Using multi-scale entropy and principal component analysis to monitor gears degradation via the motor current signature analysis. (June 2017)

• Record Type: Journal Article
• Authors: Aouabdi, Salim; Taibi, Mahmoud; Bouras, Slimane; Boutasseta, Nadir
• Is Part Of: Mechanical systems and signal processing. Volume 90(2017)
• Page Start: 298
• Page End: 316
• Publication Date: 2017-06
• Subjects: Gearbox -- Fault diagnosis -- Multi-scale entropy (MSE) -- Motor current signature analysis -- Principal component analysis (PCA); Structural dynamics -- Periodicals; Vibration -- Periodicals; Constructions -- Dynamique -- Périodiques; Vibration -- Périodiques; Structural dynamics; Vibration; Periodicals; 621
• DOI: 10.1016/j.ymssp.2016.12.027
• Languages: English
• ISSNs: 0888-3270

Abstract

Highlights: The detection of tooth pitting in the permanent regime of MCSA. The anomaly detection based on MSE algorithm SampEn in conjunction with multivariate statistics. The DWT denoising strategy is used to preprocess Statistics during MSE of the stator phase currents. Abstract: 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.