What question did this study set out to answer?

To develop an automated rolling bearing fault diagnosis method combining one-dimensional and two-dimensional convolutional neural networks to extract multi-domain features from noisy vibration data.

June 23, 2022EnergiesOpen Access

The Method of Rolling Bearing Fault Diagnosis Based on Multi-Domain Supervised Learning of Convolution Neural Network

View Full Paper

Ask AI

Bookmark

Authors

XLXuejun LiuBeijing Institute of Petrochemical Technology WSWei SunHunan University of Technology HLHongkun LiDalian University of Technology

Discussion

Member takes

Implication

Validation study demonstrates high fault detection accuracy in bearing datasets, highlighting robust automated machinery health monitoring under noisy conditions.

Key Points

To develop an automated rolling bearing fault diagnosis method combining one-dimensional and two-dimensional convolutional neural networks to extract multi-domain features from noisy vibration data.
Constructed a hybrid architecture integrating 1D and 2D convolutional neural networks (CNN) with padding and dropout regularization to extract features across two informational domains.
Evaluated the diagnostic framework using experimental vibration data from the Case Western Reserve University (CWRU) and Dalian University of Technology (DUT) bearing datasets under standard and high-noise conditions.
Achieved high recognition accuracy across various rolling bearing fault states via multi-domain supervised learning without requiring manual feature engineering.
Maintained superior fault diagnosis performance and robustness when evaluated on vibration signals subjected to strong background noise.

Cite This Study

Liu et al. (2022) studied this question.

synapsesocial.com/papers/6a200405c1b320180d0dcaa0 https://doi.org/10.3390/en15134614

View Full Paper

Ask AI

Bookmark

Implication

Validation study demonstrates high fault detection accuracy in bearing datasets, highlighting robust automated machinery health monitoring under noisy conditions.

The Method of Rolling Bearing Fault Diagnosis Based on Multi-Domain Supervised Learning of Convolution Neural Network

Discussion

Member takes

Implication

Key Points

Cite This Study

The Method of Rolling Bearing Fault Diagnosis Based on Multi-Domain Supervised Learning of Convolution Neural Network

Discussion

Member takes

Implication

Key Points

Cite This Study

Also Consider

Also Consider