Services on Demand
Journal
Article
Indicators
- Cited by SciELO
- Access statistics
Related links
- Cited by Google
- Similars in SciELO
- Similars in Google
Share
Tecnura
Print version ISSN 0123-921X
Abstract
RIVERA ROLDAN, Alejandro; BECERRA BOTERO, Miguel Alberto and GUZMAN LUNA, Jaime Alberto. Vibration signals stochastic analysis of induction motors for fault detection using empirical mode decomposition. Tecnura [online]. 2015, vol.19, n.44, pp.83-91. ISSN 0123-921X. https://doi.org/10.14483/udistrital.jour.tecnura.2015.2.a06.
This paper presents a vibration analysis on induction motors using Hidden Markov Models (HMM) applied to features obtained from the Empirical Mode Decomposition (EMD) and Hilbert-Huang transform to vibration signals obtained in the coordinates x and y, in order to detect malfunctions in bearings and bars. Additionally, a comparative analysis of the ability of the vibration signals in the x and y directions to provide information for failures detection is presented. Thus, an ergodic HMM initialized and trained by expectation maximization algorithm with convergence at 10e-7 and maximum iterations of 100 was applied to the feature space and its performance was determined by cross-validation with 80-20 with 30 fold for obtaining high performance fault detection in terms of accuracy.
Keywords : empirical mode decomposition; fault detection; Hidden Markov Models; induction motors; signal processing.