Vibration-Based Detection of Bearing Damages in a Planetary Gearbox Using Convolutional Neural Networks
Round 1
Reviewer 1 Report
Dear Authors,
My comments and suggestions are included in attached file.
Comments for author File: 
Comments.pdf
Author Response
Please see the attachment
Author Response File: Author Response.pdf
Reviewer 2 Report
The fault diagnosis of two-stage planetary gearbox based on vibration analysis is always considered as a challenging problem in the field of machinery fault diagnosis. This paper is novel and interesting. But, I have some minor problems about this manuscript.
1. The improvement percentage in the results should be stated in the Abstract.
2. The real picture of a two-stage planetary gear box and its working principle should be provided in Section 2.1.
3. The difficulty of two-stage planetary gearbox fault diagnosis should be provided in Section 2.1.
4. In the current methods, the decomposition methods have been widely applied in the machinery fault diagnosis. Such as DOI: 10.1109/TIE.2022.3156156, 10.1016/j.ymssp.2021.108333, 10.1016/j.ymssp.2021.108202. These classic methods should be reviewed in Introduction. Compared with the feature extraction methods, the advantages of the proposed methods should be highlighted.
5. Also, the English should be improved.
The English should be improved.
Author Response
Please see the attachment.
Author Response File: Author Response.pdf
Reviewer 3 Report
This paper is intended to provide an approach for monitoring bearings in a two-stage planetary gearbox based on vibration analysis. However, some essential descriptions needed to be improved.
1 Experiment is performed under different speeds without loads. As the author stated that the vibration analysis under rough and highly stressful environmental conditions is related to the damage phenomena and loading conditions.
2 What is the type of distributed and localized damages, pitting, scoring, or excessive wear? Need to be more specific. What’s the degree of damages?
3 What’s the capacity of Training and testing samples for convolutional neural network (CNN)?
4 Table 2 presented in graphical or text form may be better.
Author Response
Please see the attachment.
Author Response File: Author Response.pdf
Round 2
Reviewer 3 Report
Accept.
