Using multi-scale entropy and principal component analysis to monitor gears degradation via the motor current signature analysis
| Autor: | Slimane Bouras, Mahmoud Taibi, Nadir Boutasseta, Salim Aouabdi |
|---|---|
| Rok vydání: | 2017 |
| Předmět: |
0209 industrial biotechnology
Engineering business.industry Mechanical Engineering 020208 electrical & electronic engineering Aerospace Engineering Pattern recognition 02 engineering and technology Computer Science Applications Multi scale entropy Induction machine 020901 industrial engineering & automation Gear tooth Control and Systems Engineering Signal Processing Principal component analysis Phase currents 0202 electrical engineering electronic engineering information engineering Multiple time Entropy (information theory) Anomaly detection Artificial intelligence business Civil and Structural Engineering |
| Zdroj: | Mechanical Systems and Signal Processing. 90:298-316 |
| ISSN: | 0888-3270 |
| DOI: | 10.1016/j.ymssp.2016.12.027 |
| Popis: | This paper describes an approach for identifying localized gear tooth defects, such as pitting, using phase currents measured from an induction machine driving the gearbox. A new tool of anomaly detection based on multi-scale entropy (MSE) algorithm SampEn which allows correlations in signals to be identified over multiple time scales. The motor current signature analysis (MCSA) in conjunction with principal component analysis (PCA) and the comparison of observed values with those predicted from a model built using nominally healthy data. The Simulation results show that the proposed method is able to detect gear tooth pitting in current signals. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|
Full Text from ScienceDirect