2000
DOI: 10.1006/mssp.2000.1297
|View full text |Cite
|
Sign up to set email alerts
|

Toward Helicopter Gearbox Diagnostics From a Small Number of Examples

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
3

Citation Types

0
30
0

Year Published

2000
2000
2023
2023

Publication Types

Select...
6
2

Relationship

0
8

Authors

Journals

citations
Cited by 39 publications
(30 citation statements)
references
References 10 publications
0
30
0
Order By: Relevance
“…Conventional statistical pattern recognition methods and artificial neural networks (ANNs) classifiers are studied based on the premise that the sufficient samples are available, which is not always true in practice [19]. Support vector machines (SVMs, as defined in Section 3) based on statistical learning theory that are of specialties for a smaller sample number have better generalization than ANNs and guarantee the local and global optimal solution are exactly the same [20].…”
Section: Introductionmentioning
confidence: 99%
“…Conventional statistical pattern recognition methods and artificial neural networks (ANNs) classifiers are studied based on the premise that the sufficient samples are available, which is not always true in practice [19]. Support vector machines (SVMs, as defined in Section 3) based on statistical learning theory that are of specialties for a smaller sample number have better generalization than ANNs and guarantee the local and global optimal solution are exactly the same [20].…”
Section: Introductionmentioning
confidence: 99%
“…In most cases, the modulation waveforms are also sinusoids with lower shaft orders, i.e., 1× and/or 2× the shaft frequency. In cases where the shaft has multiple gears, the signal will be more complex due to the cross gear modulation interaction [2]. When a localized tooth defect such as a tooth crack is present, the engagement of the cracked tooth will induce an impulsive change with comparatively low energy to the gear mesh signal.…”
Section: Introductionmentioning
confidence: 99%
“…Comparing two outstanding and application effective techniques in diagnosing rotating machineries, i.e., the artificial neural networks (ANNs) and the support vector machines (SVMs), the latter proves to attain higher accuracy and a better generalization power for a smaller number of training samples when used in non-linear pattern recognition tasks [8], [9]. This paper describes a multi-model approach for monitoring and diagnosing the health of bearings under different operation regimes such as speed, torque, stress and/or load.…”
Section: Introductionmentioning
confidence: 99%