2008
DOI: 10.1051/meca:2008001
|View full text |Cite
|
Sign up to set email alerts
|

Analyse spectrale singulière des signaux vibratoires et Machine Learning pour la surveillance d'usure d'outils

Abstract: Cetteétude explore l'utilisation des techniques de Machine Learning pour la classification de l'état d'outils en usinage. Une analyse spectrale singulière (ASS) pseudo-locale des signaux vibratoires relevés sur le porte-outil, coupléeà un filtrage passe-bande a permis la définition et la mise enévidence d'indicateurs très sensiblesà l'évolution de l'état de l'outil. Ces indicateurs sont définisà partir des sommes des raies spectrales des signaux reconstruits par ASS et de leurs résidus, dans des gammes de fréq… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2

Citation Types

0
2
0

Year Published

2022
2022
2023
2023

Publication Types

Select...
1
1

Relationship

0
2

Authors

Journals

citations
Cited by 2 publications
(2 citation statements)
references
References 20 publications
0
2
0
Order By: Relevance
“…The rolling bearing is one of the machine's elements present in most industrial plants, and its failure can lead to severe consequences in the production process [1]. Therefore, it is critical to monitor the defect from the very beginning of its occurrence [2]. The vibration analysis technique has already been used in several research projects.…”
Section: Introductionmentioning
confidence: 99%
See 1 more Smart Citation
“…The rolling bearing is one of the machine's elements present in most industrial plants, and its failure can lead to severe consequences in the production process [1]. Therefore, it is critical to monitor the defect from the very beginning of its occurrence [2]. The vibration analysis technique has already been used in several research projects.…”
Section: Introductionmentioning
confidence: 99%
“…The singular spectrum analysis (SSA) is a time series analysis technique based on decomposing the original signal into independent ones, the sum of which gives the starting signal. These independent components are reconstructed to distinguish the trending component, the oscillatory content, and the noise, respectively [2]. On the other hand, envelope analysis (EA) demodulates the system's resonant response, followed by frequency shifting and low-pass filtering in the time domain.…”
Section: Introductionmentioning
confidence: 99%