Improvement of Roller Bearing Diagnosis with Unlabeled Data Using Cut Edge Weight Confidence Based Tritraining

Joint Authors

Qin, Wei-Li
Zhang, Wen-Jin
Wang, Zhen-Ya

Source

Shock and Vibration

Issue

Vol. 2016, Issue 2016 (31 Dec. 2016), pp.1-9, 9 p.

Publisher

Hindawi Publishing Corporation

Publication Date

2016-11-23

Country of Publication

Egypt

No. of Pages

9

Main Subjects

Civil Engineering

Abstract EN

Roller bearings are one of the most commonly used components in rotational machines.

The fault diagnosis of roller bearings thus plays an important role in ensuring the safe functioning of the mechanical systems.

However, in most cases of bearing fault diagnosis, there are limited number of labeled data to achieve a proper fault diagnosis.

Therefore, exploiting unlabeled data plus few labeled data, this paper proposed a roller bearing fault diagnosis method based on tritraining to improve roller bearing diagnosis performance.

To overcome the noise brought by wrong labeling into the classifiers training process, the cut edge weight confidence is introduced into the diagnosis framework.

Besides a small trick called suspect principle is adopted to avoid overfitting problem.

The proposed method is validated in two independent roller bearing fault experiment vibrational signals that both include three types of faults: inner-ring fault, outer-ring fault, and rolling element fault.

The results demonstrate the desirable diagnostic performance improvement by the proposed method in the extreme situation where there is only limited number of labeled data.

American Psychological Association (APA)

Qin, Wei-Li& Zhang, Wen-Jin& Wang, Zhen-Ya. 2016. Improvement of Roller Bearing Diagnosis with Unlabeled Data Using Cut Edge Weight Confidence Based Tritraining. Shock and Vibration،Vol. 2016, no. 2016, pp.1-9.
https://search.emarefa.net/detail/BIM-1118816

Modern Language Association (MLA)

Qin, Wei-Li…[et al.]. Improvement of Roller Bearing Diagnosis with Unlabeled Data Using Cut Edge Weight Confidence Based Tritraining. Shock and Vibration No. 2016 (2016), pp.1-9.
https://search.emarefa.net/detail/BIM-1118816

American Medical Association (AMA)

Qin, Wei-Li& Zhang, Wen-Jin& Wang, Zhen-Ya. Improvement of Roller Bearing Diagnosis with Unlabeled Data Using Cut Edge Weight Confidence Based Tritraining. Shock and Vibration. 2016. Vol. 2016, no. 2016, pp.1-9.
https://search.emarefa.net/detail/BIM-1118816

Data Type

Journal Articles

Language

English

Notes

Includes bibliographical references

Record ID

BIM-1118816