault diagnosis method; feature form extraction; feature form optimization; induction machine faults; induction motor test bench; particle swarm optimisation; power 5.5 kW; time-frequency representation; Discrete wavelet transforms; Inverters; Kernel; Monitoring; Neurons; Oils; Robustness; ANN; Induction Machine Diagnosis; PSO; Time-Frequency;
Conference_Titel :
Electric Power and Energy Conversion Systems (EPECS), 2013 3rd International Conference on
Conference_Location :
Istanbul
Print_ISBN :
978-1-4799-0687-1
DOI :
10.1109/EPECS.2013.6713029
